Stage 9-1 Level View

Primary 5 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.

62 reports 5 subjects 2 LLMs Updated 2026-06-02 12:01:27 UTC Refreshes every 5 min

All Levels Primary 1 Primary 2 Primary 3 Primary 4 Primary 5 Primary 6 PSLE Secondary 1 Secondary 2 Secondary 3 Secondary 4 O-Level A-Level

Evaluator Gemma 4 26B A4B google/gemma-4-26b-a4b-it

Subject view

Showing all Primary 5 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 Primary 5 content.

Generation Model	Artifacts	Overall	Missing Images	Language	Syllabus	Answers	Notation	Timing
Claude Sonnet 4	5	9.6	1	9.6	9.3	-	10.0	9.5
Legacy generator	57	8.6	20	9.6	9.2	8.2	8.8	8.3

Subject Summary

Average scores grouped by subject inside Primary 5.

Subject	Artifacts	Overall	Missing Images	Language	Syllabus	Answers	Notation	Timing
Chinese	7	8.9	2	9.4	8.9	9.1	10.0	8.4
English	19	8.5	4	9.4	9.2	6.4	10.0	8.2
Higher Chinese	7	8.7	2	9.3	8.8	9.1	10.0	8.0
Mathematics	20	8.7	6	9.9	9.8	9.2	7.5	8.4
Science	9	8.6	7	9.5	8.3	9.0	10.0	8.6

LLM by Content Type

Model scores split by quizzes, papers, cheatsheets, and parent guides.

Generation Model	Type	Artifacts	Overall	Missing Images	Language	Syllabus	Answers	Notation	Timing
Claude Sonnet 4	Cheatsheet	5	9.6	1	9.6	9.3	-	10.0	9.5
Legacy generator	Parents Guide	5	9.6	0	9.8	9.3	-	10.0	-
Legacy generator	Quiz	52	8.5	20	9.5	9.1	8.2	8.7	8.3

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	Comments
6.2	Legacy generator	English	Quiz	3-0	editing-spelling	9.0	8.0	5.0	0.0	10.0	5.0	Critical failure in answer key alignment: Section A answers refer to a completely different text (about habitats/Siberia) than the provided text (about Singapore heritage). Section B answers also do not match the questions asked in the quiz. The quiz content is appropriate for P5, but the mismatch makes it unusable.
6.6	Legacy generator	English	Quiz	3-0	vocabulary-cloze	9.0	8.0	4.0	0.0	10.0	7.0	Major failure in answer key alignment: the answer key provided is for a completely different quiz (about Gardens by the Bay/Kaya toast) than the actual quiz generated (about Recycling). Section A in the quiz is Word Form Cloze, but the answer key describes Multiple Choice Cloze. Difficulty is uneven as Section A is quite mechanical while Section B is standard.
7.2	Legacy generator	English	Quiz	3-0	comprehension-open-ended	9.0	8.5	7.0	5.0	10.0	4.0	Major hallucination in answer key: the answers refer to a 'Singapore River' passage, but the quiz content is about 'Education System'. Question count and marks in the key do not match the quiz. Difficulty is uneven; Section C is too cognitively demanding for a 35-minute P5 quiz. Timeframe is unrealistic for 20 questions of this depth.
7.2	Legacy generator	English	Quiz	3-0	grammar-tenses	9.0	9.5	4.0	2.0	10.0	8.0	Major hallucination in the answer key: the questions in the answer key do not match the questions in the quiz. Section A, B, and C in the key are entirely different from the quiz content. Difficulty is uneven due to this mismatch.
7.3	Legacy generator	Science	Quiz	5-1	systems	9.0	4.0	6.0	9.0	10.0	8.0	Major syllabus misalignment: The content covers advanced secondary school biology (alveoli, blood components, heart chambers, bile, peristalsis) which is explicitly excluded from the P5 MOE syllabus. P5 should focus on basic parts and functions without detailed cellular or biochemical mechanisms. The quiz is too difficult for the intended level.
7.8	Legacy generator	Higher Chinese	Quiz	5-1	vocabulary	9.0	8.5	7.0	9.0	-	7.0	Vocabulary level is appropriate for P5 Higher Chinese. Major issue: The total marks in the header (50) contradicts the actual sum in the scoring table (65). Question 21 contains a syntax error with an unmatched parenthesis. The format is more like a worksheet than a formal exam paper.
7.8	Legacy generator	Mathematics	Quiz	3-0	area-perimeter	9.5	10.0	7.0	9.0	4.0	8.0	The quiz content is syllabus-accurate for P5. Major issues: 1. Missing diagrams for composite shapes and word problems. 2. Lack of proper LaTeX for mathematical notation (uses plain text/symbols). 3. Question count (20) does not match the provided Section A/B/C breakdown (only 14 questions listed). 4. Exam format lacks standard marks distribution per question in the header.
7.8	Legacy generator	Mathematics	Quiz	5-1	geometry	9.5	9.0	7.0	9.0	4.0	8.0	The quiz includes topics slightly beyond P5 (regular hexagon/pentagon interior angles) which are typically P6 or secondary. Notation lacks proper LaTeX for geometry symbols. ASCII art is used for diagrams which is insufficient for a formal math paper. The marking scheme total (55) does not match the header total (50).
7.9	Legacy generator	Mathematics	Quiz	3-0	geometry	10.0	9.0	6.0	9.0	10.0	8.0	Major issue: Multiple questions (Q2, Q9, Q10) refer to diagrams or grids that are missing. The difficulty is too low for P5; it focuses on P3/P4 concepts like symmetry and basic 3D shapes rather than P5-specific geometry like area of triangles or complex quadrilateral properties. The question count (20) does not match the section breakdown (5+5+4=14 questions provided).

