Stage 9-1 Level View
Secondary 4 Benchmark Scores
Per-level benchmark view grouped by generation model and subject. Scores are derived from the Stage 9-0 evaluator reports without changing the underlying scoring algorithm.
Showing all Secondary 4 subjects. Pick a subject to recalculate the LLM scores, low-score review list, and detailed rows for that subview.
LLM Summary
Average scores grouped by the model that generated the Secondary 4 content.
| Generation Model | Artifacts | Overall | Missing Images | Language | Syllabus | Answers | Notation | Timing | Audio |
|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 4 | 84 | 9.4 | 45 | 9.5 | 9.7 | 9.0 | 9.5 | 9.2 | - |
| DeepSeek V4 Pro | 275 | 9.4 | 169 | 9.9 | 9.8 | 9.2 | 9.5 | 9.0 | - |
| Gemma 4 31B | 273 | 9.3 | 163 | 9.9 | 9.8 | 8.6 | 9.9 | 9.0 | 2.0 |
| Tencent HY3 Free | 269 | 8.8 | 175 | 9.8 | 9.2 | 7.9 | 9.9 | 8.9 | 7.0 |
| Kimi K2.6 Free | 41 | 9.1 | 40 | 10.0 | 9.9 | 8.7 | 9.8 | 9.0 | - |
| LongCat 2.0 LLM | 259 | 9.3 | 147 | 10.0 | 9.7 | 8.8 | 9.6 | 9.1 | - |
| Qwen3.6 Plus | 281 | 9.4 | 179 | 9.9 | 9.8 | 9.2 | 10.0 | 9.2 | 9.0 |
| Qwen3.7 Plus | 21 | 9.1 | 6 | 9.9 | 8.5 | 8.6 | 10.0 | 9.0 | - |
Subject Summary
Average scores grouped by subject inside Secondary 4.
| Subject | Artifacts | Overall | What You'll Learn | WTL <8.5 | Missing Images | Language | Syllabus | Answers | Notation | Timing | Audio |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Additional Mathematics | 128 | 9.1 | 9.6 | 0 | 80 | 10.0 | 9.6 | 8.9 | 9.9 | 8.8 | - |
| Chinese | 9 | 8.7 | 9.9 | 0 | 2 | 10.0 | 8.9 | 8.7 | 10.0 | 9.8 | 7.0 |
| Combined Science Biology | 94 | 9.5 | 9.2 | 0 | 82 | 10.0 | 10.0 | 9.0 | 9.9 | 9.5 | - |
| Combined Science Chemistry | 92 | 9.5 | 9.6 | 0 | 40 | 10.0 | 10.0 | 9.2 | 9.4 | 9.6 | - |
| Combined Science Physics | 86 | 9.3 | 9.1 | 0 | 61 | 9.9 | 9.9 | 9.3 | 9.2 | 9.5 | - |
| Elementary Mathematics | 129 | 9.2 | 9.6 | 0 | 115 | 10.0 | 9.9 | 9.0 | 9.7 | 8.9 | - |
| English | 20 | 8.9 | 9.8 | 0 | 16 | 9.4 | 9.3 | 7.6 | 10.0 | 8.8 | - |
| Geography | 102 | 9.4 | 9.3 | 0 | 96 | 9.9 | 9.8 | 8.8 | 9.9 | 8.9 | - |
| Higher Chinese | 92 | 8.8 | 10.0 | 0 | 12 | 9.7 | 8.7 | 8.2 | 10.0 | 9.1 | 5.5 |
| Higher Malay | 11 | 7.4 | 9.9 | 0 | 1 | 8.4 | 7.5 | 5.8 | 10.0 | 8.4 | - |
| Higher Tamil | 9 | 7.8 | 9.8 | 0 | 1 | 8.8 | 8.6 | 6.4 | 10.0 | 8.6 | - |
| History | 96 | 8.9 | 9.6 | 0 | 56 | 9.8 | 9.5 | 8.2 | 10.0 | 8.0 | - |
| Literature | 92 | 9.0 | 9.8 | 0 | 15 | 9.7 | 9.3 | 7.8 | 10.0 | 8.5 | - |
| Malay | 9 | 7.8 | 9.9 | 0 | 4 | 10.0 | 8.2 | 6.3 | 10.0 | 9.4 | - |
| Principles of Accounts | 74 | 9.6 | - | - | 1 | 10.0 | 10.0 | 9.6 | 9.8 | 9.6 | - |
| Pure Biology | 116 | 9.5 | 9.2 | 0 | 114 | 10.0 | 10.0 | 9.0 | 9.9 | 9.2 | - |
| Pure Chemistry | 115 | 9.5 | 9.6 | 0 | 65 | 10.0 | 10.0 | 9.0 | 9.4 | 9.5 | - |
| Pure Physics | 126 | 9.5 | 9.1 | 0 | 111 | 10.0 | 10.0 | 9.3 | 9.6 | 9.3 | - |
| Social Studies | 94 | 9.0 | 9.7 | 0 | 52 | 9.7 | 9.2 | 8.3 | 10.0 | 8.3 | - |
| Tamil | 9 | 7.3 | 9.8 | 0 | 0 | 8.8 | 7.2 | 6.8 | 10.0 | 8.9 | 7.0 |
LLM by Content Type
Model scores split by quizzes, papers, cheatsheets, parent guides, and audio scripts.
| Generation Model | Type | Artifacts | Overall | Missing Images | Language | Syllabus | Answers | Notation | Timing | Audio |
|---|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 4 | Cheatsheet | 15 | 9.2 | 9 | 8.7 | 9.9 | - | 9.3 | - | - |
| Claude Sonnet 4 | Paper | 27 | 9.3 | 20 | 9.9 | 9.6 | 8.8 | 9.5 | 9.0 | - |
| Claude Sonnet 4 | Parents Guide | 15 | 9.7 | 0 | 8.7 | 9.9 | - | 10.0 | - | - |
| Claude Sonnet 4 | Quiz | 27 | 9.3 | 16 | 9.9 | 9.6 | 9.1 | 9.4 | 9.5 | - |
| DeepSeek V4 Pro | Paper | 138 | 9.5 | 94 | 9.9 | 9.8 | 9.2 | 9.7 | 9.1 | - |
| DeepSeek V4 Pro | Quiz | 137 | 9.3 | 75 | 9.9 | 9.8 | 9.3 | 9.3 | 8.8 | - |
| Gemma 4 31B | Paper | 139 | 9.3 | 88 | 9.9 | 9.7 | 8.6 | 10.0 | 9.0 | - |
| Gemma 4 31B | Quiz | 134 | 9.3 | 75 | 9.9 | 9.8 | 8.7 | 9.9 | 9.1 | 2.0 |
| Tencent HY3 Free | Paper | 133 | 8.6 | 89 | 9.8 | 9.1 | 7.7 | 9.9 | 8.6 | - |
| Tencent HY3 Free | Quiz | 136 | 8.9 | 86 | 9.8 | 9.2 | 8.2 | 9.9 | 9.3 | 7.0 |
| Kimi K2.6 Free | Paper | 19 | 9.1 | 19 | 10.0 | 9.9 | 8.5 | 9.8 | 8.9 | - |
| Kimi K2.6 Free | Quiz | 22 | 9.2 | 21 | 10.0 | 9.8 | 8.8 | 9.8 | 9.1 | - |
| LongCat 2.0 LLM | Paper | 125 | 9.3 | 68 | 10.0 | 9.8 | 8.7 | 9.6 | 9.0 | - |
| LongCat 2.0 LLM | Quiz | 134 | 9.3 | 79 | 10.0 | 9.6 | 8.9 | 9.5 | 9.1 | - |
| Qwen3.6 Plus | Paper | 137 | 9.4 | 92 | 9.9 | 9.8 | 9.0 | 10.0 | 9.1 | - |
| Qwen3.6 Plus | Quiz | 144 | 9.5 | 87 | 10.0 | 9.9 | 9.3 | 9.9 | 9.2 | 9.0 |
| Qwen3.7 Plus | Paper | 4 | 9.4 | 3 | 10.0 | 10.0 | 8.8 | 10.0 | 8.8 | - |
| Qwen3.7 Plus | Quiz | 17 | 9.0 | 3 | 9.8 | 8.1 | 8.6 | 10.0 | 9.1 | - |
Needs Review: Scores Below 8.0
Artifacts with overall benchmark scores below 8.0 for the current level view.
| Overall | Model | Subject | Type | Stage | Topic / Paper | Language | Syllabus | Template | Answers | Notation | Timing | Audio | Comments |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6.1 | Tencent HY3 Free | Tamil | Paper | 5-2 | practice-paper-5 | 5.0 | 6.0 | 4.0 | 5.0 | 10.0 | 9.0 | - | The content is significantly below Secondary 4 (O-Level) standards. The vocabulary, sentence structures, and question complexity are more suited for Primary school levels. While it covers syllabus topics like idioms and grammar, the depth is insufficient for Sec 4. The answer key provides brief corrections but lacks the pedagogical depth required for a high-stakes exam preparation tool. |
| 6.3 | Tencent HY3 Free | Tamil | Paper | 5-2 | practice-paper-3 | 10.0 | 7.0 | 5.0 | 4.0 | - | 8.0 | - | The content is significantly below Secondary 4 (O-Level) standard; the passages and questions are at a Primary/Lower Secondary level. Section B (Error Correction) is logically flawed as the 'errors' provided in the text are actually grammatically correct, making the task impossible for a student. Section D is missing/merged incorrectly. The answer key provides some teaching notes for grammar, but the overall complexity does not match the 1157 syllabus requirements for Sec 4. |
| 6.3 | Tencent HY3 Free | Higher Malay | Quiz | 5-1 | oral-listening | 10.0 | 4.0 | 3.0 | 5.0 | 10.0 | 8.0 | - | The content is significantly below Secondary 4 Higher Malay standards. The listening passages are extremely basic (Primary/Lower Sec level) and do not reflect the complexity of O-Level Higher Malay oral components. The question format is a generic quiz rather than an exam-style oral assessment (which should focus on stimulus-based discussion and video-based presentation). The answer key provides marking points but lacks the depth required for higher-order thinking skills expected at this level. |
| 6.4 | Tencent HY3 Free | Higher Malay | Quiz | 5-1 | comprehension | 10.0 | 4.0 | 3.0 | 5.0 | 10.0 | 10.0 | - | The content is significantly below Secondary 4 Higher Malay standards. The passages are extremely short (approx 30-45 words), whereas the syllabus requires texts of ~200 to ~390 words. The questions are basic literal recall, lacking the higher-order thinking, inference, and evaluative skills required for the O-Level standard. While the language is correct, the depth is more suited to Primary school level. |
| 6.4 | Tencent HY3 Free | Social Studies | Quiz | 5-1 | ancient-civilisations | 9.0 | 2.0 | 4.0 | 5.0 | 10.0 | 9.0 | - | Major syllabus misalignment: The content covers 'Ancient Civilisations', which is a History/Geography topic and is NOT part of the Singapore Secondary 4 Social Studies syllabus. SS focuses on Citizenship, Governance, and Diversity. The quiz is also far too simple for Sec 4 level, resembling Lower Secondary or Primary school content. Question templates do not match the heavy emphasis on Source-Based Case Studies (SBCS) seen in actual SS exams. |
| 6.6 | Tencent HY3 Free | Higher Malay | Paper | 5-2 | practice-paper-3 | 10.0 | 7.0 | 6.0 | 4.0 | 10.0 | 5.0 | - | The content is significantly below Secondary 4 Higher Malay standards; the vocabulary and sentence structures are closer to Primary school level. While the paper structure mimics the Kertas 2 format, the texts are far too short and simplistic for the allocated marks and time. The answer key provides only brief points rather than detailed explanations for why specific words are correct or how to derive answers from the text, which is insufficient for a 'Higher' level student. |
| 6.7 | Tencent HY3 Free | History | Paper | 5-2 | practice-paper-1 | 10.0 | 10.0 | 4.0 | 5.0 | 10.0 | 4.0 | - | The paper is fundamentally flawed for Secondary 4 History. It asks 20 'essay' questions but assigns only 3 marks each, which is a contradiction in terms; a 3-mark question is a short-answer/structured response, not an essay. The difficulty is far too low as it only requires simple identification rather than the complex analysis/evaluation required at this level. The timing is unrealistic for the volume of writing requested, even if the marks are low. Answer key provides points but lacks the depth needed for actual essay guidance. |
| 6.8 | Tencent HY3 Free | Higher Malay | Paper | 5-2 | practice-paper-5 | 10.0 | 7.0 | 6.0 | 5.0 | 10.0 | 8.0 | - | The content is far too simple for Secondary 4 Higher Malay; the texts and questions resemble Lower Secondary or even Primary level. While it follows the Kertas 2 structure, the depth of comprehension and vocabulary is insufficient for the 'Higher' syllabus. The answer key provides marking points but lacks detailed explanations for why specific answers are correct, which is necessary for a new student. The paper format is incomplete as it only covers a fraction of the marks. |
| 6.8 | Tencent HY3 Free | History | Paper | 3-1 | prelim-paper-2 | 10.0 | 10.0 | 4.0 | 7.0 | 10.0 | 2.0 | - | Major structural failure in paper design. The total marks (80) do not match the sum of the questions, and the question count (20) is impossible to reconcile with the marks allocated for Section C. Section C questions are labeled as 12-mark essays but the answer key treats them as 4-mark short answers to fix the math. This makes the paper logically broken and unfinishable within 90 minutes if taken as written. |
| 6.9 | Gemma 4 31B | Higher Chinese | Quiz | 5-1 | oral-listening | 10.0 | 6.0 | 5.0 | 10.0 | 10.0 | 10.0 | 2.0 | The content is far too simple for Secondary 4 Higher Chinese; the vocabulary and sentence structures resemble Primary school level. Major flaw: it is a 'listening' quiz without any actual audio or even a full transcript to listen to, relying instead on vague 'Context' descriptions which makes it a reading comprehension task rather than a listening assessment. The syllabus requires complex discourse, but these are basic multiple-choice questions. |
| 7.0 | Claude Sonnet 4 | Higher Malay | Cheatsheet | 2-7 | cheatsheet | 1.0 | 10.0 | - | - | - | - | - | Major failure in language suitability: the artifact is a Malay subject cheatsheet but is written almost entirely in English. While the content is syllabus-accurate and high-quality, it fails the primary requirement for a Malay language resource. The cheatsheet structure is also too verbose, acting more like a syllabus summary than a high-signal, condensed cheatsheet. |
| 7.0 | LongCat 2.0 LLM | Additional Mathematics | Paper | 5-2 | practice-paper-5 | 10.0 | 9.0 | 9.0 | 5.0 | 10.0 | 7.0 | - | Major failure in the answer key. The model identifies mathematical errors in its own generated questions (Questions 1 and 7) but fails to provide a corrected paper, instead providing a long, rambling 'thought process' of failed attempts to fix the math. This makes the answer key useless for a student. While the question format and LaTeX are good, the logical inconsistency between the paper and the key is a critical defect. |
| 7.0 | Tencent HY3 Free | Higher Tamil | Paper | 5-2 | practice-paper-1 | 10.0 | 8.5 | 7.0 | 6.0 | - | 5.0 | - | The content is significantly below Secondary 4 Higher Tamil standards; the passages and questions are too simplistic and resemble Primary/Lower Secondary level. While it attempts to follow the syllabus structure (A1, A2, B3, C4, C5), the actual linguistic complexity is insufficient for O-Level preparation. The answer key provides marking points but lacks deep pedagogical explanations for a new student. Timing is also unrealistic as the tasks are too trivial for 90 minutes. |
| 7.0 | Tencent HY3 Free | History | Paper | 3-1 | prelim-paper-5 | 9.5 | 10.0 | 4.0 | 5.0 | 10.0 | 8.0 | - | The paper fails to follow the actual Secondary 4 History exam format. Real prelim papers consist of Source-Based Case Studies (SBCS) and Structured/Essay questions. This artifact is merely a list of 20 short-answer 'explain' questions, which does not exist in the O-Level/Sec 4 syllabus. The difficulty is far too low as it lacks source analysis and high-order evaluation. The answer key provides brief points but lacks the depth required for a student to understand how to construct a full historical argument. |
| 7.0 | Tencent HY3 Free | Tamil | Paper | 5-2 | practice-paper-4 | 10.0 | 8.5 | 6.0 | 4.0 | 10.0 | 8.0 | - | The content is significantly below Secondary 4 (O-Level) standards; the vocabulary and sentence structures are more aligned with Primary school levels. The answer key provides translations but lacks deep pedagogical explanations for grammar rules. The exam format lacks the complexity of actual O-Level Tamil papers (e.g., long-form comprehension passages). |
| 7.1 | LongCat 2.0 LLM | History | Quiz | 5-1 | ancient-civilisations | 9.0 | 2.0 | 7.0 | 8.0 | 10.0 | 5.0 | - | Major syllabus misalignment: The artifact covers 'Ancient Civilisations', which is not part of the provided Singapore Sec 4 History syllabus (which focuses on 19th-20th century global history). While the question structure and answer quality are high, the content is irrelevant to the specified curriculum. Difficulty is too low for Sec 4 level. |
| 7.1 | Tencent HY3 Free | History | Paper | 3-1 | prelim-paper-4 | 9.5 | 9.0 | 6.0 | 7.0 | 10.0 | 3.0 | - | The paper fails to follow the actual O-Level/Sec 4 History exam format. Real papers consist of a Source-Based Case Study (SBCS) and an Essay section; this artifact is a collection of 20 small 4-mark questions, which is not a standard assessment structure. The difficulty is too low as it lacks the depth of analysis required for 8-12 mark questions. Timing is unrealistic for the content density. Answer key is good for teaching but the paper structure itself is non-standard. |
| 7.1 | Tencent HY3 Free | Malay | Paper | 5-2 | practice-paper-3 | 10.0 | 7.0 | 5.0 | 6.0 | 10.0 | 9.0 | - | The content is significantly below Secondary 4 (O-Level) standards. The passages are extremely short (primary school level) and the questions are mostly literal retrieval rather than the higher-order thinking, inference, and evaluation required by the 1148 syllabus. While the format includes marks and timing, the depth of comprehension is insufficient for the level. |
| 7.1 | Tencent HY3 Free | Malay | Paper | 5-2 | practice-paper-5 | 10.0 | 7.0 | 5.0 | 5.0 | 10.0 | 10.0 | - | The content is significantly below Secondary 4 (O-Level) standards. The texts are extremely short (primary school level) and the questions are overly simplistic, lacking the depth of inference and critical thinking required by the 1148 syllabus. While the format includes marks and timing, the complexity of the language and comprehension tasks does not match the target level. |
| 7.2 | Tencent HY3 Free | Higher Tamil | Paper | 5-2 | practice-paper-2 | 10.0 | 8.5 | 6.0 | 5.0 | 10.0 | 9.0 | - | The content is significantly below Secondary 4 Higher Tamil standards; the passages and vocabulary are extremely basic (Primary/Lower Sec level). While it attempts to follow the syllabus structure (Paper 2 sections), the actual linguistic complexity is insufficient for O-Level preparation. The answer key provides marking points but lacks deep pedagogical explanations for why certain grammar rules apply. The error correction section (A2) focuses on word order rather than the complex grammatical errors expected at this level. |
| 7.2 | Tencent HY3 Free | Social Studies | Paper | 3-1 | prelim-paper-2 | 9.0 | 9.5 | 7.0 | 6.0 | 10.0 | 4.0 | - | The paper has significant structural issues. The total marks calculation is contradictory: Section C is listed as 20 marks but the individual questions sum to 46, and the paper total is stated as 80 while the components are inconsistent. The question count (20) is extremely high for a 90-minute Social Studies paper, making it impossible to complete within the timeframe. While the source-based questions are well-aligned with the syllabus, the sheer volume of questions makes the paper unrealistic for a prelim exam. Answer key provides good logic but lacks the depth required for high-mark essay questions. |
| 7.2 | Tencent HY3 Free | Tamil | Paper | 5-2 | practice-paper-1 | 10.0 | 6.0 | 5.0 | 7.0 | 10.0 | 9.0 | - | The content is significantly below Secondary 4 (O-Level) standards. The passages are extremely short (approx. 80-120 words) and use very basic vocabulary/sentence structures more suited to Primary school levels. O-Level Tamil requires complex narrative/informative texts and higher-order thinking. The paper format is decent, but the depth of comprehension and vocabulary is insufficient for the target stage. |
| 7.2 | Tencent HY3 Free | Tamil | Paper | 5-2 | practice-paper-2 | 10.0 | 6.0 | 5.0 | 7.0 | 10.0 | 9.0 | - | The content is significantly below Secondary 4 (O-Level) standards. The passages are extremely short (3-4 sentences) and the vocabulary/sentence structures are more suited for Primary school levels. While the format includes sections and marks, the depth of comprehension required is minimal and does not reflect the complexity of the 1157 syllabus. Answer key is clear but the questions lack the rigor expected for this stage. |
| 7.2 | Tencent HY3 Free | History | Quiz | 3-0 | ancient-civilisations | 9.0 | 2.0 | 7.0 | 8.0 | - | 9.0 | - | Major syllabus misalignment: The artifact covers 'Ancient Civilisations' (Egypt, Greece, Rome, Mesopotamia), which is not part of the Singapore Sec 3/4 History syllabus. The syllabus focuses on 19th/20th-century history (European control in SE Asia, WWI, WWII, Cold War). While the question structure and source-based skills are well-modeled after exam templates, the content is irrelevant to the target level's curriculum. |
| 7.2 | Tencent HY3 Free | History | Quiz | 5-1 | ancient-civilisations | 9.0 | 2.0 | 7.0 | 8.0 | - | 9.0 | - | Major syllabus misalignment: The content covers Ancient Civilisations (Egypt, Mesopotamia, Indus Valley, Greece), which is not part of the Singapore Secondary 4 History syllabus (which focuses on 19th-20th century Imperialism, WWI, WWII, and the Cold War). While the quiz structure and answer key quality are good, the topic is irrelevant to the specified curriculum level. |
| 7.3 | LongCat 2.0 LLM | Social Studies | Quiz | 3-0 | ancient-civilisations | 9.5 | 4.0 | 8.5 | 8.0 | 10.0 | 5.0 | - | Major syllabus misalignment: The content covers Ancient Civilisations (History/Geography topic), whereas the Sec 4 Social Studies syllabus focuses on Citizenship, Governance, Diversity, and Globalisation. The difficulty is too low for Sec 4; it reads like Lower Secondary History. The quiz is also truncated/incomplete. Question count and marks exceed the 45-minute timeframe. |
| 7.3 | Qwen3.7 Plus | History | Quiz | 5-1 | ancient-civilisations | 9.5 | 2.0 | 8.5 | 8.0 | - | 8.0 | - | Major syllabus misalignment: The artifact covers Ancient Civilisations, which is not part of the Singapore Sec 4 History syllabus (which focuses on 19th-20th century modern history). While the question structure and source-based skills are excellent and follow exam templates, the content is irrelevant to the specified level and syllabus. Difficulty is too low for Sec 4. |
| 7.3 | Tencent HY3 Free | History | Quiz | 5-1 | essay-explanation | 9.5 | 9.0 | 6.0 | 5.0 | 10.0 | 4.0 | - | Major mathematical inconsistency in the mark scheme: Section C is listed as 5 marks per question in the quiz, but the answer key corrects this to 2 marks to fit a 60-mark total. This makes the quiz impossible to grade as written. Additionally, 20 questions (including 5 essay-style) in 75 minutes is unrealistic for Secondary 4 History. The difficulty is uneven; Section A is too brief for a Sec 4 level, while Section C asks for essay-style depth but only allocates 2 marks in the key. |
| 7.5 | Gemma 4 31B | Higher Chinese | Paper | 3-1 | prelim-paper-3 | 10.0 | 7.0 | 8.0 | 5.0 | 10.0 | 8.0 | - | The content is significantly below Secondary 4 Higher Chinese standards; the texts and questions are more aligned with Lower Secondary or even Primary level. Major flaw in Section 1B: the prompt asks to find errors in a text that contains no errors, making the task impossible. Answer key lacks depth for comprehension and provides no pedagogical explanation for why specific vocabulary choices are correct. |
| 7.5 | LongCat 2.0 LLM | Additional Mathematics | Paper | 3-1 | prelim-paper-3 | 10.0 | 8.0 | 9.0 | 8.0 | 9.0 | 8.0 | - | The paper is significantly too easy for Sec 4 A-Math; it focuses almost exclusively on basic Coordinate Geometry and Circles, ignoring Calculus, Trigonometry, and Algebra required by the syllabus. Major issue: The model's own answer key identifies mathematical errors in its generated questions (e.g., Question 11 triangle is not right-angled, Question 12 forms a trapezium instead of a triangle), which is a critical failure for an exam artifact. |
| 7.5 | Qwen3.7 Plus | Social Studies | Quiz | 5-1 | ancient-civilisations | 9.0 | 2.0 | 7.0 | 8.0 | 10.0 | 9.0 | - | Major syllabus misalignment: The content focuses on 'Ancient Civilisations' (History/Geography topic), whereas the Singapore Sec 4 Social Studies syllabus is strictly issues-based (Citizenship, Diversity, Globalisation). While the question format (Source-Based Questions) is excellent and mimics exam style, the subject matter is irrelevant to the actual SS curriculum. Difficulty is also too low for Sec 4 level. |
| 7.5 | Tencent HY3 Free | Higher Chinese | Paper | 5-2 | practice-paper-5 | 10.0 | 7.0 | 6.0 | 8.0 | - | 9.0 | - | The paper is significantly easier than the actual Sec 4 Higher Chinese O-Level standard; the vocabulary and sentence structures are more aligned with Lower Secondary or Standard Chinese. While it follows the Paper 2 structure (Language Use, Comprehension 1, Comprehension 2), the marks and question depth are shallow. The answer key is good, providing reasoning for Section A and B. An image placeholder is present for the chart. |
| 7.5 | Tencent HY3 Free | Higher Tamil | Paper | 5-2 | practice-paper-5 | 10.0 | 8.0 | 6.0 | 5.0 | 10.0 | 9.0 | - | The content is significantly below Secondary 4 Higher Tamil standards; the vocabulary and sentence structures are too simplistic (closer to Primary/Lower Sec). Section A is logically flawed as it asks to fill in markers (அ, ஆ, இ) which are just sequence indicators, not content. The exam format lacks the complexity of actual O-Level Paper 2. Answer explanations are helpful but the questions themselves lack depth. |
| 7.5 | Tencent HY3 Free | History | Quiz | 3-0 | conflict-international-relations | 10.0 | 10.0 | 6.0 | 5.0 | 10.0 | 8.0 | - | The quiz is significantly too easy for Secondary 4 History. While the topics align with the syllabus, the marks assigned are extremely low (mostly 2 marks per question), which prevents any depth of analysis required for O-Level standards. Section C (Essay) questions are only worth 2 marks each, which is fundamentally incorrect for an extended response section. The question template fails to reflect the weightage of actual exam papers where SBQs and Essays carry much higher marks. |
| 7.5 | Tencent HY3 Free | Social Studies | Quiz | 3-0 | ancient-civilisations | 9.0 | 2.0 | 8.5 | 7.0 | 10.0 | 8.0 | - | Major syllabus misalignment: The content focuses on 'Ancient Civilisations' (History/Geography topic), whereas the Singapore Secondary 4 Social Studies syllabus is strictly issues-based (Citizenship, Diversity, Globalization). While the question format and SBQ skills are well-modeled after exam templates, the subject matter is irrelevant to the specified syllabus. Difficulty is too low for Sec 4 level. |
| 7.6 | Tencent HY3 Free | Tamil | Quiz | 5-1 | comprehension | 10.0 | 7.0 | 6.0 | 8.0 | - | 9.0 | - | The content is significantly below Secondary 4 (O-Level) standards. The passages are extremely short (2-3 sentences) and the vocabulary/sentence structures are more suited for Primary school levels. While the format (MCQ, Open-ended, Vocabulary) mimics an exam, the cognitive demand is too low for Sec 4. Language suitability is excellent as the content is almost entirely in Tamil. |
| 7.6 | Tencent HY3 Free | Tamil | Quiz | 5-1 | oral-listening | 10.0 | 6.0 | 4.0 | 10.0 | 10.0 | 10.0 | 7.0 | The content is significantly below Secondary 4 (O-Level) standards. The vocabulary and sentence structures are extremely basic, resembling Primary school level rather than the complex linguistic requirements of the 1157 syllabus. While the answer key provides excellent teaching notes, the quiz itself lacks the depth, nuance, and complex listening comprehension required for Sec 4. The format is a simple MCQ quiz rather than a formal oral listening assessment which usually involves more sophisticated audio-visual or long-form audio stimuli. |
| 7.7 | Gemma 4 31B | Higher Chinese | Paper | 3-1 | prelim-paper-1 | 10.0 | 7.0 | 8.0 | 6.0 | 10.0 | 8.0 | - | The content is significantly below Secondary 4 Higher Chinese standards. The texts are too short and simple (primary/lower secondary level), and the comprehension questions are mostly literal rather than inferential. The 'Word Replacement' section is logically flawed as it asks to replace words that are already correct. Answer key lacks deep pedagogical explanations for why specific answers are correct. |
| 7.7 | LongCat 2.0 LLM | Additional Mathematics | Paper | 5-2 | practice-paper-3 | 10.0 | 9.0 | 8.0 | 7.0 | 8.0 | 8.0 | - | Major issue: The paper contains several mathematically incorrect questions (Q11, Q13, Q14) where the 'show that' values or intersection conditions do not match the provided equations. The answer key identifies these errors but provides 'corrected' versions rather than fixing the paper itself. Difficulty is uneven, ranging from very basic coordinate geometry to complex circumcentre problems. Missing diagrams for geometry questions. |
| 7.7 | LongCat 2.0 LLM | Additional Mathematics | Paper | 3-1 | prelim-paper-2 | 10.0 | 9.0 | 8.0 | 8.0 | 9.0 | 8.0 | - | Major failure in mathematical consistency: Question 10 and Question 12 contain errors where the provided parameters do not match the required outcomes (no real intersection in Q10; triangle is scalene instead of isosceles in Q12). The model's internal monologue/correction is visible in the answer key, which is a major artefact. Difficulty is uneven due to these logical flaws. |
| 7.7 | Qwen3.6 Plus | Higher Chinese | Paper | 5-2 | practice-paper-1 | 1.0 | 8.5 | 7.0 | 9.0 | 10.0 | 9.0 | - | The language suitability score is low because the Section C reading passage is entirely in English, whereas a Secondary 4 Higher Chinese paper should feature Chinese texts for comprehension. The difficulty is too low for Higher Chinese; the reading passage is a simple English text with English questions, which is more aligned with English Language papers than Higher Chinese. The answer key is excellent and provides good reasoning. |
| 7.7 | Tencent HY3 Free | Higher Malay | Paper | 5-2 | practice-paper-1 | 10.0 | 8.5 | 9.0 | 5.0 | 10.0 | 8.0 | - | The content is significantly below Secondary 4 Higher Malay standards. The vocabulary and sentence structures used in the texts (e.g., 'Ali pergi ke pasar', 'Kereta itu sangat cepat') are more suited for Primary school levels. The answer key for Bahagian A2 is logically flawed and admits to not finding enough errors in the generated text. While the paper structure follows the Kertas 2 format, the actual linguistic complexity is insufficient for the 'Higher' level. |
| 7.7 | Tencent HY3 Free | Malay | Paper | 5-2 | practice-paper-1 | 10.0 | 8.0 | 7.0 | 6.0 | 10.0 | 9.0 | - | The content is significantly below Secondary 4 (O-Level) standards. The texts are extremely short and simple, more suitable for Primary school levels. The questions are mostly literal retrieval rather than the higher-order thinking/inference required by the 1148 syllabus. While the format (instructions, marks, timing) is present, the complexity of the language and the depth of comprehension are insufficient for the target level. |
| 7.7 | Tencent HY3 Free | Additional Mathematics | Quiz | 3-0 | graphs-coordinate-geometry | 10.0 | 9.0 | 8.0 | 6.0 | 10.0 | 9.0 | - | The quiz contains significant mathematical errors in the answer key. Q12 and Q16 are logically flawed (Q12 involves a point inside the circle making a tangent impossible; Q16 has a geometric contradiction between the perpendicularity requirement and the y-axis constraint). The answer key includes 'error checks' and meta-commentary within the solutions, which is inappropriate for a student-facing artifact. Difficulty is uneven, ranging from very basic to complex, but the logical inconsistencies undermine the quality. |
| 7.7 | Tencent HY3 Free | Additional Mathematics | Quiz | 5-1 | numbers-ratio-proportion | 10.0 | 4.0 | 5.0 | 10.0 | 10.0 | 10.0 | - | The content is significantly below Secondary 4 Additional Mathematics level. The topic 'Numbers, Ratio and Proportion' in A-Math typically involves complex algebraic manipulation, surds, or indices, whereas this quiz covers basic Lower Secondary Mathematics (ratio, direct/inverse proportion). It does not meet the rigor of the G3 syllabus. |
| 7.7 | Tencent HY3 Free | Higher Malay | Quiz | 5-1 | composition | 10.0 | 8.5 | 6.0 | 5.0 | 10.0 | 9.0 | - | The quiz is significantly too easy for Secondary 4 Higher Malay. It focuses on basic grammar (active/passive voice, conjunctions) and general essay structure which are more suited to Lower Secondary or Standard Malay. Higher Malay should focus on nuanced vocabulary, complex sentence structures, and sophisticated argumentative techniques. The exam format is a quiz rather than a formal paper component. Answer key provides good teaching notes but lacks step-by-step derivation for complex questions. |
| 7.8 | Claude Sonnet 4 | Higher Chinese | Cheatsheet | 2-7 | cheatsheet | 2.0 | 10.0 | - | - | - | - | - | The cheatsheet is highly comprehensive and aligns perfectly with the Sec 4 Higher Chinese syllabus. However, the language suitability is low because the main content is written in English rather than Chinese, which is inappropriate for a language subject cheatsheet. It should ideally provide the Chinese terms and concepts directly. |
| 7.8 | Claude Sonnet 4 | Higher Chinese | Parents Guide | 2-9 | parents-guide | 1.0 | 9.0 | - | - | - | - | - | Major failure in language suitability: The artifact is a Chinese subject parent guide, but the entire content is written in English. Per instructions, this receives a low languageSuitability score. The content itself is high quality, syllabus-aligned, and practically useful for parents, but fails the primary requirement for a Chinese subject artifact. |
| 7.8 | Gemma 4 31B | Higher Chinese | Paper | 5-2 | practice-paper-1 | 5.0 | 8.5 | 8.0 | 7.0 | 10.0 | 7.0 | - | The content is significantly below Secondary 4 Higher Chinese standards; the reading comprehension texts and questions are more aligned with Lower Secondary or even Primary school levels. Language use tasks are too simplistic. The answer key uses English for explanations, which is acceptable for support but the depth of reasoning is shallow. Timeframe is slightly inconsistent with the total marks/difficulty. |
| 7.8 | Gemma 4 31B | Higher Chinese | Paper | 3-1 | prelim-paper-5 | 10.0 | 8.0 | 7.0 | 6.0 | 10.0 | 8.0 | - | The paper is well-structured for Higher Chinese, but it is critically incomplete as the reading comprehension passages (the core of the exam) are replaced by placeholders. The answer key provides marking points but lacks deep pedagogical explanations for why specific vocabulary or nuances are correct, which is necessary for a 'new student' as per instructions. Language suitability is excellent. |
| 7.8 | Qwen3.6 Plus | Higher Chinese | Paper | 5-2 | practice-paper-2 | 10.0 | 8.5 | 7.0 | 7.0 | 10.0 | 8.0 | - | Language suitability is excellent. However, the difficulty is uneven: Section A (Word Replacement) contains significant meta-commentary and 'broken' logic where the model struggles to generate clean error sentences, leading to confusing instructions for students. Section B is too easy (Primary level comprehension), while Section C is appropriate. The answer key for Section A is messy due to the model's internal reasoning being left in the text. |
| 7.8 | Tencent HY3 Free | Higher Malay | Paper | 5-2 | practice-paper-4 | 10.0 | 8.5 | 7.0 | 6.0 | 10.0 | 9.0 | - | The content is significantly below Secondary 4 Higher Malay standards; the vocabulary and sentence structures are more suited for Primary school or Lower Secondary. While the paper format (marks/timing) mimics the syllabus, the actual linguistic complexity is too low. Answer key provides answers but lacks deep pedagogical explanations for why specific grammar choices are correct. |
| 7.8 | Tencent HY3 Free | History | Paper | 5-2 | practice-paper-4 | 9.5 | 9.0 | 6.0 | 7.0 | 10.0 | 9.0 | - | The paper is essentially a list of 3-mark short-answer questions rather than a standard Secondary 4 History paper which requires Source-Based Case Studies (SBCS) and structured/extended essays. While the content is syllabus-aligned, the format is highly atypical for the level; it lacks the depth and complexity of actual O-Level papers. The answer key is good for short answers but does not provide the depth needed for actual essay grading. |
| 7.8 | Tencent HY3 Free | History | Paper | 5-2 | practice-paper-5 | 9.5 | 9.0 | 6.0 | 7.0 | 10.0 | 6.0 | - | The paper lacks actual source documents (images/text extracts) for the source-based questions (Q11, Q15), providing only brief descriptions which makes them impossible to answer properly. The format is not a standard O-Level paper; it is a collection of short-answer and essay questions rather than the typical split between Section A (Source-Based) and Section B (Structured/Essay). The difficulty is uneven, jumping from 4-mark 'explain' questions to 8-mark 'how far' essays without the necessary scaffolding or source material. |
| 7.8 | Tencent HY3 Free | Social Studies | Paper | 3-1 | prelim-paper-5 | 9.5 | 9.0 | 7.0 | 6.0 | 10.0 | 8.0 | - | The paper is significantly too easy for a Secondary 4 Prelim. Section A sources are extremely short and lack the complexity of actual SEAB-style source-based questions. Section C 'Essay Explanations' are only 4 marks each, which does not reflect the actual weightage or depth of a Sec 4 Social Studies essay (usually 8-12 marks). The marking scheme provides answers but lacks the depth of reasoning required for high-level humanities assessment. |
| 7.8 | Tencent HY3 Free | Higher Tamil | Quiz | 5-1 | composition | 4.0 | 9.5 | 7.0 | 5.0 | 10.0 | 9.0 | - | Language suitability is penalized because the questions are written in English rather than Tamil, which is inappropriate for a Higher Tamil composition quiz. Syllabus adherence is excellent, covering specific Paper 1 requirements and grammar components. The answer key provides good teaching notes, though the quiz itself is more of a knowledge check than a practical composition exercise. |
| 7.8 | Tencent HY3 Free | Malay | Quiz | 5-1 | composition | 10.0 | 8.0 | 6.0 | 7.0 | 10.0 | 9.0 | - | The content is significantly below Secondary 4 (O-Level) standards. The questions focus on basic primary/lower secondary grammar (parts of speech) rather than the complex composition skills, nuanced vocabulary, and critical analysis required for G3 Malay 1148. While the format is clean and the Malay language is used correctly, the cognitive demand is too low for the target level. |
| 7.8 | Tencent HY3 Free | Malay | Quiz | 5-1 | comprehension | 10.0 | 9.0 | 6.0 | 7.0 | 10.0 | 10.0 | - | The content is significantly below Secondary 4 (O-Level) standards. The texts are extremely short (primary school level) and the questions only require literal retrieval rather than the higher-order thinking, inference, and evaluation required by the G3 syllabus. While the format mimics an exam, the cognitive demand is inappropriate for the level. |
| 7.8 | Tencent HY3 Free | Malay | Quiz | 5-1 | language-use | 10.0 | 9.0 | 6.0 | 5.0 | 10.0 | 10.0 | - | The content is significantly below Secondary 4 (O-Level) standards. The questions focus on basic primary/lower secondary grammar (identifying Kata Nama, Kata Kerja) rather than the complex language use, nuances, and contextual application required for the 1148 syllabus. While the Malay language usage is correct and the answer explanations are helpful, the difficulty level is inappropriate for the target stage. |
| 7.8 | Tencent HY3 Free | Social Studies | Quiz | 5-1 | conflict-international-relations | 9.5 | 9.0 | 7.0 | 6.0 | 10.0 | 7.0 | - | The content is high quality and syllabus-aligned. However, there is a major mathematical error in the exam paper format: the total marks stated (40) contradicts the sum of the sections (58). This would confuse students in a real exam. The question templates for Section B and C are good, but the marking scheme is slightly terse for a 'new student' as requested, though the teaching notes help. |
| 7.9 | DeepSeek V4 Pro | Higher Chinese | Paper | 5-2 | practice-paper-2 | 10.0 | 6.0 | 5.0 | 10.0 | 10.0 | 10.0 | - | The content is significantly below Secondary 4 Higher Chinese standards. The reading comprehension texts (community notice, news report, product ad) and the multiple-choice questions are more aligned with Primary 6 or Lower Secondary levels. Higher Chinese Sec 4 should involve complex literary analysis, implicit meanings, and long-form structured responses rather than simple factual retrieval from short advertisements. The marks/timing are consistent, and the answer explanations are excellent, but the academic rigor is insufficient for the level. |
| 7.9 | LongCat 2.0 LLM | History | Quiz | 3-0 | ancient-civilisations | 9.5 | 2.0 | 8.5 | 9.0 | 10.0 | 8.0 | - | Major syllabus misalignment: The artifact covers 'Ancient Civilisations' (Rome, Egypt, China, Greece), which is NOT part of the provided Singapore Sec 4 History syllabus (which focuses on 19th-20th century modern history). While the question format and answer quality are excellent, the content is irrelevant to the specified curriculum. Difficulty is uneven due to the topical mismatch. |
| 7.9 | Tencent HY3 Free | History | Paper | 3-1 | prelim-paper-3 | 9.5 | 9.0 | 6.0 | 8.0 | 10.0 | 7.0 | - | The paper fails to follow the standard O-Level/Sec 4 History Paper 3 format, which is typically a Source-Based Case Study (SBCS) consisting of several sources and specific question types (Inference, Comparison, Reliability, etc.). Instead, this is a collection of short-answer and essay questions. The difficulty is too low for a Prelim paper; questions are mostly 'Explain' or 'Identify' rather than high-order analysis. Marks and timing are inconsistent with actual exam structures. Answer key is good but the paper structure is not exam-derived in terms of format. |
| 7.9 | Tencent HY3 Free | Malay | Paper | 5-2 | practice-paper-2 | 10.0 | 8.5 | 7.0 | 6.0 | 10.0 | 9.0 | - | The content is significantly below Secondary 4 (G3) standards. The texts are extremely short (micro-texts) and the questions are mostly literal retrieval rather than the high-order inference, evaluation, and synthesis required for O-Level Malay. While the format is clean, the complexity of the passages and the depth of the questions are more suited for Primary or Lower Secondary levels. Answer key provides good teaching notes but lacks detailed step-by-step reasoning for complex questions. |
| 7.9 | Tencent HY3 Free | Additional Mathematics | Quiz | 3-0 | numbers-ratio-proportion | 10.0 | 4.0 | 7.0 | 9.0 | 10.0 | 10.0 | - | The content is significantly below Secondary 4 Additional Mathematics level. The topics (ratio, proportion, direct/inverse variation) are standard Secondary 3/4 Mathematics (E-Math) topics. A-Math should involve more complex algebraic manipulation, surds, or quadratic functions as per the syllabus. The questions are too basic for an A-Math student. |
| 7.9 | Tencent HY3 Free | Chinese | Quiz | 5-1 | oral-listening | 10.0 | 7.0 | 6.0 | 10.0 | 10.0 | 10.0 | 7.0 | The content is significantly below Secondary 4 (O-Level) standards; the vocabulary and sentence structures are more suited for Primary school or Lower Secondary. While it follows the 'Listening' theme, the complexity of the dialogues and news snippets lacks the depth required for the 1160 syllabus. The exam format is decent for a classroom quiz but does not mimic the actual O-Level paper structure (which uses specific audio segments and question types). |