Content Type Summary

Average scores grouped by content type.

Cheatsheet 9.6 5 artifacts, 1 with missing-image flags

Parents Guide 9.6 5 artifacts, 0 with missing-image flags

Quiz 8.5 52 artifacts, 20 with missing-image flags

Detailed Benchmark Rows

Topics, quiz variants, paper versions, cheatsheets, and parent guides listed individually.

Model	Type	Stage	Subject	Topic / Paper	Overall	Missing Images	Language	Syllabus	Template	Clean	Step Answers	Notation	Paper Format	Difficulty	Time Fit	3-Point Summary	Parent Guide	Difficulty	Comments
Claude Sonnet 4	Cheatsheet	2-7	Chinese	cheatsheet	9.5	No	9.5	8.5	-	10.0	-	10.0	-	9.0	-	10.0	-	appropriate	High quality cheatsheet. Uses effective three-point summaries (Key Vocabulary, Sentence Construction, Common Errors) for each topic. Language is appropriate for P5. Content aligns well with the focus on composition types and grammar required at this level.
Claude Sonnet 4	Cheatsheet	2-7	English	cheatsheet	9.7	No	9.5	10.0	-	10.0	-	-	-	9.0	-	10.0	-	appropriate	Excellent cheatsheet. It follows the syllabus perfectly, covering critical reading, advanced grammar, and writing techniques. Each section uses effective three-point summaries rather than generic lists. Language is highly appropriate for P5 Upper Primary level.
Claude Sonnet 4	Cheatsheet	2-7	Higher Chinese	cheatsheet	9.3	No	9.5	9.0	-	10.0	-	10.0	9.0	9.0	9.5	8.5	-	appropriate	High quality cheatsheet. Excellent use of tables and structured summaries. Content aligns well with P5 Higher Chinese requirements, including classical Chinese and advanced vocabulary. Three-point summaries are used effectively in most sections.
Claude Sonnet 4	Cheatsheet	2-7	Mathematics	cheatsheet	10.0	No	10.0	10.0	-	10.0	-	10.0	-	10.0	-	10.0	-	appropriate	Excellent cheatsheet. Highly aligned with the P5 MOE syllabus. Each chapter uses effective three-point summaries and clear examples. Notation is clean and appropriate for the level.
Claude Sonnet 4	Cheatsheet	2-7	Science	cheatsheet	9.3	Yes	9.5	9.0	-	10.0	-	10.0	-	9.0	-	8.5	-	appropriate	High quality cheatsheet. Language is perfect for P5. Adheres well to the MOE syllabus, including specific exclusions like not needing to know xylem/phloem names. Uses effective bulleted summaries rather than generic pointers. Missing diagrams for biological processes (reproduction, respiratory system) and electrical circuits which are essential for Science cheatsheets.
Legacy generator	Parents Guide	2-9	Chinese	parents-guide	10.0	No	10.0	10.0	-	10.0	-	-	-	10.0	-	-	10.0	appropriate	Excellent parent guide. Highly aligned with the 2024 MOE syllabus, specifically regarding the streaming phase and character recognition targets. Provides practical, actionable advice for home support across all three tracks.
Legacy generator	Parents Guide	2-9	English	parents-guide	10.0	No	10.0	10.0	-	10.0	-	-	-	10.0	-	-	10.0	appropriate	Excellent parent guide. Highly aligned with the MOE P5 English syllabus, covering critical reading, sophisticated writing, and grammar mastery. Practical advice and assessment schedules are well-structured.
Legacy generator	Parents Guide	2-9	Higher Chinese	parents-guide	9.4	No	9.5	9.0	-	10.0	-	-	-	9.0	-	-	9.5	appropriate	High quality parent guide. Accurately reflects the P5 Higher Chinese syllabus, including character recognition targets and the shift towards literary appreciation. The distinction between Chinese and Higher Chinese is well-articulated. Content is practical and supportive for parents.
Legacy generator	Parents Guide	2-9	Mathematics	parents-guide	10.0	No	10.0	10.0	-	10.0	-	10.0	-	10.0	-	-	10.0	appropriate	Excellent guide. Highly aligned with the MOE P5 syllabus, specifically noting the shift to heuristics and the inclusion of GST and volume. The use of ASCII/text-based models is a clever way to handle the lack of actual images. Very practical for parents.