Content Type Summary
Average scores grouped by content type.
Detailed Benchmark Rows
Topics, quiz variants, paper versions, cheatsheets, parent guides, and audio scripts listed individually.
Showing the first 250 of 1503 rows to keep this page responsive.
| Model | Type | Stage | Subject | Topic / Paper | Overall | Missing Images | Language | Syllabus | Template | Clean | Step Answers | Explanations | Notation | Paper Format | Difficulty | Time Fit | Focused Summary | Parent Guide | Audio Listenability | Audio Learning | Difficulty | Comments |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 4 | Cheatsheet | 2-7 | Additional Mathematics | cheatsheet | 9.7 | Yes | 10.0 | 10.0 | - | 10.0 | - | - | 9.0 | - | 10.0 | - | 9.0 | - | - | - | appropriate | High quality cheatsheet. Covers all major Sec 4 A-Math topics including Calculus, Kinematics, and Trigonometry. Uses effective summaries. Notation is mostly clean, though some complex fractions could benefit from more formal LaTeX rendering. No diagrams provided for graphs or geometry. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Combined Science Biology | cheatsheet | 9.7 | Yes | 10.0 | 10.0 | - | 10.0 | - | - | 10.0 | - | 9.0 | - | 9.0 | - | - | - | appropriate | High quality cheatsheet. Content aligns perfectly with the O-Level Combined Science Biology syllabus. Uses effective bulleted summaries rather than generic text. Missing diagrams for cell structures and heart anatomy which are essential for this subject. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Combined Science Chemistry | cheatsheet | 9.3 | Yes | 9.5 | 10.0 | - | 10.0 | - | - | 9.0 | - | 9.0 | - | 8.5 | - | - | - | appropriate | High quality cheatsheet. Content aligns perfectly with the O-Level Combined Science Chemistry syllabus. Uses effective bulleted summaries for key concepts. Notation for chemical formulas and subscripts is generally good, though some complex equations could benefit from more formal LaTeX. Missing diagrams for electronic configurations and salt preparation methods which are standard for this level. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Combined Science Physics | cheatsheet | 9.3 | Yes | 9.5 | 10.0 | - | 10.0 | - | - | 9.0 | - | 9.0 | - | 8.5 | - | - | - | appropriate | High quality cheatsheet. Covers all major Physics sections of the Combined Science syllabus. Uses clear bullet points and concise summaries. Notation is mostly correct, though some formulas could benefit from full LaTeX formatting. Lacks diagrams for wave properties, circuit diagrams, and ray diagrams which are essential for a physics cheatsheet. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Elementary Mathematics | cheatsheet | 9.7 | Yes | 10.0 | 10.0 | - | 10.0 | - | - | 9.0 | - | 10.0 | - | 9.0 | - | - | - | appropriate | High quality cheatsheet. Excellent syllabus coverage including advanced topics like radians and vectors. Uses effective concise summaries. Notation is mostly good, though some mathematical symbols like square roots and vectors could benefit from more formal LaTeX rendering. Missing diagrams for geometry and graphs which are essential for a math cheatsheet. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Geography | cheatsheet | 9.5 | Yes | 9.5 | 10.0 | - | 10.0 | - | - | - | - | 9.0 | - | 9.0 | - | - | - | appropriate | Excellent syllabus coverage following the 2023 framework. Uses effective bulleted summaries that act as high-quality three-point pointers. Language is perfectly pitched for Sec 4. Missing diagrams for tectonics and climate cycles which are essential for this subject. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Higher Chinese | cheatsheet | 7.8 | No | 2.0 | 10.0 | - | 10.0 | - | - | - | - | 9.0 | - | 8.0 | - | - | - | appropriate | The cheatsheet is highly comprehensive and aligns perfectly with the Sec 4 Higher Chinese syllabus. However, the language suitability is low because the main content is written in English rather than Chinese, which is inappropriate for a language subject cheatsheet. It should ideally provide the Chinese terms and concepts directly. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Higher Malay | cheatsheet | 7.0 | No | 1.0 | 10.0 | - | 10.0 | - | - | - | - | 10.0 | - | 4.0 | - | - | - | appropriate | Major failure in language suitability: the artifact is a Malay subject cheatsheet but is written almost entirely in English. While the content is syllabus-accurate and high-quality, it fails the primary requirement for a Malay language resource. The cheatsheet structure is also too verbose, acting more like a syllabus summary than a high-signal, condensed cheatsheet. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | History | cheatsheet | 9.4 | No | 9.5 | 9.8 | - | 10.0 | - | - | - | - | 9.0 | - | 8.5 | - | - | - | appropriate | High quality cheatsheet. Excellent syllabus alignment covering all major units including Cold War and Decolonisation. Uses effective bulleted summaries rather than generic pointers. Language is perfectly pitched for Sec 4. Could benefit from more explicit 'three-point' structural cues in some sections, but content is dense and useful. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Literature | cheatsheet | 8.6 | No | 9.5 | 9.0 | - | 10.0 | - | - | - | - | 8.5 | - | 6.0 | - | - | - | appropriate | Language is sophisticated and appropriate for Sec 4. Strong alignment with the 'Eye' framework and syllabus components (Prose, Poetry, Drama, Unseen). However, the cheatsheet fails to use useful three-point summaries, instead providing dense, generic paragraphs that are difficult to scan quickly during revision. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Principles of Accounts | cheatsheet | 9.8 | No | 10.0 | 10.0 | - | 10.0 | - | - | 10.0 | - | 9.0 | - | 9.5 | - | - | - | appropriate | Excellent cheatsheet. High syllabus coverage including specific O-Level topics like partnership and ratio analysis. Uses effective bulleted summaries rather than generic text. Notation is clear and accurate. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Pure Biology | cheatsheet | 9.8 | Yes | 10.0 | 10.0 | - | 10.0 | - | - | 10.0 | - | 9.0 | - | 9.5 | - | - | - | appropriate | Excellent cheatsheet. High syllabus coverage for Sec 4 Pure Bio. Uses effective bulleted summaries rather than generic text. Notation for chemical equations is correct. Missing diagrams for cell structures and heart/lung anatomy which are critical for biology. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Pure Chemistry | cheatsheet | 9.6 | Yes | 10.0 | 10.0 | - | 10.0 | - | - | 9.0 | - | 9.5 | - | 9.0 | - | - | - | appropriate | High quality cheatsheet. Excellent syllabus coverage for Sec 4 Pure Chemistry. Uses effective bulleted summaries rather than generic text. Notation is mostly good, though some chemical formulas could benefit from more formal LaTeX subscripting. Missing diagrams for dot-and-cross and electrolysis setups which are standard for this topic. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Pure Physics | cheatsheet | 9.4 | Yes | 10.0 | 10.0 | - | 10.0 | - | - | 9.0 | - | 9.0 | - | 8.5 | - | - | - | appropriate | High quality cheatsheet covering the full O-Level Pure Physics syllabus. Uses effective concise summaries. Notation is generally good, though some mathematical expressions could use more formal LaTeX formatting. Missing diagrams for motion graphs, circuits, and ray diagrams which are essential for a physics cheatsheet. |
| Claude Sonnet 4 | Cheatsheet | 2-7 | Social Studies | cheatsheet | 9.5 | No | 9.5 | 10.0 | - | 10.0 | - | - | - | - | 9.0 | - | 9.0 | - | - | - | appropriate | Excellent syllabus coverage for Sec 4 Social Studies. The cheatsheet uses effective bulleted summaries that act as high-quality three-point pointers for key concepts. Language is perfectly pitched for the level. No technical artefacts found. |
| Claude Sonnet 4 | Paper | 3-1 | Additional Mathematics | prelim-paper-1 | 8.2 | Yes | 10.0 | 9.0 | 8.0 | 9.0 | 7.0 | - | 10.0 | 9.0 | 4.0 | 8.0 | - | - | - | - | uneven | Major mathematical errors in question 3 and 6. Question 3 is unsolvable without a diagram, and the answer key admits it cannot find point C. Question 6 contains a geometric impossibility where the distance between centers equals the radius of the first circle, making the radius of the second circle zero. Difficulty is uneven due to these logical flaws. |
| Claude Sonnet 4 | Paper | 5-2 | Combined Science Biology | practice-paper-1 | 9.7 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level structure and marks distribution well. Note: Question 9(c) answer key contains a logical error where it suggests animal cells do not have a nucleus, which is incorrect; it should clarify that the student might be misidentifying the organelle. Images are missing but placeholders are correctly used. |
| Claude Sonnet 4 | Paper | 3-1 | Combined Science Biology | prelim-paper-1 | 9.7 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Biology syllabus and structure. Major issue: several questions (5, 6, 9, 11) refer to diagrams or graphs that are missing from the text. Marking scheme is excellent and provides clear point-based allocation. |
| Claude Sonnet 4 | Paper | 5-2 | Combined Science Chemistry | practice-paper-1 | 9.3 | Yes | 10.0 | 9.5 | 9.0 | 10.0 | 9.0 | - | 8.5 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level structure and marks well. Note: Several diagrams are represented by text placeholders rather than actual images. Calculation in 5(d)(iii) results in a yield > 100%, which is a minor logical error in question design. Notation is generally good but could use more consistent LaTeX for chemical formulas. |
| Claude Sonnet 4 | Paper | 3-1 | Combined Science Chemistry | prelim-paper-1 | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 8.0 | 10.0 | - | 9.0 | 10.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Combined Science Chemistry syllabus and structure. Missing diagrams for question 9 and 13 (graph space) are noted via placeholders. Notation is generally good, though some chemical formulas could benefit from more consistent LaTeX formatting. Marking scheme is excellent with clear step-by-step logic. |
| Claude Sonnet 4 | Paper | 5-2 | Combined Science Physics | practice-paper-1 | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 8.0 | 10.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Combined Science Physics structure and marks. Note: Images are represented by text descriptions rather than actual graphics. Notation is mostly clear but could benefit from more consistent LaTeX for mathematical expressions and units. |
| Claude Sonnet 4 | Paper | 3-1 | Combined Science Physics | prelim-paper-1 | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 9.0 | 8.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Combined Science Physics syllabus and structure. Marks and timing are realistic. Note: Several questions rely on diagrams that are currently represented by text placeholders. Difficulty is appropriate for a Prelim paper. |
| Claude Sonnet 4 | Paper | 5-2 | Elementary Mathematics | practice-paper-1 | 9.2 | Yes | 10.0 | 9.5 | 9.0 | 9.0 | 9.0 | - | 8.5 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows Sec 4 E-Math structure well. Notation is mostly good but some math symbols in the marking scheme could use more consistent LaTeX. Missing diagrams are clearly marked with placeholders. Difficulty is well-balanced across topics. |
| Claude Sonnet 4 | Paper | 3-1 | Elementary Mathematics | prelim-paper-1 | 9.0 | Yes | 10.0 | 9.5 | 9.0 | 10.0 | 9.0 | - | 10.0 | 9.5 | 6.0 | 8.0 | - | - | - | - | uneven | Major issue: Question 19 is mathematically incorrect as the triangle is not right-angled, which breaks the logic of the question. Difficulty is uneven; some questions are very basic while others (like the calculus-based kinematics in Q20) are more aligned with Additional Math than standard E-Math. Missing diagrams for Q9, Q16, and Q17. |
| Claude Sonnet 4 | Paper | 5-2 | Geography | practice-paper-1 | 9.1 | Yes | 9.5 | 9.0 | 8.5 | 10.0 | 8.5 | - | 10.0 | 9.0 | 8.5 | 9.0 | - | - | - | - | appropriate | The paper follows the syllabus well, covering Map Skills, Tourism, Tectonics, and Fieldwork. Major issue: Figure 3 and Figure 4 are missing actual images/maps, relying only on text descriptions. The marking scheme is high quality and provides clear guidance. |
| Claude Sonnet 4 | Paper | 3-1 | Geography | prelim-paper-1 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to the Sec 4 Geography syllabus (Tourism, Climate, Tectonics/Coastal). Question types (Data, Structured, Essay) match exam patterns. Answer key is excellent with clear mark allocation. Major issue is the reliance on text placeholders for essential diagrams/maps/graphs which are required for Geography Paper 1. |
| Claude Sonnet 4 | Paper | 5-2 | Higher Chinese | practice-paper-1 | 9.0 | No | 10.0 | 9.0 | 8.5 | 10.0 | 8.0 | 8.5 | 10.0 | 9.0 | 8.0 | 9.0 | - | - | - | - | appropriate | The paper is well-structured and follows the Higher Chinese syllabus for Language Use and Comprehension. The difficulty is appropriate for Sec 4, though Section A is slightly on the easier side compared to actual O-Level standards. The answer key is excellent, providing clear marking schemes and explanations for language choices. No major formatting issues found. |
| Claude Sonnet 4 | Paper | 3-1 | Higher Chinese | prelim-paper-1 | 9.1 | No | 10.0 | 8.5 | 9.0 | 10.0 | 8.0 | 9.0 | 10.0 | 9.5 | 7.5 | 9.0 | - | - | - | - | too easy | The paper follows the exam format well with clear instructions and marking schemes. However, the difficulty is slightly low for a Secondary 4 Higher Chinese Prelim; the reading passages are quite short and the vocabulary/comprehension questions are relatively straightforward compared to actual O-Level standards. The answer key is excellent, providing clear explanations and marking rubrics. |
| Claude Sonnet 4 | Paper | 5-2 | History | practice-paper-1 | 9.2 | Yes | 9.5 | 10.0 | 9.0 | 10.0 | 8.5 | - | - | 9.0 | 9.0 | 8.5 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 History syllabus (Nazi Germany and WWII). Question types (Inference, Utility, Comparison, Surprise, Evaluation) follow standard O-Level/Sec 4 formats. Note: Source C is a text description rather than an actual image, which is a missing image issue. Answer key is excellent, providing balanced L1-L3 marking schemes. The essay section is truncated in the artifact. |
| Claude Sonnet 4 | Paper | 3-1 | History | prelim-paper-1 | 9.6 | No | 10.0 | 10.0 | 9.5 | 10.0 | 8.5 | - | 10.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality prelim paper. Follows O-Level History structure (SBC and Essay) and syllabus topics perfectly. Answer key provides good frameworks and marking levels. Note: Section B answer key was truncated in the artifact. |
| Claude Sonnet 4 | Paper | 5-2 | Literature | practice-paper-1 | 8.9 | Yes | 9.5 | 9.0 | 8.5 | 10.0 | 7.0 | - | 10.0 | 9.0 | 8.5 | 9.0 | - | - | - | - | appropriate | The paper structure and marking scheme are high quality. However, it is a 'template' rather than a complete paper because the actual prose extracts are missing and replaced by placeholders. The answer key provides excellent sample responses for a specific text (Lord of the Flies) which helps demonstrate the expected depth. |
| Claude Sonnet 4 | Paper | 3-1 | Literature | prelim-paper-1 | 8.7 | Yes | 9.5 | 9.0 | 8.5 | 9.0 | 7.0 | - | 10.0 | 8.5 | 9.0 | 8.0 | - | - | - | - | appropriate | The paper follows the Sec 4 Literature syllabus well, covering Prose, Unseen Poetry, and Critical Response. Major issue: Section A, Question 2 contains a placeholder '[Extract showing a key moment...]' instead of the actual text required for the question. The answer key provides marking bands and frameworks rather than full model essays, which is appropriate for Literature. Timing is slightly tight for three 20-mark essay-style responses in 100 minutes. |
| Claude Sonnet 4 | Paper | 5-2 | Principles of Accounts | practice-paper-1 | 9.6 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 8.5 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with O-Level POA syllabus (Inventory, Ratios, Financial Statements). Answer key is excellent with clear workings. Minor format discrepancy: Paper 1 in syllabus is 1 hour/40 marks, whereas this is 1.5 hours/60 marks, but difficulty is appropriate for Sec 4. |
| Claude Sonnet 4 | Paper | 3-1 | Principles of Accounts | sa1-paper-1 | 9.2 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 9.0 | 8.0 | 9.0 | 8.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 POA syllabus. Marks and structure are mostly correct, though the total marks (50) and duration (1.5h) deviate from the standard Paper 1 (40 marks, 1h) specified in the syllabus. Notation is clean, using standard accounting formats. |
| Claude Sonnet 4 | Paper | 5-2 | Pure Biology | practice-paper-1 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns well with Sec 4 Pure Biology syllabus. Format includes instructions, marks, and timing. Answer key is detailed with marking points. Note: All diagrams are text placeholders and must be replaced with actual images for use. |
| Claude Sonnet 4 | Paper | 3-1 | Pure Biology | prelim-paper-1 | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 10.0 | 8.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns well with Sec 4 Pure Biology syllabus. Marks and timing are realistic. Major issue: multiple diagrams are represented by text placeholders instead of actual images. Difficulty is appropriate for a Prelim paper, though slightly leaning towards foundational topics. |
| Claude Sonnet 4 | Paper | 5-2 | Pure Chemistry | practice-paper-1 | 8.7 | Yes | 9.5 | 9.0 | 8.5 | 9.0 | 8.5 | - | 7.0 | 8.5 | 9.0 | 9.0 | - | - | - | - | appropriate | The paper covers key Sec 4 topics (Acids/Bases, Salts, Haber, Rate, Electrolysis, Organic) well. Major issue: several questions rely on diagrams (Rate of reaction, Electrolysis) that are only provided as text placeholders. Notation for chemical formulae is inconsistent, using plain text instead of proper LaTeX subscripts (e.g., H2SO4 instead of H₂SO₄ in some parts, though the answer key uses subscripts). The answer key is high quality with clear marking points. |
| Claude Sonnet 4 | Paper | 3-1 | Pure Chemistry | prelim-paper-1 | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 8.5 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality prelim paper. Missing diagrams for Question 2 and Question 6(b) are noted via placeholders. Notation is generally good but could use more consistent LaTeX for chemical formulae (e.g., H2SO4 vs H2SO4). Answer key is excellent with clear marking schemes. |
| Claude Sonnet 4 | Paper | 5-2 | Pure Physics | practice-paper-1 | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 9.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level structure (Section A/B) and marking conventions well. Notation is generally good, though some math symbols could use more formal LaTeX. Missing diagrams are clearly marked with placeholders. Difficulty is well-balanced for Sec 4 Pure Physics. |
| Claude Sonnet 4 | Paper | 3-1 | Pure Physics | prelim-paper-1 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 9.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality prelim paper. Content aligns well with Sec 4 Pure Physics syllabus (Electricity, Mechanics, Moments). Marking scheme is excellent with clear step-by-step working and mark allocation. Note: All diagrams are currently text placeholders and must be replaced with actual images. Notation is generally good, though some mathematical symbols could use more formal LaTeX formatting. |
| Claude Sonnet 4 | Paper | 5-2 | Social Studies | practice-paper-1 | 9.4 | No | 9.5 | 10.0 | 9.0 | 10.0 | 8.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Social Studies issues (Diversity, Globalisation). SBQ questions follow standard formats (Agreement, Usefulness, Surprise). Answer key provides good L1-L3 marking schemes. Note: The essay answer is truncated due to generation limits. |
| Claude Sonnet 4 | Paper | 3-1 | Social Studies | prelim-paper-1 | 9.1 | No | 9.5 | 9.0 | 8.5 | 10.0 | 8.0 | - | 10.0 | 9.0 | 9.0 | 8.5 | - | - | - | - | appropriate | High quality paper. Content aligns well with Sec 4 Social Studies issues (Globalisation, Diversity). Question types (SBQ and Structured Response) follow standard SEAB formats. Answer key provides excellent level-based descriptors. Note: The answer key for Question 5 is truncated. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Additional Mathematics | parents-guide | 10.0 | No | 10.0 | 10.0 | - | 10.0 | - | - | 10.0 | - | 10.0 | - | - | 10.0 | - | - | appropriate | Excellent parent guide. It accurately reflects the Sec 4 A-Math syllabus, including specific topics like R-formula, partial fractions, and calculus. The breakdown of exam content percentages aligns well with the provided evidence summary. Language is professional and helpful for parents. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Combined Science Biology | parents-guide | 9.7 | No | 9.5 | 10.0 | - | 10.0 | - | - | - | - | 9.0 | - | - | 10.0 | - | - | appropriate | Excellent parent guide. Language is professional yet accessible for parents. Highly aligned with the O-Level Combined Science Biology syllabus, specifically covering the four main sections (Cell Bio, Human Phys, Plant Bio, Genetics/Ecology) and assessment objectives. The 'Common Struggles' and 'Weekly Support Plan' sections provide high practical utility. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Combined Science Chemistry | parents-guide | 10.0 | No | 10.0 | 10.0 | - | 10.0 | - | - | - | 10.0 | 10.0 | - | - | 10.0 | - | - | appropriate | Excellent parent guide. It accurately reflects the O-Level Combined Science structure, weightages, and topic importance based on the provided syllabus. The advice on mathematical challenges and language precision is highly relevant to the Singapore context. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Combined Science Physics | parents-guide | 10.0 | No | 10.0 | 10.0 | - | 10.0 | - | - | - | 10.0 | 10.0 | - | - | 10.0 | - | - | appropriate | Excellent parent guide. It accurately reflects the O-Level Combined Science Physics syllabus structure, including the specific paper durations and marks. The advice on common struggles (mathematical, conceptual, and language precision) is highly relevant to the Secondary 4 level. No markdown errors or broken symbols found. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Elementary Mathematics | parents-guide | 9.8 | No | 10.0 | 10.0 | - | 10.0 | - | - | - | 9.0 | 10.0 | - | - | 10.0 | - | - | not applicable | High quality parent guide. Language is professional and empathetic. Accurately reflects the O-Level E-Math structure (Paper 1 and 2 durations/weighting) and syllabus domains. Provides practical, actionable advice for parents without adding unsupported academic demands. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Geography | parents-guide | 10.0 | No | 10.0 | 10.0 | - | 10.0 | - | - | - | - | 10.0 | - | - | 10.0 | - | - | appropriate | Excellent parent guide. It accurately reflects the 2023 syllabus clusters (Everyday Life, Tourism, Climate, Tectonics, Singapore) and correctly identifies the emphasis on data interpretation and fieldwork. The advice on avoiding generic examples and improving evaluation skills is highly relevant to Sec 4 Geography requirements. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Higher Chinese | parents-guide | 7.8 | No | 1.0 | 9.0 | - | 10.0 | - | - | - | - | 10.0 | - | - | 9.0 | - | - | appropriate | Major failure in language suitability: The artifact is a Chinese subject parent guide, but the entire content is written in English. Per instructions, this receives a low languageSuitability score. The content itself is high quality, syllabus-aligned, and practically useful for parents, but fails the primary requirement for a Chinese subject artifact. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Higher Malay | parents-guide | 8.7 | No | 1.0 | 10.0 | - | 10.0 | - | - | 10.0 | 10.0 | 10.0 | - | - | 10.0 | - | - | appropriate | The guide is excellent in terms of syllabus alignment and practical advice for parents. However, it fails the language suitability requirement for a Malay subject; the entire guide is in English. While the prompt allows for English support notes, a parent guide for a Malay subject should ideally be in Malay or at least bilingual to be truly useful for the target demographic. Since the content is 100% English, the language score is heavily penalized. |
| Claude Sonnet 4 | Parents Guide | 2-9 | History | parents-guide | 10.0 | No | 10.0 | 10.0 | - | 10.0 | - | - | - | - | 10.0 | - | - | 10.0 | - | - | appropriate | Excellent parent guide. High syllabus alignment with specific mention of British Malaya, Nazi Germany, and Cold War. Provides practical, actionable advice for parents regarding source-based skills and essay structure. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Literature | parents-guide | 10.0 | No | 10.0 | 10.0 | - | 10.0 | - | - | - | - | 10.0 | - | - | 10.0 | - | - | appropriate | Excellent parent guide. It accurately reflects the Sec 4 Literature syllabus (Full vs Elective, Unseen Poetry, Set Texts). The distinction between technique spotting and analysis is highly relevant for this level. The weekly support plan is practical and age-appropriate. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Principles of Accounts | parents-guide | 10.0 | No | 10.0 | 10.0 | - | 10.0 | - | - | - | 10.0 | 10.0 | - | - | 10.0 | - | - | appropriate | Excellent parent guide. It accurately reflects the O-Level 7087 syllabus, including specific weighting, paper durations, and the unique 7-mark scenario question. The advice on common struggles (template dependency, ratio interpretation) is highly relevant to POA students. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Pure Biology | parents-guide | 9.9 | No | 9.5 | 10.0 | - | 10.0 | - | - | - | - | 10.0 | - | - | 10.0 | - | - | appropriate | Excellent parent guide. Language is professional yet accessible for parents. Highly aligned with the 6093 syllabus themes. Provides practical, actionable advice for home support and exam preparation without being overwhelming. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Pure Chemistry | parents-guide | 10.0 | No | 10.0 | 10.0 | - | 10.0 | - | - | - | - | 10.0 | - | - | 10.0 | - | - | appropriate | Excellent parent guide. It accurately reflects the O-Level Pure Chemistry syllabus weighting and structure. The advice is practical, age-appropriate, and provides actionable support strategies for parents without overstepping into teaching content. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Pure Physics | parents-guide | 10.0 | No | 10.0 | 10.0 | - | 10.0 | - | - | 10.0 | - | 10.0 | - | - | 10.0 | - | - | appropriate | Excellent parent guide. It accurately reflects the 6091 syllabus, correctly identifies paper weightings and timeframes, and provides high-quality, actionable advice for parents regarding mathematical and conceptual struggles. |
| Claude Sonnet 4 | Parents Guide | 2-9 | Social Studies | parents-guide | 10.0 | No | 10.0 | 10.0 | - | 10.0 | - | - | - | - | 10.0 | - | - | 10.0 | - | - | appropriate | Excellent parent guide. It accurately reflects the three major issues of the Sec 4 Social Studies syllabus, correctly identifies the Issue Investigation component, and provides highly practical advice for parents regarding source-based skills and current events connection. |
| Claude Sonnet 4 | Quiz | 3-0 | Additional Mathematics | graphs-coordinate-geometry | 9.2 | Yes | 10.0 | 10.0 | 8.5 | 10.0 | 10.0 | - | 10.0 | 9.0 | 6.0 | 9.0 | - | - | - | - | too easy | The quiz is significantly too easy for Secondary 4 Additional Mathematics; most questions are basic foundational skills (Sec 3 level) rather than challenging Sec 4 exam-standard questions. Question 7 explicitly references a diagram that is missing. Answer key is excellent with clear marking schemes. |
| Claude Sonnet 4 | Quiz | 5-1 | Additional Mathematics | graphs-coordinate-geometry | 8.4 | Yes | 10.0 | 9.0 | 8.0 | 10.0 | 4.0 | - | 10.0 | 9.0 | 7.0 | 9.0 | - | - | - | - | uneven | The answer key is highly unreliable; it contains multiple self-corrections, contradictory logic, and incorrect final answers (e.g., Q1, Q5, Q9c, Q11a, Q11b, Q11c). While the question difficulty is generally appropriate for Sec 4 A-Math, the mathematical errors in the solutions make the artifact unusable for study. Question 9 refers to a diagram that is missing. |
| Claude Sonnet 4 | Quiz | 3-0 | Combined Science Biology | cells-biomolecules | 9.1 | Yes | 10.0 | 9.0 | 8.0 | 10.0 | 9.0 | - | 10.0 | 8.0 | 8.0 | 10.0 | - | - | - | - | appropriate | The quiz contains several references to diagrams (cell types, leaf cross-section, photosynthesis graph) that are missing from the artifact. While the content is syllabus-aligned and the difficulty is appropriate for Sec 4, the lack of visual aids makes the questions unanswerable in their current state. Answer key is high quality with clear marking schemes. |
| Claude Sonnet 4 | Quiz | 5-1 | Combined Science Biology | cells-biomolecules | 9.3 | No | 10.0 | 9.5 | 8.5 | 10.0 | 9.0 | - | 10.0 | 9.0 | 8.5 | 9.0 | - | - | - | - | appropriate | High quality quiz. Content aligns well with Sec 4 Combined Science Biology. Section C is quite advanced (approaching Pure Bio level) but acceptable for high-ability students. Marks and timing are realistic. No notation issues found. |
| Claude Sonnet 4 | Quiz | 3-0 | Combined Science Chemistry | acids-bases-salts | 9.3 | No | 10.0 | 8.5 | 9.0 | 10.0 | 10.0 | - | 9.0 | 9.0 | 8.0 | 10.0 | - | - | - | - | appropriate | The quiz is well-structured and follows the exam-derived style. Syllabus adherence is slightly diluted as several questions (mixtures, bonding, CO, stoichiometry, atomic structure) belong to other topics rather than focusing strictly on Acids, Bases, and Salts as per the artifact title. Notation is generally good, though some chemical formulas could use more consistent LaTeX formatting. Difficulty is appropriate for Sec 4 Combined Science. |
| Claude Sonnet 4 | Quiz | 5-1 | Combined Science Chemistry | acids-bases-salts | 9.7 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 9.0 | 9.0 | 10.0 | 10.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with O-Level Combined Science Chemistry syllabus for Acids, Bases, and Salts. Notation is generally good, though some chemical formulas use plain text instead of LaTeX. The structure, marks, and timing are realistic for a 30-minute topical assessment. |
| Claude Sonnet 4 | Quiz | 3-0 | Combined Science Physics | summary | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 8.0 | 10.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality quiz covering multiple physics topics (Mechanics, Thermal, Waves, Electricity). Follows exam structure well. Note: Question 5(b) answer key has a calculation discrepancy (600/40 is 15, not 16). Missing diagrams are clearly marked with text descriptions. Notation is mostly plain text rather than LaTeX. |
| Claude Sonnet 4 | Quiz | 5-1 | Combined Science Physics | summary | 9.5 | Yes | 10.0 | 10.0 | 8.5 | 10.0 | 10.0 | - | 9.0 | 9.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality quiz. Missing actual image files for the velocity-time graph and the force diagram in Q10, though descriptions are provided. Notation is generally good, though some math symbols could use formal LaTeX. Marks and timing are well-structured. |
| Claude Sonnet 4 | Quiz | 3-0 | Elementary Mathematics | geometry-trigonometry | 8.3 | Yes | 10.0 | 9.0 | 8.0 | 10.0 | 7.0 | - | 9.0 | 9.0 | 4.0 | 9.0 | - | - | - | - | uneven | Major issue: Question 10 is mathematically flawed; the coordinates provided do not form a right-angled triangle, which the question explicitly asks to prove. Additionally, several questions (1, 3, 9) refer to 'the diagram' or 'the diagram below' but no images are provided. The difficulty is uneven, ranging from very basic trigonometry to complex sine/cosine rule applications. |
| Claude Sonnet 4 | Quiz | 5-1 | Elementary Mathematics | geometry-trigonometry | 9.1 | Yes | 10.0 | 10.0 | 8.0 | 10.0 | 9.0 | - | 9.0 | 8.0 | 9.0 | 9.0 | - | - | - | - | appropriate | The quiz is well-structured and covers the Sec 4 E-Math syllabus accurately. However, it is heavily reliant on diagrams (Questions 1, 2, 3, 12) which are missing, making the quiz impossible to attempt as-is. The answer key is excellent, providing clear marking schemes and reasoning. Notation is generally good, though some mathematical symbols could be more consistently rendered in LaTeX. |
| Claude Sonnet 4 | Quiz | 3-0 | Geography | map-graph-data-skills | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality quiz. Adheres well to Sec 4 Geography skills requirements (Map, Graph, Data). Answer key is excellent with clear marking schemes. Note: All visual aids (photographs, maps, graphs) are represented by placeholders and must be provided for the quiz to be functional. |
| Claude Sonnet 4 | Quiz | 5-1 | Geography | map-graph-data-skills | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with Sec 4 Geography syllabus (Map/Graph/Data/Fieldwork). Question types (Describe, Explain, Evaluate) match exam standards. Answer key is excellent with clear marking schemes. Note: Images are represented by descriptive placeholders which is expected for this artifact type. |
| Claude Sonnet 4 | Quiz | 3-0 | Higher Chinese | comprehension | 8.9 | No | 10.0 | 8.5 | 9.0 | 10.0 | 8.0 | 8.5 | 10.0 | 9.5 | 7.0 | 9.0 | - | - | - | - | too easy | The content is well-structured and follows the exam format well. However, the reading passages and vocabulary questions are significantly below the expected complexity for Secondary 4 Higher Chinese; the texts are quite simple and the vocabulary is more aligned with Lower Secondary or standard Chinese rather than the rigorous Higher Chinese O-Level standard. Answer explanations are good. |
| Claude Sonnet 4 | Quiz | 3-0 | History | essay-explanation | 9.5 | No | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | - | 9.0 | 10.0 | 9.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with Sec 4 History syllabus (Versailles, Stalin, Japan, Indonesia). Answer key provides excellent sample answers and marking schemes. Note: The answer key is truncated at the end of Question 6. |
| Claude Sonnet 4 | Quiz | 5-1 | History | essay-explanation | 9.1 | No | 9.5 | 10.0 | 9.0 | 8.0 | 9.0 | - | - | 9.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality essay-based quiz. Content aligns perfectly with the Sec 4 History syllabus (Versailles, Nazi rise, Cold War, Japanese Occupation). Answer key provides excellent model answers and level-based marking schemes. Note: The artifact is truncated at the end of the answer key for Question 7. No major formatting issues found. |
| Claude Sonnet 4 | Quiz | 3-0 | Literature | prose | 9.0 | Yes | 9.5 | 9.0 | 8.5 | 10.0 | 8.0 | - | - | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | The quiz is well-structured and aligns with Sec 4 Literature expectations (using Lord of the Flies as the prose text). However, Section B is critically flawed because the required passage is missing, replaced by a placeholder. The answer key provides good sample responses and marking notes, though it cannot provide specific answers for the missing passage. |
| Claude Sonnet 4 | Quiz | 5-1 | Literature | prose | 8.8 | No | 9.5 | 9.0 | 8.5 | 9.0 | 8.0 | - | - | 9.0 | 9.0 | 8.5 | - | - | - | - | appropriate | High quality quiz. Questions align well with Upper Secondary Literature requirements (analysis of style, character, and theme). The answer key is excellent, providing sophisticated sample responses and clear marking rubrics. Note: The answer key is truncated at the end. The quiz is designed for a specific text (Lord of the Flies) in the key, but the questions are generic enough for any prose text, which is a good design for practice. |
| Claude Sonnet 4 | Quiz | 3-0 | Principles of Accounts | inventory-costing | 9.5 | No | 10.0 | 9.0 | 8.5 | 10.0 | 10.0 | - | 10.0 | 9.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality quiz. Content aligns well with Sec 4 Inventory and Ratio analysis. Question 2 and 3 are slightly generic for a topic-specific quiz but acceptable for a warm-up. Answer key is excellent with clear marking schemes and workings. |
| Claude Sonnet 4 | Quiz | 5-1 | Principles of Accounts | inventory-costing | 9.7 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 9.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality quiz. Excellent coverage of FIFO, AVCO, and inventory ratios. Answer key provides clear marking schemes and step-by-step workings. Format closely mimics O-Level structured questions. |
| Claude Sonnet 4 | Quiz | 3-0 | Pure Biology | cells-biomolecules | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 9.0 | 8.5 | 10.0 | - | - | - | - | appropriate | High quality quiz. Adheres well to Sec 4 Pure Biology syllabus. Question 9a is a clever 'trick' question regarding unlabeled ribosomes, though it might be frustrating if not intended. Missing diagrams are clearly marked with placeholders. Answer key is excellent with clear marking schemes. |
| Claude Sonnet 4 | Quiz | 5-1 | Pure Biology | cells-biomolecules | 9.7 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 9.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with Sec 4 Pure Biology syllabus (Cells, Movement, Biomolecules, Enzymes). Answer key is excellent with clear marking points. Note: Question 6 requires a diagram which is currently a text placeholder. Marks and timing are realistic. |
| Claude Sonnet 4 | Quiz | 3-0 | Pure Chemistry | acids-bases-salts | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 8.0 | 9.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality quiz. Content aligns well with Sec 4 Acids, Bases and Salts syllabus. The answer key provides excellent step-by-step working for stoichiometry. Note: Question 8 contains a placeholder for a diagram that is not rendered. Notation is mostly clear but could benefit from more consistent LaTeX for chemical formulae (e.g., subscripts). |
| Claude Sonnet 4 | Quiz | 5-1 | Pure Chemistry | acids-bases-salts | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 9.0 | 9.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality quiz. Content aligns well with Sec 4 Pure Chemistry syllabus. Note: Question 12 requires a titration curve diagram which is missing. Notation is generally good, though some chemical formulas could use more consistent LaTeX formatting for subscripts. |
| Claude Sonnet 4 | Quiz | 3-0 | Pure Physics | electricity-magnetism | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 8.0 | 9.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality quiz. Content aligns well with Sec 4 Pure Physics syllabus. Answer key provides excellent step-by-step working and marking schemes. Minor notation improvement: use LaTeX for subscripts in formulas. Missing diagram for Question 7 is noted via placeholder. |
| Claude Sonnet 4 | Quiz | 5-1 | Pure Physics | electricity-magnetism | 9.6 | Yes | 10.0 | 9.5 | 9.0 | 10.0 | 10.0 | - | 9.0 | 9.5 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality quiz. Adheres well to Sec 4 Pure Physics syllabus. Includes necessary marks and instructions. Note: Question 10 requires a diagram which is currently a placeholder. Notation is generally good, though some mathematical expressions could use more formal LaTeX formatting for exponents and subscripts. |
| Claude Sonnet 4 | Quiz | 3-0 | Social Studies | essay-explanation | 9.7 | No | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 9.0 | 10.0 | 10.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with Sec 4 Social Studies issues (Smart Nation, Globalization, Diversity). SBA and ER questions follow standard SEAB-style command words and mark allocations. Answer key provides excellent structured frameworks for students. |
| Claude Sonnet 4 | Quiz | 5-1 | Social Studies | essay-explanation | 9.4 | No | 9.5 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality quiz. Questions align perfectly with the three major Social Studies issues. The marking scheme is excellent, providing clear breakdown of marks for position, explanation, and examples. The difficulty is appropriate for Sec 4. Note: While the quiz is 'Essay Explanation' focused, it lacks the Source-Based Question (SBQ) component typically found in actual SS papers, but as a topical quiz for essay skills, it is highly effective. |