Legacy generator	Parents Guide	2-9	Science	parents-guide	8.8	No	9.5	7.5	-	10.0	-	-	-	9.0	-	-	8.0	appropriate	Language is excellent for parents. Syllabus adherence is slightly flawed: it includes 'Cells' and 'Photosynthesis/Respiration' as major P5 topics, whereas the provided MOE syllabus lists these as part of the broader context or implies they are not the primary P5 focus areas compared to Reproduction, Water, and Electricity. It also includes 'Cell Theory' which is too advanced for P5. However, the guidance on reproduction and water cycle is very accurate.
Legacy generator	Quiz	5-1	Chinese	listening	8.2	No	9.0	8.5	7.0	10.0	9.0	-	7.5	6.0	9.0	-	-	too easy	The language is suitable for P5, but the content is too simplistic (closer to P3/P4 level). The listening passages lack the analytical depth, inference, or complex vocabulary required for the P5 streaming phase. The total marks in the scoring table (46) do not match the header (50). The format is decent but lacks the formal structure of a standard MOE listening paper.
Legacy generator	Quiz	5-1	Chinese	reading	8.9	No	9.0	9.0	8.5	10.0	9.5	10.0	8.0	7.5	9.0	-	-	too easy	Language and syllabus alignment are good. However, the reading passages and question types (direct retrieval) are slightly too simple for P5 Chinese/Higher Chinese standards, leaning more towards P3/P4 level. The total marks in the scoring table (45) do not match the header (50).
Legacy generator	Quiz	5-1	Chinese	speaking	9.0	Yes	9.5	9.0	8.5	10.0	9.0	-	8.0	9.0	9.0	-	-	appropriate	Language is highly appropriate for P5. The content follows the oral exam structure (Reading and Video/Picture Discussion). However, the 'Picture Description' section uses text placeholders instead of actual images, which is a critical missing component for a speaking quiz. The answer key provides excellent model responses.
Legacy generator	Quiz	5-1	Chinese	vocabulary	8.1	No	9.0	8.5	7.0	10.0	9.0	-	6.0	7.5	8.0	-	-	appropriate	Language and vocabulary are appropriate for P5. However, the exam paper format is inconsistent: the header states a total of 50 marks, but the answer key calculation results in 74 marks. The question types (synonyms/antonyms) are more characteristic of lower primary or general drills rather than the specific format of P5 MOE Chinese papers which focus more on contextual usage and comprehension.
Legacy generator	Quiz	5-1	Chinese	writing	8.8	Yes	9.5	9.0	8.5	10.0	9.0	-	8.0	9.0	7.0	-	-	appropriate	Language and content are highly appropriate for P5. The 'Picture Composition' section relies entirely on text descriptions because the actual images are missing, which is a major flaw for this specific task type. The timeframe is likely too short for a student to complete both a picture composition and a topical composition in one sitting. The answer key provides excellent model essays and rubric-based grading.
Legacy generator	Quiz	5-1	English	composition	8.3	Yes	9.5	9.0	7.0	10.0	5.0	10.0	7.5	8.5	8.0	-	-	appropriate	The artifact uses text descriptions instead of actual images for the picture composition, which is a major flaw for a primary school student. The structure combines three different writing tasks (Picture, Situational, Continuous) into one 50-mark quiz, which is atypical for a single exam paper but works as a comprehensive practice set. Marking guides are high quality with good sample answers.