| DeepSeek V4 Pro | Paper | 5-2 | Additional Mathematics | practice-paper-1 | 9.4 | Yes | 10.0 | 9.5 | 9.0 | 10.0 | 9.0 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns well with Sec 4 A-Math syllabus (Coordinate Geometry, Calculus, Logarithms). Format is professional with clear marks and instructions. Major issue: Question 11 refers to a diagram that is not provided, and Question 5/13 require graph plotting which lacks the actual grid/graph paper. Answer key is detailed and follows marking scheme logic. |
| DeepSeek V4 Pro | Paper | 5-2 | Additional Mathematics | practice-paper-3 | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns well with Sec 4 A-Math syllabus (Graphs, Circles, Calculus). Note: Question 15 requires a graph to be plotted, but no grid/graph paper is provided. The answer key is truncated at the end. |
| DeepSeek V4 Pro | Paper | 5-2 | Additional Mathematics | practice-paper-4 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns well with Sec 4 A-Math syllabus (Coordinate Geometry, Calculus, Linearisation). Marks and instructions follow exam standards. Note: Questions 13, 15, and 20 refer to diagrams/graphs that are missing in the text. Answer key is excellent and provides clear marking schemes, though truncated at the end. |
| DeepSeek V4 Pro | Paper | 5-2 | Additional Mathematics | practice-paper-5 | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 9.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 8.5 | - | - | - | - | appropriate | High quality paper. Content aligns well with Sec 4 A-Math syllabus. Marks and instructions follow exam standards. Note: Question 20 explicitly mentions a missing diagram, and Question 14b requires manual calculation/plotting which might be tight for a 90-minute window for 20 questions. Answer key is excellent and provides clear marking steps. |
| DeepSeek V4 Pro | Paper | 3-1 | Additional Mathematics | prelim-paper-1 | 8.9 | Yes | 10.0 | 9.5 | 9.0 | 8.5 | 9.0 | - | 9.5 | 10.0 | 7.0 | 8.0 | - | - | - | - | uneven | Major issue: Question 4 is mathematically incorrect (the triangle is not right-angled at B), which invalidates the 'Show that' instruction. The difficulty is uneven; Section A is standard coordinate geometry, but Section B introduces linearisation which is more advanced. Answer key is truncated at the end. Missing graph paper/axes for the linearisation questions. |
| DeepSeek V4 Pro | Paper | 3-1 | Additional Mathematics | prelim-paper-2 | 8.9 | Yes | 10.0 | 10.0 | 9.0 | 8.0 | 9.0 | - | 10.0 | 9.0 | 7.0 | 8.0 | - | - | - | - | uneven | Major issue: Question 3(b) is mathematically impossible with the provided coordinates (lines are not perpendicular). The model even detects this in the answer key but fails to fix the question. Difficulty is uneven; Section A/B are standard, but Section D (Linearisation) is quite heavy for a 90-minute paper. Missing grids for plotting questions. |
| DeepSeek V4 Pro | Paper | 3-1 | Additional Mathematics | prelim-paper-4 | 9.2 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 10.0 | 7.0 | 8.0 | - | - | - | - | uneven | Major issue: Question 3 contains a mathematical error where the provided coordinates do not form a right-angled triangle, making the 'Show that' instruction impossible. The difficulty is uneven, ranging from very basic coordinate geometry to complex kinematics and linear law. Missing diagrams for Question 11. Answer key correctly identifies the error in Q3 but the paper itself is flawed. |
| DeepSeek V4 Pro | Paper | 3-1 | Additional Mathematics | prelim-paper-5 | 8.7 | Yes | 10.0 | 10.0 | 9.0 | 8.0 | 7.0 | - | 10.0 | 10.0 | 6.0 | 8.0 | - | - | - | - | uneven | Major mathematical errors in the question/answer key: Q4(b) coordinates do not result in perpendicular lines; Q6(a) discriminant does not match the 'show that' target; Q7(c) geometric property is false for the given values. The model correctly identified its own errors in the marking scheme, but the paper itself is flawed. Difficulty is uneven due to these inconsistencies. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Biology | practice-paper-1 | 8.9 | Yes | 9.5 | 10.0 | 9.0 | 9.0 | 8.5 | - | 7.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | The paper is well-structured and aligns closely with the O-Level Combined Science Biology syllabus. It uses ASCII art to represent diagrams, which is a functional placeholder but lacks the professional visual quality of actual exam papers. Notation for chemical/biological processes is mostly plain text rather than LaTeX. The answer key is high quality, providing clear marking schemes and logic. The paper is truncated at the end. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Biology | practice-paper-2 | 9.7 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with O-Level Combined Science Biology syllabus. Marks and timing are realistic. Answer key is detailed with specific marking notes. Note: Images are represented by text placeholders which is expected for this artifact type. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Biology | practice-paper-3 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 9.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level structure and syllabus closely. Marks and timing are realistic. Note: Several diagrams are represented by text placeholders which must be replaced with actual images for use. Answer key is detailed with marking notes. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Biology | practice-paper-4 | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 9.5 | 9.5 | - | 10.0 | 9.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level structure well. Note: Images are replaced by text descriptions which is acceptable for LLM generation but requires manual insertion for real use. Marks and timing are realistic. Answer key is detailed and provides clear marking logic. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Biology | practice-paper-5 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Combined Science Biology syllabus. The paper uses descriptive placeholders for diagrams (e.g., 'Diagram: Red blood cell...') which is necessary for LLM generation but requires actual images for a real exam. Marking scheme is excellent, providing clear point-based allocation and acceptable variations. Note: The paper is truncated at the end of Section C. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Biology | prelim-paper-1 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 9.0 | 9.5 | - | 10.0 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Combined Science Biology structure and syllabus. Uses descriptive placeholders for missing diagrams which is helpful. Answer key is detailed with clear marking points. Note: The answer key for Question 6 is truncated. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Biology | prelim-paper-2 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.0 | 9.5 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with the O-Level Combined Science Biology syllabus. The structure (Section A, B, C) and mark allocation are realistic. Major issue: Question 1 and Question 5 refer to diagrams (Cell P/Q and Fluid Mosaic Model) that are not provided in the text, and Question 8 requires a grid for a graph that is missing. The answer key is excellent, providing specific marking points and expected terminology. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Biology | prelim-paper-3 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 9.0 | 9.5 | - | 10.0 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Combined Science Biology structure and syllabus. Marks and timing are realistic. Note: Diagram descriptions are used as placeholders for missing images. Answer key is detailed and follows marking scheme logic. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Biology | prelim-paper-4 | 9.8 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Combined Science Biology structure and syllabus. Marks and timing are realistic. Note: Images are represented by text placeholders which is expected for this artifact type. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Biology | prelim-paper-5 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Combined Science Biology structure and syllabus. Note: The paper relies heavily on 'Assume a diagram' placeholders which must be replaced with actual images for use. The answer key is excellent, providing clear marking points. The truncation at the end of Section B and the answer key is a minor technical artifact. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Chemistry | practice-paper-1 | 9.8 | No | 10.0 | 10.0 | 9.5 | 10.0 | 10.0 | - | 9.0 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level Combined Science Chemistry structure and syllabus (Acids, Bases, Salts, Redox, Stoichiometry) very well. Marks and timing are realistic. Answer key is excellent with clear marking schemes. Minor notation improvement: chemical formulas in text could use more consistent LaTeX for subscripts, though it is highly readable. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Chemistry | practice-paper-2 | 9.7 | No | 10.0 | 10.0 | 9.5 | 9.0 | 9.5 | - | 9.0 | 10.0 | 10.0 | 10.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level Combined Science Chemistry structure and marks distribution well. Notation is generally good, though some chemical formulas use subscript text rather than full LaTeX. The graph in Q4 is a text-based placeholder which is acceptable for this format. Answer key is detailed and provides marking schemes. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Chemistry | practice-paper-3 | 9.7 | No | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 9.5 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Excellent adherence to O-Level Combined Science Chemistry syllabus and structure. Marks and timing are realistic. Notation is clean, though some chemical equations could benefit from more formal LaTeX formatting for subscripts. Answer key is detailed and provides clear marking criteria. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Chemistry | practice-paper-4 | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 9.0 | 9.5 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. The graph in Question 16 is described via text but the actual image is missing. Notation is generally good, though some chemical formulas use subscript text rather than full LaTeX. The marking scheme is excellent and provides clear logic for marks. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Chemistry | practice-paper-5 | 9.7 | No | 10.0 | 10.0 | 9.5 | 10.0 | 10.0 | - | 9.0 | 10.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level Combined Science structure well. Notation is mostly good, though some chemical formulas use subscript text rather than full LaTeX, which is acceptable for markdown but less professional. Difficulty is well-calibrated for Sec 4. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Chemistry | prelim-paper-1 | 9.1 | Yes | 10.0 | 9.5 | 9.0 | 8.5 | 9.0 | - | 8.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | The paper is high quality and follows the O-Level Combined Science structure well. Major issue: The graph in Question 6 is provided as a text description rather than an image, and Question 8 is truncated. Notation for chemical equations is generally good but could benefit from more consistent LaTeX for subscripts. The QA section contains a logical contradiction between the brown gas test and the barium nitrate test which is noted in the marking scheme, suggesting a slight flaw in question design. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Chemistry | prelim-paper-2 | 9.3 | No | 10.0 | 10.0 | 9.5 | 8.0 | 9.0 | - | 9.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level Combined Science structure well. Note: The answer key for 4(e) contains a self-correction within the text which is helpful but should be cleaned for a final product. The paper is truncated at the end of Section C. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Chemistry | prelim-paper-3 | 9.8 | No | 10.0 | 10.0 | 9.5 | 10.0 | 9.5 | - | 10.0 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level Combined Science Chemistry structure and syllabus perfectly. Marks, timing, and instructions are accurate. Answer key provides excellent marking schemes with specific award criteria. Notation is clean. Only minor truncation at the very end of the answer key. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Chemistry | prelim-paper-4 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 10.0 | - | 9.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with O-Level Combined Science Chemistry syllabus (Acids, Salts, Redox, Organic). Note: Images for the graph in Q11c and the titration curve in Q16 are described in text but the actual visual assets are missing. Notation is generally good, though some chemical formulas could benefit from more consistent LaTeX formatting. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Chemistry | prelim-paper-5 | 9.7 | No | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 9.5 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality prelim paper. Follows O-Level Combined Science Chemistry structure and weighting perfectly. Questions cover key topics like Acids, Bases, Salts, and Stoichiometry. Answer key provides clear marking schemes and step-by-step calculations. Note: The answer key for Question 7 was truncated in the artifact. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Physics | practice-paper-1 | 9.2 | Yes | 10.0 | 10.0 | 9.0 | 9.0 | 10.0 | - | 8.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns well with O-Level Combined Science Physics syllabus. Marks and instructions follow standard exam formats. Note: Question 11 and 17 contain text-based descriptions of images/graphs instead of actual diagrams, which is a significant drawback for a practice paper. Notation is generally good but could benefit from more consistent LaTeX for mathematical expressions. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Physics | practice-paper-2 | 9.0 | Yes | 10.0 | 10.0 | 9.0 | 8.0 | 9.5 | - | 9.0 | 9.5 | 7.0 | 9.0 | - | - | - | - | uneven | The paper follows the O-Level format well. However, there is a significant logical error in MCQ Question 3 where the physics setup is impossible for a standard metre rule, which the answer key correctly identifies but the question itself remains flawed. Difficulty is generally appropriate but the error in Q3 makes the section uneven. Placeholder descriptions for graphs are used instead of actual images. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Physics | practice-paper-3 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 9.0 | 10.0 | - | 9.0 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level Physics Paper 2 structure and marks distribution well. Content covers Mechanics, Thermal, Waves, and Electricity accurately. Note: Images are represented by text descriptions/placeholders which must be replaced with actual diagrams for use. Answer key provides excellent marking schemes and ECF notes. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Physics | practice-paper-4 | 9.7 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 9.0 | 10.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Combined Science Physics syllabus. Note: Several questions (11a, 13, 14, 15a) rely on diagrams/graphs that are provided as text descriptions rather than actual images. Notation is generally good, though some mathematical symbols could use more formal LaTeX formatting. |
| DeepSeek V4 Pro | Paper | 5-2 | Combined Science Physics | practice-paper-5 | 9.7 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 9.0 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Combined Science Physics syllabus and structure. Marks and timing are realistic. Note: Images are provided as text descriptions/placeholders rather than actual graphics, which is expected for this artifact type but requires manual insertion. Notation is generally good, though some scientific notation could use formal LaTeX for better presentation. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Physics | prelim-paper-1 | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 8.0 | 10.0 | - | 9.0 | 10.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level structure and syllabus well. Note: The artifact is truncated at the end of Section C and contains ASCII-based graph placeholders instead of actual images. Notation is generally good, though some scientific notation in the answer key could use more formal LaTeX. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Physics | prelim-paper-2 | 9.4 | Yes | 10.0 | 10.0 | 9.5 | 9.0 | 9.5 | - | 8.5 | 10.0 | 9.0 | 9.5 | - | - | - | - | appropriate | High quality prelim paper. Follows O-Level structure and syllabus closely. Marks and timing are accurate. Note: Several diagrams are represented by text placeholders or ASCII, which is expected for this artifact type, but the answer key for 7(c) is truncated. Notation is generally good but could use more consistent LaTeX for scientific units and powers. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Physics | prelim-paper-3 | 9.4 | No | 10.0 | 10.0 | 9.5 | 9.0 | 9.5 | - | 8.5 | 10.0 | 9.0 | 9.5 | - | - | - | - | appropriate | High quality paper. Uses ASCII art for graphs and diagrams which is acceptable for markdown but lacks professional polish. Notation is mostly good but could use more consistent LaTeX for units and formulas. Marking scheme is excellent and provides clear breakdown for marks. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Physics | prelim-paper-4 | 9.7 | No | 10.0 | 10.0 | 9.5 | 9.0 | 10.0 | - | 9.0 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level Combined Science Physics structure and syllabus well. ASCII art used for graphs/circuits is clear. Answer key is excellent with detailed marking schemes. Minor truncation at the very end of the document. |
| DeepSeek V4 Pro | Paper | 3-1 | Combined Science Physics | prelim-paper-5 | 9.6 | Yes | 10.0 | 10.0 | 9.5 | 9.0 | 9.5 | - | 9.0 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Combined Science Physics structure and syllabus. Marks and timing are realistic. Answer key provides excellent step-by-step working. Note: The paper is truncated at the end, and while image placeholders are descriptive, the actual visual assets are missing. |
| DeepSeek V4 Pro | Paper | 5-2 | Elementary Mathematics | practice-paper-1 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Geometry and Trigonometry syllabus. Excellent step-by-step marking scheme. Major issue: several questions (1, 6, 7, 14, 18) rely on diagrams that are not provided, though the text describes them. Format is professional and timing is realistic. |
| DeepSeek V4 Pro | Paper | 5-2 | Elementary Mathematics | practice-paper-2 | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 9.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns well with Sec 4 Geometry and Trigonometry syllabus. Notation is correct. Note: Several diagrams are represented by text placeholders which must be replaced with actual images for a real exam. The marking scheme is detailed and provides clear method marks. |
| DeepSeek V4 Pro | Paper | 5-2 | Elementary Mathematics | practice-paper-3 | 9.3 | Yes | 10.0 | 10.0 | 9.0 | 9.0 | 9.0 | - | 10.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | The paper is high quality and follows the Sec 4 E-Math syllabus well. However, it is heavily dependent on diagrams (e.g., circle theorems, trigonometry, vectors) which are missing in the text-only output. The answer key is detailed but contains a minor calculation error in Q6 (result 11.3 vs 11.4) and Q14 (segment area calculation). The truncation at the end of the answer key is noted. |
| DeepSeek V4 Pro | Paper | 5-2 | Elementary Mathematics | practice-paper-4 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Geometry and Trigonometry syllabus. Format follows standard exam structures with marks and instructions. Note: Several questions rely on diagrams that are currently represented by text placeholders rather than actual images. Answer key is excellent, providing clear method marks and alternative solutions. |