Legacy generator	Quiz	5-1	English	comprehension	8.9	No	9.5	9.0	8.5	10.0	9.0	10.0	7.5	8.5	8.0	-	-	appropriate	Language and content are well-suited for P5. The marking scheme is excellent with clear point allocation. However, the total marks in the marking scheme (41) do not match the header (50), and the exam format lacks a specific time duration (e.g., 1 hour 30 mins) typically seen in MOE papers.
Legacy generator	Quiz	3-0	English	comprehension-open-ended	9.1	No	9.5	9.0	8.5	10.0	8.0	10.0	9.0	8.5	9.0	-	-	appropriate	High quality quiz. Content is highly relevant to Singapore context. Question distribution across literal, inferential, and critical levels is well-structured. Answer key provides good model answers and mark allocation. Minor note: 20 questions listed in header but only 15 are present in the body.
Legacy generator	Quiz	3-0	English	comprehension-open-ended	7.2	No	9.0	8.5	7.0	10.0	5.0	10.0	6.0	5.0	4.0	-	-	uneven	Major hallucination in answer key: the answers refer to a 'Singapore River' passage, but the quiz content is about 'Education System'. Question count and marks in the key do not match the quiz. Difficulty is uneven; Section C is too cognitively demanding for a 35-minute P5 quiz. Timeframe is unrealistic for 20 questions of this depth.
Legacy generator	Quiz	3-0	English	comprehension-visual	8.9	Yes	9.5	9.0	8.5	10.0	7.0	10.0	9.0	8.5	9.0	-	-	appropriate	The quiz is well-structured for P5 level. However, it relies entirely on text descriptions of images (placeholders) rather than actual visual assets, which is a critical failure for a 'visual comprehension' task. The answer key provides logic for calculations but lacks a true step-by-step pedagogical breakdown for complex inference questions. Difficulty is well-calibrated for Upper Primary.
Legacy generator	Quiz	3-0	English	comprehension-visual	8.4	Yes	9.0	9.5	7.0	10.0	5.0	10.0	8.5	8.0	9.0	-	-	appropriate	Major issue: The answer key is completely hallucinated. It provides answers for a 'Night Safari' and 'Recycling' topic, whereas the actual quiz questions are about 'Read for Singapore' and 'Screen Time'. The content of the quiz and the answer key do not match. Question templates for visual comprehension are generally good, but the mismatch makes the artifact unusable.
Legacy generator	Quiz	3-0	English	editing-spelling	8.1	No	9.0	8.5	7.0	10.0	9.0	-	7.5	6.0	8.0	-	-	uneven	The quiz has a major structural error: Section A contains 12 errors in the answer key but the instructions and question list only account for 10. Section B is significantly easier than Section A. The exam format is slightly inconsistent with standard Singaporean paper layouts regarding mark distribution and question numbering.
Legacy generator	Quiz	3-0	English	editing-spelling	6.2	No	9.0	8.0	5.0	10.0	0.0	10.0	7.0	2.0	5.0	-	-	uneven	Critical failure in answer key alignment: Section A answers refer to a completely different text (about habitats/Siberia) than the provided text (about Singapore heritage). Section B answers also do not match the questions asked in the quiz. The quiz content is appropriate for P5, but the mismatch makes it unusable.
Legacy generator	Quiz	5-1	English	grammar	9.3	No	9.5	10.0	8.5	10.0	10.0	10.0	7.5	9.0	9.0	-	-	appropriate	High quality grammar quiz. Content aligns perfectly with P5 syllabus (subject-verb agreement, conditionals, reported speech, passive voice). The marking scheme total (45) does not match the header total (50), which is a minor inconsistency. Question formats are standard for Singapore English papers.
Legacy generator	Quiz	3-0	English	grammar-synthesis	9.2	No	10.0	10.0	9.0	10.0	8.0	-	9.0	8.0	10.0	-	-	appropriate	High quality quiz. Content aligns well with P5 Synthesis & Transformation topics (Passive Voice, Reported Speech, Conjunctions). The answer key includes helpful teaching points. Minor discrepancy: header says 20 questions but only 15 are provided. Marks and timing are realistic.