| DeepSeek V4 Pro | Paper | 5-2 | Elementary Mathematics | practice-paper-5 | 9.3 | Yes | 10.0 | 9.5 | 9.0 | 10.0 | 8.5 | - | 10.0 | 9.5 | 8.5 | 9.0 | - | - | - | - | appropriate | The paper is high quality and follows the Sec 4 E-Math syllabus well, focusing on Geometry and Trigonometry. However, it is heavily reliant on diagrams (e.g., circle properties, bearings, triangles) which are entirely missing from the text, making the paper impossible to solve as presented. The answer key contains some internal reasoning/correction notes which should be cleaned up for a final version. |
| DeepSeek V4 Pro | Paper | 3-1 | Elementary Mathematics | prelim-paper-1 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 9.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Geometry and Trigonometry syllabus. Format is professional with clear instructions and marks. Major issue: many questions (1, 2, 7, 8, 9, 10, 12, 14, 15, 16, 18, 19) rely on diagrams that are not provided, making them impossible to solve as written. Answer key is excellent and provides clear method marks. |
| DeepSeek V4 Pro | Paper | 3-1 | Elementary Mathematics | prelim-paper-2 | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 8.5 | 9.0 | - | - | - | - | appropriate | The paper is high quality and follows the Sec 4 E-Math Paper 2 structure well. However, it relies heavily on diagrams (e.g., Q1, Q4, Q6, Q7, Q10) which are not rendered, making the paper unusable without the visual assets. The difficulty is appropriate for a Preliminary exam, focusing on Trigonometry, Geometry, and Bearings. The answer key is excellent, providing clear marking schemes and method marks (M1/A1), though it contains a self-correction note in Q4(d) which should be cleaned up in a final version. |
| DeepSeek V4 Pro | Paper | 3-1 | Elementary Mathematics | prelim-paper-3 | 9.2 | Yes | 10.0 | 10.0 | 9.0 | 8.0 | 9.0 | - | 9.0 | 10.0 | 8.5 | 9.0 | - | - | - | - | appropriate | The paper is high quality and follows the Sec 4 E-Math syllabus well, focusing on Trigonometry and Geometry. However, it is heavily reliant on diagrams (e.g., Q1, Q5, Q9, Q10, Q12, Q14, Q16, Q18, Q19, Q20) which are missing, making the paper impossible to solve as-is. The answer key contains some internal calculation inconsistencies (e.g., Q4 bearing and Q11 height) that require verification. |
| DeepSeek V4 Pro | Paper | 3-1 | Elementary Mathematics | prelim-paper-4 | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 9.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Geometry and Trigonometry syllabus. Format is professional with clear instructions and marks. Major issue: several questions (6, 7, 8, 10, 13, 15, 16, 17, 18, 19, 20) explicitly refer to diagrams that are not provided. Answer key is excellent and provides clear marking schemes. |
| DeepSeek V4 Pro | Paper | 3-1 | Elementary Mathematics | prelim-paper-5 | 9.3 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 8.0 | - | 10.0 | 9.5 | 8.5 | 9.0 | - | - | - | - | appropriate | The paper is high quality and follows the Sec 4 E-Math syllabus well. Major issue: several questions (1, 2, 3, 5, 6, 10) rely heavily on diagrams that are missing, making them impossible to solve as presented. The answer key contains a self-correction/recalculation in Question 1b and 3c, which is helpful but indicates the model struggled with internal consistency during generation. Difficulty is appropriate for a Prelim Paper 2. |
| DeepSeek V4 Pro | Paper | 5-2 | Geography | practice-paper-1 | 9.4 | Yes | 10.0 | 9.5 | 9.0 | 10.0 | 9.0 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Excellent alignment with Geography skills (Map, Graph, Data). Note: The paper relies heavily on 'Insert' placeholders for Figure 1, 2, and 3, which are essential for the questions to be functional. The answer key is detailed and provides clear marking schemes. |
| DeepSeek V4 Pro | Paper | 5-2 | Geography | practice-paper-2 | 9.2 | Yes | 9.5 | 9.0 | 8.5 | 10.0 | 9.0 | - | 10.0 | 9.0 | 9.0 | 8.5 | - | - | - | - | appropriate | High quality paper. Follows Singapore Sec 4 Geography structure well (Map Skills, Structured, Data Response). Marks and timing are realistic. Major issue: The paper relies heavily on 'Insert' figures which are not provided, making the paper impossible to complete as a standalone artifact. Answer key is excellent and provides clear marking rubrics. |
| DeepSeek V4 Pro | Paper | 5-2 | Geography | practice-paper-3 | 9.1 | Yes | 9.5 | 9.0 | 8.5 | 10.0 | 9.0 | - | 10.0 | 9.0 | 8.5 | 8.0 | - | - | - | - | appropriate | The paper is well-structured and aligns closely with the Geography syllabus, particularly the Map, Graph, and Data Skills cluster. However, it relies heavily on '(Insert)' placeholders for figures, maps, and photographs, making it impossible to actually attempt the paper. The marking scheme is high quality, providing clear guidance and tolerances. The timeframe is slightly optimistic given the complexity of drawing graphs and interpreting maps without the actual visual aids. |
| DeepSeek V4 Pro | Paper | 5-2 | Geography | practice-paper-4 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Excellent alignment with Geography syllabus (Tourism, Climate, Coastal processes). Marks and instructions follow exam standards. Answer key provides clear marking schemes and working steps. Note: Figure 3 and 5 are placeholders and require actual diagrams to be functional. |
| DeepSeek V4 Pro | Paper | 5-2 | Geography | practice-paper-5 | 9.0 | Yes | 9.5 | 9.0 | 8.5 | 9.0 | 8.5 | - | 10.0 | 9.0 | 9.0 | 8.5 | - | - | - | - | appropriate | High quality paper. Content aligns well with Sec 4 Geography clusters (Tourism, Climate, Coastal). Major issue: The paper relies heavily on 'Insert' placeholders (Figure 1, Figure 2, Photograph A) which are essential for Map Skills and Data Interpretation; without these, the paper is non-functional. Marking scheme is detailed and follows standard Singapore grading logic. |
| DeepSeek V4 Pro | Paper | 3-1 | Geography | prelim-paper-1 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to the Sec 4 Geography syllabus (Coastal, Climate, Tourism). Format is professional with clear mark allocations and instructions. Note: The paper relies heavily on 'Insert X' placeholders for images/maps/graphs which are necessary for the questions to be functional. Answer key provides excellent marking notes and logical steps for calculations. |
| DeepSeek V4 Pro | Paper | 3-1 | Geography | prelim-paper-2 | 9.6 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 Geography syllabus (Coastal, Tectonics, Tourism). Format is professional with clear mark allocation. Note: Multiple (Insert) placeholders for Figure 1, Photograph A, and Figure 2 are present, which is expected for an exam-derived template but requires actual assets for use. Answer key is detailed and provides clear marking criteria. |
| DeepSeek V4 Pro | Paper | 3-1 | Geography | prelim-paper-3 | 9.4 | Yes | 10.0 | 9.5 | 9.0 | 10.0 | 9.0 | - | 10.0 | 9.5 | 9.0 | 8.5 | - | - | - | - | appropriate | High quality paper. Adheres well to the Sec 4 Geography syllabus (Coastal, Tourism, Climate, Sustainability). Format is professional with clear mark allocations. Major issue: The paper relies heavily on 'Insert X' placeholders for photographs, maps, and diagrams which are not provided, making the paper non-functional for actual practice without the visual assets. The answer key is excellent, providing clear marking criteria and logical steps. |
| DeepSeek V4 Pro | Paper | 3-1 | Geography | prelim-paper-4 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 Geography syllabus (Coastal, Tectonics, Climate). Format is professional with clear mark allocation and timing. Note: Images are correctly marked as (Insert) but are physically missing from the artifact. Answer key is detailed and provides clear marking logic. |
| DeepSeek V4 Pro | Paper | 3-1 | Geography | prelim-paper-5 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Excellent adherence to the Geography syllabus (Coastal, Tourism, Climate). Format is professional with clear instructions and mark allocation. Note: Images are missing as expected for a text-based generation, but placeholders are correctly used. Answer key is detailed and provides clear marking criteria. |
| DeepSeek V4 Pro | Paper | 5-2 | Higher Chinese | practice-paper-1 | 9.2 | No | 10.0 | 9.0 | 8.5 | 10.0 | 9.0 | 9.5 | 10.0 | 9.0 | 8.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Language is appropriate for Sec 4 Higher Chinese. The structure follows standard comprehension formats (Cloze, MCQ, and Open-ended). Answer key is excellent, providing clear marking schemes and reasoning. Difficulty is well-balanced between literal and inferential questions. Note: The question numbering in the text goes up to Q25, but the instructions say 20 questions; this is a minor inconsistency. |
| DeepSeek V4 Pro | Paper | 5-2 | Higher Chinese | practice-paper-2 | 7.9 | No | 10.0 | 6.0 | 5.0 | 10.0 | 10.0 | 9.0 | 10.0 | 6.0 | 3.0 | 10.0 | - | - | - | - | too easy | The content is significantly below Secondary 4 Higher Chinese standards. The reading comprehension texts (community notice, news report, product ad) and the multiple-choice questions are more aligned with Primary 6 or Lower Secondary levels. Higher Chinese Sec 4 should involve complex literary analysis, implicit meanings, and long-form structured responses rather than simple factual retrieval from short advertisements. The marks/timing are consistent, and the answer explanations are excellent, but the academic rigor is insufficient for the level. |
| DeepSeek V4 Pro | Paper | 5-2 | Higher Chinese | practice-paper-3 | 8.2 | No | 10.0 | 8.0 | 7.0 | 10.0 | 9.0 | 9.0 | 10.0 | 6.0 | 4.0 | 9.0 | - | - | - | - | too easy | The content is significantly below Secondary 4 Higher Chinese standards; it reads more like Lower Secondary or even Primary school level. The comprehension texts are extremely simple and the questions are purely literal with no inference required. There is a major discrepancy between the stated total marks (70) and the actual marks provided in the paper (35). The exam format instructions are present but the difficulty level is not appropriate for the target stage. |
| DeepSeek V4 Pro | Paper | 5-2 | Higher Chinese | practice-paper-4 | 9.3 | No | 10.0 | 9.0 | 9.0 | 10.0 | 9.0 | 9.5 | 10.0 | 9.5 | 8.5 | 9.0 | - | - | - | - | appropriate | High quality paper. The language is appropriate for Sec 4 Higher Chinese. The structure follows the O-Level comprehension format (Cloze, Practical, and Passage). The answer key is excellent, providing clear marking schemes and linguistic explanations for the cloze section. Difficulty is appropriate, though the passage comprehension texts are slightly more standard/generic than high-level O-Level literary texts. |
| DeepSeek V4 Pro | Paper | 5-2 | Higher Chinese | practice-paper-5 | 9.1 | No | 10.0 | 9.0 | 8.5 | 10.0 | 9.0 | 9.5 | 10.0 | 9.0 | 7.5 | 8.0 | - | - | - | - | too easy | The paper is well-structured and the answer key is excellent, providing clear marking schemes and reasoning. However, the difficulty is slightly low for Secondary 4 Higher Chinese; the comprehension texts and vocabulary questions are more aligned with standard Chinese or lower secondary levels rather than the sophisticated nuance expected in O-Level Higher Chinese. |
| DeepSeek V4 Pro | Paper | 3-1 | Higher Chinese | prelim-paper-1 | 9.3 | No | 10.0 | 9.5 | 9.0 | 10.0 | 8.5 | 9.0 | 10.0 | 9.5 | 8.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Language is appropriate for Sec 4 Higher Chinese. The answer key is excellent, providing clear marking schemes and logical explanations for why certain answers are correct. The difficulty is well-calibrated for a Prelim paper, though Section A (Word Replacement) is slightly straightforward for Higher Chinese level. Format follows standard exam structures well. |
| DeepSeek V4 Pro | Paper | 3-1 | Higher Chinese | prelim-paper-2 | 8.3 | No | 10.0 | 6.0 | 7.0 | 10.0 | 10.0 | 9.0 | 10.0 | 8.0 | 3.0 | 10.0 | - | - | - | - | too easy | The content is significantly below Secondary 4 Higher Chinese standards. The vocabulary and sentence structures are more aligned with Primary school or Lower Secondary levels. The reading comprehension questions are purely literal/retrieval-based, lacking the inference and critical analysis required for O-Level/Higher Chinese. While the format and answer key are excellent, the academic rigor is insufficient for the target level. |
| DeepSeek V4 Pro | Paper | 3-1 | Higher Chinese | prelim-paper-3 | 9.2 | No | 10.0 | 9.0 | 9.5 | 10.0 | 8.5 | 9.0 | 10.0 | 10.0 | 7.5 | 9.0 | - | - | - | - | too easy | The paper follows the O-Level format well with appropriate sections and marking schemes. However, the difficulty is significantly lower than a true Secondary 4 Higher Chinese Prelim; the texts and questions are more aligned with Lower Secondary or Standard Chinese levels. The answer key is excellent, providing clear marking points and logic. |
| DeepSeek V4 Pro | Paper | 3-1 | Higher Chinese | prelim-paper-4 | 9.4 | No | 10.0 | 9.0 | 9.5 | 10.0 | 9.0 | 9.5 | 10.0 | 10.0 | 8.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Language suitability is excellent as the content is entirely in Chinese. The structure mirrors O-Level Paper 2 well. Answer key is exceptionally detailed with clear marking rubrics for open-ended questions. Difficulty is appropriate for Sec 4 Higher Chinese, though Section A is slightly on the easier side compared to the depth of Section C. |
| DeepSeek V4 Pro | Paper | 3-1 | Higher Chinese | prelim-paper-5 | 9.1 | No | 10.0 | 9.0 | 9.0 | 10.0 | 8.0 | 9.5 | 10.0 | 9.0 | 7.0 | 9.0 | - | - | - | - | too easy | The language and format are excellent, following the O-Level/Prelim style well. However, the difficulty is too low for Secondary 4 Higher Chinese; the reading comprehension texts (poster, news, manual) are more aligned with Lower Secondary or standard Chinese rather than the complex, nuanced texts expected at the Higher Chinese level. The answer key is high quality with clear explanations. |
| DeepSeek V4 Pro | Paper | 5-2 | History | practice-paper-1 | 9.5 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | - | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 History syllabus (Nazi Germany and WWII). Question types (Inference, Utility, Comparison, Message, Evaluation) match O-Level/Sec 4 standards. Marks and timing are realistic. Note: Source B requires an actual image; the visual description is a good placeholder but not a substitute for a real exam. Answer key is excellent, providing clear level-based marking rubrics and sample L3 answers. The answer key was truncated in the artifact. |
| DeepSeek V4 Pro | Paper | 5-2 | History | practice-paper-2 | 9.4 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | - | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 History syllabus (Rise of Authoritarianism/WWII). Question types (Message, Comparison, Surprise, Usefulness, Evaluation) match O-Level standards. Major issue: Source B (cartoon) and Source E (photo) are described in text but the actual images are missing, making the paper impossible to use as-is. Answer key is excellent with clear L1/L2/L3 marking schemes. |
| DeepSeek V4 Pro | Paper | 5-2 | History | practice-paper-3 | 9.4 | Yes | 9.5 | 10.0 | 9.0 | 10.0 | 8.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with the Sec 4 History syllabus (Nazi Germany/Militarism). Question types (Message, Comparison, Surprise, Provenance/Significance, Evaluation) follow O-Level SBQ standards. Note: Source C is described textually but the actual cartoon image is missing, which is a requirement for a real exam. Answer key is excellent, providing clear L1/L2/L3 marking schemes. |
| DeepSeek V4 Pro | Paper | 5-2 | History | practice-paper-4 | 9.4 | No | 10.0 | 10.0 | 9.0 | 10.0 | 8.5 | - | - | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with the Sec 4 History syllabus (Malaya, Germany, Cold War). Question structure and marking schemes are professional. Note: While no images are 'missing' in terms of broken links, the paper is purely essay/explanation based and lacks the Source-Based Questions (SBQ) which are a major component of the actual O-Level/Sec 4 History exams. |
| DeepSeek V4 Pro | Paper | 5-2 | History | practice-paper-5 | 9.3 | Yes | 9.5 | 10.0 | 9.0 | 10.0 | 8.5 | - | - | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 History syllabus (Nazi Germany/Versailles). Question types (Message, Comparison, Surprise, Evaluation) mirror O-Level SBQ formats. Note: Source A is described textually but requires an actual image for a real exam. Answer key is excellent, providing clear level-based marking schemes and model answers. The truncation at the end of the answer key is a minor technical issue. |
| DeepSeek V4 Pro | Paper | 3-1 | History | prelim-paper-1 | 9.6 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 History syllabus (Nazi Germany, Treaty of Versailles, Japan). Question types (Message, Similarity, Surprise, Usefulness, Evaluation) match O-Level/Prelim standards. Note: Source B is a text description of a cartoon; while acceptable for a text-only artifact, a real exam would require the image. Answer key provides excellent L1-L3 marking frameworks. |
| DeepSeek V4 Pro | Paper | 3-1 | History | prelim-paper-2 | 9.4 | Yes | 9.5 | 10.0 | 9.0 | 10.0 | 8.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 History (Pure) standards. Note: Source B is described as a cartoon but the image itself is missing (textual description only). Answer key provides excellent L1-L3 marking levels and contextual depth. Section B essay questions are standard. Truncation in the answer key is noted but the provided portion is high quality. |
| DeepSeek V4 Pro | Paper | 3-1 | History | prelim-paper-3 | 9.4 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 8.5 | - | - | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 History syllabus and source-based question (SBQ) formats. Note: Source C is described in text but the actual image is missing. Answer key provides good level-based marking schemes. Section B essay marks are slightly inconsistent with the total marks provided in the header (50 total vs 30 SBQ + 20 Essay, but Section B lists three 20-mark options). |
| DeepSeek V4 Pro | Paper | 3-1 | History | prelim-paper-4 | 9.4 | No | 10.0 | 10.0 | 9.0 | 10.0 | 8.0 | - | 10.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows the Pure History syllabus well (Versailles, Japan, Stalin). Marking scheme uses appropriate level-based descriptors. Note: The answer key is truncated at the end of Question 4. |
| DeepSeek V4 Pro | Paper | 3-1 | History | prelim-paper-5 | 9.7 | No | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality Paper 2 (Essay) simulation. Follows Pure History syllabus and exam structure perfectly. Marking scheme uses appropriate level-based descriptors and provides strong model answer frameworks. Note: The answer key is truncated at the end, but the provided sections are excellent. |
| DeepSeek V4 Pro | Paper | 5-2 | Literature | practice-paper-1 | 9.1 | No | 9.5 | 9.0 | 9.5 | 9.0 | 8.5 | - | - | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level Literature structure (Passage-based and Essay). The answer key is excellent, providing thematic frameworks and technique-based guidance rather than specific text answers, which is necessary for a generic practice paper. Note: The answer key is truncated at the end. |
| DeepSeek V4 Pro | Paper | 5-2 | Literature | practice-paper-2 | 9.2 | No | 9.5 | 9.0 | 9.5 | 10.0 | 7.0 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. The language is sophisticated and appropriate for Sec 4. The marking scheme uses professional band descriptors and provides excellent illustrative content for different texts. Note: The answer key is truncated in the provided artifact, which affects the score for step-by-step answers. |
| DeepSeek V4 Pro | Paper | 5-2 | Literature | practice-paper-3 | 9.2 | Yes | 10.0 | 9.5 | 9.0 | 10.0 | 7.0 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | The paper follows the O-Level Literature structure well, including passage-based and essay questions. However, it is a template-only artifact; it lacks the actual literary passages and specific text names, making it impossible to 'do' as a real paper. The answer key provides excellent qualitative guidance and marking rubrics but cannot provide specific textual analysis without the source text. |
| DeepSeek V4 Pro | Paper | 5-2 | Literature | practice-paper-4 | 9.1 | No | 9.5 | 9.0 | 8.5 | 10.0 | 9.0 | - | - | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. The passage is well-written and mimics the complexity of O-Level prose. The marking scheme is excellent, providing specific textual evidence and thematic depth. Note: Section B contains placeholders [TRAIT A/B] which is expected for a generic template, but requires student text context. |
| DeepSeek V4 Pro | Paper | 5-2 | Literature | practice-paper-5 | 9.3 | No | 9.5 | 9.0 | 9.5 | 10.0 | 8.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level Literature structure (Passage-based and Essay). The marking scheme uses appropriate band descriptors and provides excellent analytical guidance for the passages. Note: The answer key is truncated at the end. |
| DeepSeek V4 Pro | Paper | 3-1 | Literature | prelim-paper-1 | 9.7 | No | 10.0 | 10.0 | 9.5 | 10.0 | 8.0 | - | 10.0 | 10.0 | 10.0 | 10.0 | - | - | - | - | appropriate | High quality prelim paper. Excellent adherence to Literature syllabus and exam structure. Passage-based and essay questions are well-balanced. Marking scheme uses appropriate band descriptors for literature. Answer key is content-rich but truncated in the artifact. |
| DeepSeek V4 Pro | Paper | 3-1 | Literature | prelim-paper-2 | 9.5 | No | 10.0 | 10.0 | 9.5 | 10.0 | 8.0 | - | 10.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows the O-Level/Sec 4 Literature format perfectly with Section A (Prose) and Section B (Drama). The marking scheme is excellent, providing band descriptors and indicative content. Note: The 'passages' provided are generic placeholders/templates rather than excerpts from specific real-world novels/plays, which is expected for a generic practice paper, but students would need their own texts to use this. |
| DeepSeek V4 Pro | Paper | 3-1 | Literature | prelim-paper-3 | 9.9 | No | 10.0 | 10.0 | 10.0 | 10.0 | 9.0 | - | 10.0 | 10.0 | 10.0 | 10.0 | - | - | - | - | appropriate | Excellent alignment with Sec 4 Literature Prelim standards. The passage-based and essay questions follow the standard O-Level/Prelim format for Prose. The marking scheme is high quality, providing both thematic frameworks and specific textual analysis. Answer key is truncated but the provided portion is highly professional. |
| DeepSeek V4 Pro | Paper | 3-1 | Literature | prelim-paper-4 | 9.3 | No | 9.5 | 9.0 | 9.5 | 10.0 | 8.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. The passage-based questions and marking scheme are sophisticated and align well with Sec 4 Literature expectations. The answer key provides excellent 'Expected Response Frameworks' which are highly useful for students. The truncation in the answer key is noted but the provided content is sufficient for benchmarking. |
| DeepSeek V4 Pro | Paper | 3-1 | Literature | prelim-paper-5 | 9.3 | Yes | 9.5 | 9.0 | 9.5 | 10.0 | 8.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | The paper follows the O-Level Literature format very well. However, it is a template-only artifact; the actual prose passages and specific character names are replaced by descriptive placeholders, making it impossible to actually 'sit' the paper. The marking scheme is high quality, providing excellent response frameworks and band descriptors. |
| DeepSeek V4 Pro | Paper | 5-2 | Principles of Accounts | practice-paper-1 | 9.4 | No | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 8.5 | 9.5 | 8.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with the O-Level POA syllabus (Inventory, Ratios, Valuation). The exam format is slightly off: Paper 1 should be 1 hour for 40 marks, but this is 1.5 hours for 60 marks. The answer key is excellent and provides clear marking schemes, though it was truncated at the end. |
| DeepSeek V4 Pro | Paper | 5-2 | Principles of Accounts | practice-paper-2 | 9.6 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 8.5 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with the O-Level 7087 syllabus, specifically focusing on Inventory. The marking scheme is excellent with clear step-by-step workings and ECF provisions. Minor deduction for exam format: the duration (1h 30m) is shorter than the standard Paper 2 (2h) specified in the syllabus, though it is appropriate for a practice set. The total marks (60) match the syllabus weighting for Paper 2. |
| DeepSeek V4 Pro | Paper | 5-2 | Principles of Accounts | practice-paper-3 | 9.6 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 9.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with the O-Level POA syllabus (Inventory costing, valuation, and error effects). The marking scheme is detailed and provides clear logic for error cancellation in Question 3. Format is professional, though the duration (1.5h) is slightly shorter than a full Paper 2 (2h), which is acceptable for a topical practice paper. |
| DeepSeek V4 Pro | Paper | 5-2 | Principles of Accounts | practice-paper-4 | 9.8 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Excellent coverage of inventory costing (FIFO/AVCO), valuation (NRV), and ratio analysis. Marks and timing are well-structured. Answer key provides clear, logical steps for complex calculations. |
| DeepSeek V4 Pro | Paper | 5-2 | Principles of Accounts | practice-paper-5 | 9.6 | No | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 POA syllabus (Inventory, FIFO, AVCO, Ratios). Format is professional with clear mark allocations. Answer key provides excellent step-by-step workings and marking schemes. Minor truncation in the answer key at the end. |
| DeepSeek V4 Pro | Paper | 3-1 | Principles of Accounts | sa1-paper-1 | 9.6 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 9.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with the O-Level 7087 syllabus, specifically focusing on inventory and financial analysis. Marks and structure are realistic. The answer key provides excellent step-by-step workings and marking schemes. Minor note: The duration (1h 15m) is slightly longer than the standard Paper 1 (1h) but appropriate for the 60-mark volume. |
| DeepSeek V4 Pro | Paper | 3-1 | Principles of Accounts | sa1-paper-2 | 9.6 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 9.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows the O-Level 7087 syllabus closely, especially regarding inventory valuation and ratio analysis. The marking scheme is excellent, providing clear step-by-step logic and marking notes. Minor note: The duration (1h 15m) is slightly shorter than the standard Paper 2 (2h), but appropriate for an SA1 topical assessment. |
| DeepSeek V4 Pro | Paper | 3-1 | Principles of Accounts | sa1-paper-3 | 9.6 | No | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Excellent coverage of inventory, financial statements, and ratios. Follows O-Level POA structure well. Answer key is detailed with clear marking schemes. Minor truncation in the provided artifact text, but the content is robust. |
| DeepSeek V4 Pro | Paper | 3-1 | Principles of Accounts | sa1-paper-4 | 9.7 | No | 10.0 | 10.0 | 9.5 | 10.0 | 10.0 | - | 10.0 | 9.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Excellent coverage of inventory, financial statements, and error correction. Marks and instructions are well-structured. The duration (1h 15m) is slightly tight for 60 marks of complex accounting calculations, but generally acceptable for a practice SA1. |
| DeepSeek V4 Pro | Paper | 3-1 | Principles of Accounts | sa1-paper-5 | 9.8 | No | 10.0 | 10.0 | 9.5 | 9.0 | 10.0 | - | 10.0 | 9.5 | 10.0 | 10.0 | - | - | - | - | appropriate | High quality paper. Excellent alignment with O-Level 7087 syllabus, specifically on inventory costing (FIFO/AVCO) and ratio analysis. The scenario-based question in Section C correctly mirrors the required decision-making depth. The answer key is exceptionally detailed with clear marking schemes. Minor truncation at the very end of the answer key, but the content provided is complete and accurate. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Biology | practice-paper-1 | 9.3 | Yes | 10.0 | 10.0 | 9.0 | 8.0 | 9.0 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 Pure Biology syllabus. Format is professional with clear instructions and marks. Major issue: several questions (MCQ 3, 19; Structured 21, 23) rely on diagrams that are only present as text placeholders. Answer key is excellent and provides necessary marking nuances. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Biology | practice-paper-2 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 Pure Biology syllabus. Marks and timing are realistic. Major issue: several questions (1a, 3e, 4d) rely on diagrams/graphs that are described in text but the actual images are missing. Answer key is excellent and provides clear marking criteria. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Biology | practice-paper-3 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Pure Biology syllabus (Cells, Biomolecules, Osmosis, Enzymes). The use of descriptive placeholders for images is helpful for manual insertion. Answer key is excellent, providing clear marking schemes and biological explanations. Minor deduction for missing actual diagrams, but the text descriptions are sufficient for benchmarking. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Biology | practice-paper-4 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Pure Biology syllabus (Cells, Movement, Molecules, Enzymes). Format is professional with clear mark allocation. Major issue: several questions (Q4, Q7, Q11, Q13, Q14, Q16, Q17, Q18) refer to diagrams/graphs/models that are not rendered or provided in the text, making the paper impossible to complete as-is. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Biology | practice-paper-5 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.5 | - | 10.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Pure Biology syllabus (Cells/Biomolecules). Format is professional with clear instructions and marks. Note: Several diagrams (electron micrograph, enzyme graph, plant cell diagram, molecular structure, and grids) are represented by text placeholders and require actual images to be functional. Answer key is excellent, providing specific marking points and explanations. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Biology | prelim-paper-1 | 9.6 | Yes | 10.0 | 10.0 | 9.5 | 9.0 | 9.5 | - | 10.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Pure Biology syllabus and exam structure. Marks and timing are realistic. Note: The paper is truncated at the end of Section B and the answer key is truncated at the end of Question 5. Placeholders for diagrams are present but required for full utility. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Biology | prelim-paper-2 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.5 | - | 10.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Pure Biology standards. Note: Several questions (1, 3, 4, 5, 6, 8) refer to figures (e.g., Fig 1.1, Fig 3.1) that are not provided in the text, making the paper impossible to complete without the intended diagrams. Answer key is excellent and provides clear marking schemes. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Biology | prelim-paper-3 | 9.6 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Pure Biology syllabus. Format follows O-Level/Prelim standards with clear mark allocation and instructions. Note: The paper relies heavily on figures (Fig 1.1, 3.1, 4.1, 6.1, 7.1) which are missing in the text, making it impossible to actually answer the questions without the visual assets. Answer key is excellent, providing specific marking points and acceptable variations. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Biology | prelim-paper-4 | 9.5 | Yes | 10.0 | 10.0 | 9.5 | 9.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Pure Biology syllabus and exam structure. Major issue: several questions (1, 3, 4, 6) refer to figures (e.g., Fig 1.1, Fig 3.1) that are missing from the text. Marking scheme is excellent and provides clear point-based guidance. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Biology | prelim-paper-5 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 Pure Biology syllabus and exam structure. Major issue: Fig 1.1 (electron micrograph) and Fig 4.1 (specialised cells) are missing/not provided, making Question 1 and 4 impossible to answer as written. The ASCII graph for Question 3 is a good fallback but real papers use high-res images. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Chemistry | practice-paper-1 | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 9.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 Pure Chemistry syllabus (Acids, Bases & Salts). Format includes instructions, marks, and timing. Answer key provides excellent marking schemes and explanations. Note: The paper relies on graph descriptions rather than actual images, which is a limitation for a real exam but acceptable for this artifact. The answer key was truncated at the end. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Chemistry | practice-paper-2 | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 9.0 | 9.5 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Pure Chemistry syllabus (Acids/Bases, Redox, Haber, Contact processes). Missing images for the titration graph and sketch axes, though text descriptions are provided. Answer key is excellent and provides clear marking schemes. Notation is generally good, though some chemical formulas use plain text instead of LaTeX. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Chemistry | practice-paper-3 | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 9.0 | 9.5 | - | 9.0 | 9.5 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level structure well. Note: The pH curve in Q2 and the apparatus diagram in Q6 are represented by ASCII/text-based placeholders rather than actual images, which is a significant drawback for a chemistry paper. Notation is generally good, though some chemical formulas use plain text instead of LaTeX. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Chemistry | practice-paper-4 | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with the 6092 syllabus (Acids, Bases, Salts, Haber Process). Note: Question 2 contains a text-based description of a pH curve instead of an actual image, which is a placeholder issue. The answer key is excellent and provides clear marking schemes. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Chemistry | practice-paper-5 | 9.6 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 9.0 | 9.5 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Excellent coverage of Acids, Bases and Salts. Questions follow O-Level style (titration, salt preparation, qualitative analysis). Notation is mostly good, though some chemical formulas use subscript text rather than full LaTeX. The answer key is detailed and provides clear marking schemes. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Chemistry | prelim-paper-1 | 9.3 | Yes | 10.0 | 10.0 | 9.5 | 8.0 | 9.0 | - | 9.0 | 9.5 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Pure Chemistry syllabus (Acids, Salts, Electrolysis, Haber Process). Format is professional with clear mark allocation. Major issue: The paper is truncated at the end of Section B, and several diagrams (pH curve, electrolysis apparatus) are represented by text placeholders rather than actual images. Notation is generally good, using standard chemical symbols. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Chemistry | prelim-paper-2 | 9.7 | No | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Excellent adherence to O-Level Pure Chemistry syllabus (Acids, Bases, Salts, Qualitative Analysis, and Stoichiometry). Notation is correct. The answer key is detailed, though the final question's answer key was truncated in the artifact. Marks and timing are realistic for a 1h 45m paper. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Chemistry | prelim-paper-3 | 9.6 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.5 | - | 9.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality prelim paper. Follows O-Level structure well. Notation is mostly good, though some chemical formulas use subscripts instead of LaTeX. Missing diagram for titration apparatus and copper sulfate preparation. Answers are detailed and include marking schemes. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Chemistry | prelim-paper-4 | 9.6 | No | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level Pure Chemistry structure well. Note: The answer key for Question 4 contains a self-correction regarding the cation (Zn2+ vs Al3+) which is good for accuracy but indicates a slight logic mismatch in the initial question prompt's observation table. Marks and timing are realistic. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Chemistry | prelim-paper-5 | 9.7 | No | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows the O-Level Pure Chemistry Paper 2 structure well. Questions cover key syllabus areas like Qualitative Analysis, Stoichiometry, and the Haber Process. Answer key is detailed with clear marking schemes. Note: The answer key for Question 8(c) is truncated in the artifact. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Physics | practice-paper-1 | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 9.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Pure Physics (Electricity and Magnetism). The use of descriptive placeholders for diagrams is helpful for a text-only artifact, though actual images are missing. Marking scheme is detailed and follows standard Singapore grading logic (method marks vs answer marks). Minor truncation at the end of the answer key. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Physics | practice-paper-2 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with O-Level Pure Physics (6091) syllabus for Electricity and Magnetism. Marks and instructions follow standard exam formats. Major issue: several questions rely on diagrams (Figures 3.1, 6.1, 12.1) which are only provided as text descriptions/placeholders, making the paper unusable without the actual images. Answer key is excellent, providing clear marking schemes and method marks. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Physics | practice-paper-3 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Pure Physics (Electricity and Magnetism). The main issue is the heavy reliance on placeholder text for diagrams (e.g., 'Assume a standard parallel circuit diagram'), which makes the paper unusable without manual image insertion. Marking scheme is excellent and follows standard Singapore grading logic. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Physics | practice-paper-4 | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Pure Physics (Electricity and Magnetism). Marks and timing are realistic. Major issue: several questions (3, 10, 14, 16) refer to figures that are not provided in the text, making them impossible to solve as presented. Answer key is excellent with clear marking schemes. |
| DeepSeek V4 Pro | Paper | 5-2 | Pure Physics | practice-paper-5 | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns well with Sec 4 Pure Physics (Electricity/Magnetism). Missing diagrams for magnetic fields, circuits, and graphs (placeholders used). Answer key is excellent with clear marking schemes. Note: The paper is truncated at the end. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Physics | prelim-paper-1 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 10.0 | - | 9.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Uses ASCII art for diagrams which is a placeholder for actual images. Notation is mostly good but some subscripts in the answer key (e.g., Vp, Vs) are not in proper LaTeX. Content aligns perfectly with Sec 4 Pure Physics syllabus. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Physics | prelim-paper-2 | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | 9.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | The paper is high quality and follows the O-Level Pure Physics syllabus well. However, it contains several references to figures (e.g., Figure 3.1, 9.1, 10.1, 12.1, 16.1, 18.1) that are missing, making the paper impossible to complete as written. The answer key is detailed and provides good marking schemes. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Physics | prelim-paper-3 | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 9.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Sec 4 Pure Physics (Electricity & Magnetism). Marks and timing are realistic. Major issue: several questions (1a, 3a, 5, 6a, 8) rely on diagrams/grids that are provided only as text descriptions or placeholders, making the paper unusable without the actual visual assets. Notation is generally good, though some subscripts in the answer key could use more consistent LaTeX. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Physics | prelim-paper-4 | 9.6 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.5 | - | 9.0 | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows O-Level Pure Physics structure and marking scheme style well. Note: Several questions require diagrams (field patterns, circuit diagrams, graphs) which are currently represented by text placeholders. Notation is generally good, though some math symbols could use more consistent LaTeX formatting. |
| DeepSeek V4 Pro | Paper | 3-1 | Pure Physics | prelim-paper-5 | 9.6 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.5 | - | 10.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to O-Level Pure Physics syllabus for Electricity and Magnetism. Marks and timing are realistic. Note: Question 18 contains a text placeholder for a diagram which is required. Answer key is excellent with clear marking schemes. Minor discrepancy in the marking scheme summary math vs question totals, but question paper itself is consistent. |
| DeepSeek V4 Pro | Paper | 5-2 | Social Studies | practice-paper-1 | 9.6 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | - | 10.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Sec 4 Social Studies syllabus and question types (SBQ and SRQ). Note: Source B is a text-based table instead of a graph, and Source E is a text description instead of an image; while acceptable for LLM generation, they are technically 'missing' visual assets. Answer key is excellent and provides clear marking rubrics. |
| DeepSeek V4 Pro | Paper | 5-2 | Social Studies | practice-paper-2 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Excellent alignment with Sec 4 Social Studies syllabus (Issue 3 and Issue 1/2). Question types (SBQ and SRQ) follow standard SEAB formats. Note: Source B is a text description of a cartoon rather than an image, which is expected for text-only generation but requires a placeholder in a real exam. Answer key is detailed and uses appropriate marking levels. |
| DeepSeek V4 Pro | Paper | 5-2 | Social Studies | practice-paper-3 | 9.6 | Yes | 10.0 | 10.0 | 9.5 | 9.0 | 9.0 | - | - | 10.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality paper. Excellent alignment with Sec 4 Social Studies syllabus (Issue 2). Question types (SBQ and Structured Response) follow SEAB/O-Level patterns closely. Marks and timing are realistic. Note: Source F is a placeholder description; the answer key is truncated at the end. |
| DeepSeek V4 Pro | Paper | 5-2 | Social Studies | practice-paper-4 | 9.4 | Yes | 9.5 | 10.0 | 9.0 | 10.0 | 9.0 | - | - | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Excellent alignment with the Social Studies syllabus (Issue 3). Question types (SBQ and SRQ) mirror the actual exam structure. Note: Source B (bar chart) and Source E (cartoon) are described via text/tables but the actual visual assets are missing, which is critical for a Social Studies paper. The answer key is comprehensive and provides clear marking rubrics. |
| DeepSeek V4 Pro | Paper | 5-2 | Social Studies | practice-paper-5 | 9.4 | Yes | 9.5 | 10.0 | 9.0 | 10.0 | 8.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Excellent alignment with Social Studies Issue 1 (Governance/Ageing). Source-Based Case Study (SBCS) questions follow standard SEAB-style command words (Agree, Surprised, Similarity). Note: Source E is described textually but the actual image is missing, which is a requirement for a real exam paper. Answer key provides excellent level-based marking schemes. |
| DeepSeek V4 Pro | Paper | 3-1 | Social Studies | prelim-paper-1 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Excellent adherence to Social Studies source-based question (SBQ) formats and marking schemes. The use of image descriptions for Source B is a good workaround for missing assets. Difficulty is well-calibrated for Sec 4 Prelims. Note: The answer key for Question 4 is truncated. |
| DeepSeek V4 Pro | Paper | 3-1 | Social Studies | prelim-paper-2 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | - | 10.0 | 10.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Excellent alignment with Issue 2 syllabus. Question types (Message, Surprise, Comparison, Evaluation) perfectly mirror SEAB Social Studies formats. Answer key provides strong L1-L4 marking schemes. Note: Source B requires an actual image; the text description is a good placeholder but the image itself is missing. The answer key for Q5 was truncated. |
| DeepSeek V4 Pro | Paper | 3-1 | Social Studies | prelim-paper-3 | 9.4 | Yes | 9.5 | 10.0 | 9.0 | 10.0 | 8.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Adheres well to Social Studies SBQ and SRQ formats. Note: Source D is a text description of a cartoon rather than an image, which is a placeholder issue. Answer key is excellent, providing clear marking descriptors and frameworks. The paper is truncated at the end of the answer key. |
| DeepSeek V4 Pro | Paper | 3-1 | Social Studies | prelim-paper-4 | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality paper. Follows SS syllabus (Issue 2) and exam structure perfectly. Source-based questions (SBQ) use appropriate levels of reasoning (Surprise, Usefulness, Comparison). Answer key provides excellent level-based marking schemes. Note: The answer key is truncated at the end. |
| DeepSeek V4 Pro | Paper | 3-1 | Social Studies | prelim-paper-5 | 9.4 | Yes | 9.5 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality paper. Content aligns perfectly with Issue 2 of the syllabus. The source-based questions follow standard SBQ formats (Message, Comparison, Utility, Evaluation). Note: Source D is a text description of a cartoon rather than an image, which is expected for text-only generation but requires a placeholder for actual use. The answer key is excellent, providing clear level-based marking schemes and model answers. |
| DeepSeek V4 Pro | Quiz | 3-0 | Additional Mathematics | algebra-functions | 9.0 | No | 10.0 | 10.0 | 9.0 | 7.0 | 9.0 | - | 10.0 | 9.0 | 9.0 | 8.0 | - | - | - | - | appropriate | High quality quiz and marking scheme. Content aligns perfectly with Sec 4 A-Math syllabus. Major issue: The artifact is truncated at the end of the answer key (Question 15 is incomplete). The number of questions (20) for a 50-mark paper is quite high, making the 75-minute timeframe very tight for students to show full working. |
| DeepSeek V4 Pro | Quiz | 5-1 | Additional Mathematics | algebra-functions | 9.6 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 9.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with Sec 4 A-Math syllabus. Marking scheme is excellent with clear M and A marks. Question 4 is a clever edge case. Minor note: marks assigned to questions are slightly low for some complex topics, but overall structure is very professional. |
| DeepSeek V4 Pro | Quiz | 3-0 | Additional Mathematics | calculus | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 9.0 | 10.0 | - | 10.0 | 10.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality quiz. Follows Sec 4 A-Math calculus syllabus well. Notation is excellent. One image placeholder is present. Answer key is detailed with marking schemes. Timing is realistic for the number of questions. |
| DeepSeek V4 Pro | Quiz | 5-1 | Additional Mathematics | calculus | 9.6 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality quiz. Calculus topics (differentiation, applications, integration) are well-covered and align with Sec 4 A-Math syllabus. Answer key provides excellent step-by-step marking schemes. Formatting is professional, though Section D marks are slightly inconsistent with the total (Section D says 10 marks but questions 16-20 sum to 10, which is correct, but the header text for Section D is slightly repetitive). |
| DeepSeek V4 Pro | Quiz | 3-0 | Additional Mathematics | geometry-trigonometry | 8.9 | Yes | 10.0 | 10.0 | 9.0 | 8.0 | 9.0 | - | 10.0 | 9.0 | 7.0 | 8.0 | - | - | - | - | uneven | The quiz contains several questions (15, 20) that explicitly refer to diagrams which are missing. The difficulty is uneven; while most questions are standard Sec 4 A-Math, Question 15 contains a mathematical error in the coordinates provided (they do not form a rhombus), which is caught in the answer key's self-correction. The answer key is truncated. |
| DeepSeek V4 Pro | Quiz | 5-1 | Additional Mathematics | geometry-trigonometry | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with Sec 4 A-Math syllabus. Notation is excellent. Major issue: several questions (12, 15, 16, 17, 18, 19) explicitly refer to diagrams or require sketches that are missing from the artifact. Answer key is detailed and follows marking scheme logic. |
| DeepSeek V4 Pro | Quiz | 3-0 | Additional Mathematics | graphs-coordinate-geometry | 9.3 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 9.0 | 9.0 | 8.5 | 8.0 | - | - | - | - | appropriate | High quality quiz. Content covers coordinate geometry, circles, and linear law well. Missing images for Q13 (grid) and Q14 (diagram). Q11 has a mathematical error where the discriminant is positive but the solution says no real values; however, the marking scheme acknowledges this. Difficulty is appropriate for Sec 4 A-Math. |
| DeepSeek V4 Pro | Quiz | 5-1 | Additional Mathematics | graphs-coordinate-geometry | 9.3 | No | 10.0 | 10.0 | 9.0 | 9.0 | 10.0 | - | 10.0 | 9.0 | 9.0 | 8.0 | - | - | - | - | appropriate | High quality quiz. Content aligns well with Sec 4 A-Math syllabus for Coordinate Geometry and Circles. The marking scheme is excellent with clear method marks. Note: The answer key is truncated at the end. The timeframe might be tight for 20 questions in 45 minutes given the complexity of Section D. |
| DeepSeek V4 Pro | Quiz | 3-0 | Additional Mathematics | numbers-ratio-proportion | 8.3 | No | 10.0 | 7.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 9.0 | 5.0 | 6.0 | - | - | - | - | uneven | The quiz suffers from severe topic drift. While labeled 'Numbers, Ratio and Proportion', it includes heavy Calculus (differentiation/integration) and Binomial Expansion questions which belong to different syllabus strands. This makes the difficulty uneven and the topic focus inaccurate. Additionally, Question 9 has no integer solution for n, and Question 7 results in a non-integer number of students, which is poor practice for secondary level math. |
| DeepSeek V4 Pro | Quiz | 5-1 | Additional Mathematics | numbers-ratio-proportion | 9.2 | No | 10.0 | 9.0 | 8.5 | 10.0 | 10.0 | - | 10.0 | 9.0 | 7.0 | 9.0 | - | - | - | - | too easy | The content is more aligned with Lower Secondary or Math syllabus rather than Sec 4 Additional Mathematics. While variation and ratio are part of the broader math context, the depth of questions is quite basic for A-Math. The exam format (marks, instructions, duration) is well-structured. |
| DeepSeek V4 Pro | Quiz | 3-0 | Additional Mathematics | statistics-probability | 8.0 | No | 10.0 | 10.0 | 7.0 | 10.0 | 9.0 | - | 8.0 | 5.0 | 6.0 | 7.0 | - | - | - | - | too easy | The content is more aligned with Secondary 3 or General Math rather than Sec 4 Additional Mathematics. The questions lack the complexity and depth (e.g., more advanced probability distributions or complex conditional scenarios) expected in a Sec 4 A-Math paper. Exam format is missing a total marks count and time duration. Notation is mostly plain text rather than full LaTeX for all mathematical expressions. |
| DeepSeek V4 Pro | Quiz | 5-1 | Additional Mathematics | statistics-probability | 9.7 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 10.0 | 9.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality quiz. Follows A-Math syllabus for Statistics and Probability well. Question structure and marking schemes are realistic. Minor note: Section A is quite basic for Sec 4 A-Math, but serves as a good warm-up. |
| DeepSeek V4 Pro | Quiz | 3-0 | Combined Science Biology | cells-biomolecules | 9.7 | Yes | 10.0 | 10.0 | 9.5 | 10.0 | 9.0 | - | 10.0 | 9.5 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with Sec 4 Combined Science Biology syllabus (Cells, Movement, Biomolecules). Question structure, mark allocation, and instructions follow O-Level standards. Answer key is excellent, providing clear marking notes and common pitfalls. Note: Images are represented by text placeholders which is expected for this stage. |
| DeepSeek V4 Pro | Quiz | 5-1 | Combined Science Biology | cells-biomolecules | 9.7 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with Sec 4 Combined Science Biology syllabus. Question structure, mark allocation, and marking scheme are excellent. Note: Placeholder markers for diagrams are present and correctly identified. The marking scheme provides clear, granular points for examiners. |
| DeepSeek V4 Pro | Quiz | 3-0 | Combined Science Biology | ecology | 9.3 | Yes | 10.0 | 10.0 | 9.0 | 9.0 | 9.0 | - | 10.0 | 9.0 | 8.5 | 9.0 | - | - | - | - | appropriate | High quality quiz. Adheres well to O-Level Combined Science Biology ecology syllabus. Question 11 contains a text-based placeholder for a diagram which is a required image. The marking scheme is excellent, providing specific marking notes and acceptable alternatives. Difficulty is appropriate for Sec 4, though Section A/B are quite rapid-fire. The paper is truncated at the end of the answer key. |
| DeepSeek V4 Pro | Quiz | 5-1 | Combined Science Biology | ecology | 9.3 | Yes | 10.0 | 10.0 | 8.5 | 9.0 | 9.5 | - | 10.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality quiz. Content aligns well with Sec 4 Ecology syllabus. Note: Question 14 contains a text description of a graph instead of an actual image, which is a placeholder issue. Answer key is excellent with clear marking notes. The total marks (40) and duration (45 mins) are consistent with a topical quiz format. |
| DeepSeek V4 Pro | Quiz | 3-0 | Combined Science Biology | evolution-diversity | 8.6 | Yes | 9.5 | 9.0 | 8.5 | 9.0 | 9.0 | - | 10.0 | 9.0 | 7.0 | 6.0 | - | - | - | - | uneven | Language and syllabus alignment are excellent. However, the quiz is uneven: Section D contains an excessive number of questions (10 questions for 10 marks) which is logically inconsistent with the marks assigned and makes the paper impossible to complete in 45 minutes. The marking scheme is high quality and follows standard Singapore exam rubrics. |
| DeepSeek V4 Pro | Quiz | 5-1 | Combined Science Biology | evolution-diversity | 9.3 | Yes | 10.0 | 10.0 | 8.5 | 10.0 | 9.0 | - | 10.0 | 8.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality quiz. Major issue: several questions (7, 9, 13) explicitly reference diagrams or graphs that are missing from the text. The marking scheme is excellent and follows the required level of detail for O-Level Biology. Exam format is mostly correct but lacks the specific subject-combination context found in official papers. |
| DeepSeek V4 Pro | Quiz | 3-0 | Combined Science Biology | genetics-inheritance | 9.3 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 8.0 | 9.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality quiz. Pedigree charts are represented via ASCII/text which is a poor substitute for actual diagrams; this is a major issue for a biology paper. Notation for alleles is clear, though LaTeX could be used for better formal presentation. Marking scheme is excellent and follows standard Singapore grading logic (e.g., distinguishing genotype from phenotype). |
| DeepSeek V4 Pro | Quiz | 5-1 | Combined Science Biology | genetics-inheritance | 9.2 | Yes | 10.0 | 10.0 | 9.0 | 9.0 | 9.5 | - | 8.0 | 9.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality quiz. Content aligns well with Sec 4 Combined Science Biology. Pedigree chart and genetic diagrams are represented via text/ASCII, which is a placeholder for actual images. Notation for blood groups (I^A) is mostly correct but could use more consistent LaTeX. Answer key is excellent and provides clear marking schemes. |
| DeepSeek V4 Pro | Quiz | 3-0 | Combined Science Biology | human-physiology | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 8.0 | 9.0 | - | 10.0 | 10.0 | 9.0 | 10.0 | - | - | - | - | appropriate | High quality quiz. Adheres well to O-Level Combined Science Biology standards. Note: The artifact contains placeholder text for diagrams (stomach, graph, etc.) which are required for full usability. The answer key is truncated at the end. |
| DeepSeek V4 Pro | Quiz | 5-1 | Combined Science Biology | human-physiology | 9.5 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with the O-Level Combined Science Biology syllabus for Human Physiology. The marking scheme is excellent, providing specific marking notes and common misconceptions. Major issue: several questions (11, 13, 15) refer to diagrams or graphs that are not present in the text, making the quiz unusable without the intended visual assets. |
| DeepSeek V4 Pro | Quiz | 3-0 | Combined Science Biology | plant-biology | 9.6 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 10.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with Sec 4 Combined Science Biology (Plant Biology). The marking scheme is excellent, providing specific marking notes and alternative acceptable answers. Note: Question 8 contains a placeholder for a leaf cross-section diagram which is required for the question to be functional. |
| DeepSeek V4 Pro | Quiz | 5-1 | Combined Science Biology | plant-biology | 9.4 | Yes | 10.0 | 10.0 | 9.0 | 10.0 | 9.0 | - | 10.0 | 9.0 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with Sec 4 Combined Science Biology (Plant Biology). Note: Question 12 and 15 rely on diagrams/graphs that are provided only as text descriptions; these must be actual images in a final artifact. The answer key is excellent, providing clear marking schemes and scientific reasoning. |
| DeepSeek V4 Pro | Quiz | 3-0 | Combined Science Chemistry | acids-bases-salts | 9.4 | No | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 8.5 | 9.5 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with Sec 4 Combined Science (Chemistry) syllabus. Question types (MCQ, Structured, Calculation, Data-based) are well-distributed. Answer key is excellent with clear marking schemes. Minor notation issue: chemical equations and formulas are in plain text rather than full LaTeX, though readable. The titration question is a strong addition for this level. |
| DeepSeek V4 Pro | Quiz | 5-1 | Combined Science Chemistry | acids-bases-salts | 9.6 | No | 10.0 | 10.0 | 9.0 | 10.0 | 10.0 | - | 9.0 | 9.0 | 9.5 | 10.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with O-Level Combined Science Chemistry (Acids, Bases, Salts). Questions cover a good range of AO1, AO2, and AO3. Notation is generally good, though some chemical formulas use plain text instead of LaTeX. The answer key is excellent, providing clear marking schemes and explanations. |
| DeepSeek V4 Pro | Quiz | 3-0 | Combined Science Chemistry | atomic-structure-bonding | 8.9 | Yes | 10.0 | 10.0 | 9.0 | 8.0 | 9.0 | - | 7.0 | 9.0 | 9.5 | 9.0 | - | - | - | - | appropriate | High quality quiz aligned with Sec 4 Combined Science syllabus. Content covers atomic structure, isotopes, and bonding types well. Note: Several diagrams are missing or represented by text placeholders (e.g., Question 7a, 9b, 15, 18). Notation for ions and chemical formulas is mostly correct but lacks full LaTeX formatting for professional appearance. The answer key is detailed and provides good marking logic. |
| DeepSeek V4 Pro | Quiz | 5-1 | Combined Science Chemistry | atomic-structure-bonding | 9.4 | No | 10.0 | 10.0 | 9.0 | 10.0 | 9.5 | - | 9.0 | 9.5 | 9.0 | 9.0 | - | - | - | - | appropriate | High quality quiz. Content aligns perfectly with Sec 4 Combined Science syllabus. Notation for isotopes and ions is correct. The ASCII diagram for atomic radii is a good substitute for a missing image. Marking scheme is detailed and provides clear guidance for examiners. |
Criteria
Scores use 10.0 as best fit. Missing images are tracked as a yes/no flag.
Language suitability
Syllabus adherence
Past-paper template adherence
No weird artefacts/symbols
Step-by-step answers
Answer explanation quality
Latex/notation format
Exam paper format
Difficulty appropriateness
Doable within timeframe
Cheatsheet focused summaries
Parent guide syllabus fit
Audio script listenability
Audio script learning value