Legacy generator	Quiz	3-0	English	grammar-synthesis	8.3	No	9.5	9.0	8.0	10.0	4.0	10.0	7.0	8.5	9.0	-	-	appropriate	Major discrepancy between the quiz and the answer key: the quiz contains 20 questions on specific topics (Complex Sentences, Voice, Conditionals), but the answer key provides answers for a completely different set of 15 questions (Sentence Combination, Voice, Reported Speech). The answer key is essentially for a different paper. Exam format is generally good but marks/questions mismatch in the key.
Legacy generator	Quiz	3-0	English	grammar-tenses	9.6	No	9.5	10.0	9.0	10.0	10.0	-	9.0	9.0	10.0	-	-	appropriate	High quality quiz. Tense coverage is excellent for P5 (including perfect and continuous forms). Answer key provides clear, pedagogical explanations. Format is professional and follows standard exam structures.
Legacy generator	Quiz	3-0	English	grammar-tenses	7.2	No	9.0	9.5	4.0	10.0	2.0	10.0	7.0	5.0	8.0	-	-	uneven	Major hallucination in the answer key: the questions in the answer key do not match the questions in the quiz. Section A, B, and C in the key are entirely different from the quiz content. Difficulty is uneven due to this mismatch.
Legacy generator	Quiz	5-1	English	oral	9.2	Yes	9.5	9.0	8.5	10.0	9.0	10.0	8.5	9.0	9.0	-	-	appropriate	High quality oral practice. The stimulus-based conversation follows the standard P5/P6 format (Reading Aloud + Stimulus-Based Conversation). Major issue: The actual picture for Part B is missing, replaced only by a text description, which makes it impossible for a student to perform the task as intended. The sample responses and marking rubrics are excellent and highly aligned with MOE standards.
Legacy generator	Quiz	5-1	English	vocabulary	8.7	No	9.5	9.0	7.0	10.0	9.0	10.0	6.0	8.5	9.0	-	-	appropriate	Vocabulary level is well-aligned with P5 expectations. Answer key provides helpful brief explanations. However, the exam paper format lacks essential components like total marks, time duration, and specific instructions for each section common in MOE papers. Section D and E are slightly easier than Section A/B.
Legacy generator	Quiz	3-0	English	vocabulary-cloze	9.1	No	9.5	9.0	8.5	10.0	9.5	10.0	8.0	8.5	9.0	-	-	appropriate	High quality content. Vocabulary and context are well-aligned with P5 Singapore standards. Section B marks (1.5 per question) are slightly unusual for standard MOE papers which typically use whole numbers, but the difficulty is appropriate. The answer key is excellent with clear explanations.
Legacy generator	Quiz	3-0	English	vocabulary-cloze	6.6	No	9.0	8.0	4.0	10.0	0.0	10.0	5.0	6.0	7.0	-	-	uneven	Major failure in answer key alignment: the answer key provided is for a completely different quiz (about Gardens by the Bay/Kaya toast) than the actual quiz generated (about Recycling). Section A in the quiz is Word Form Cloze, but the answer key describes Multiple Choice Cloze. Difficulty is uneven as Section A is quite mechanical while Section B is standard.
Legacy generator	Quiz	5-1	Higher Chinese	listening	8.1	No	9.0	8.5	7.0	10.0	9.0	-	6.0	7.0	8.0	-	-	appropriate	Language is suitable for P5 Higher Chinese. Content covers relevant themes like environment and culture. However, the total marks in the header (50) do not match the calculated total in the answer key (39). The question format is a bit generic and lacks the specific structure of official MOE listening papers (which usually involve specific question types like multiple choice and short answer with distinct scoring). Difficulty is appropriate for the level.
Legacy generator	Quiz	5-1	Higher Chinese	reading	8.6	No	9.0	8.5	8.0	10.0	9.5	-	7.5	8.0	8.0	-	-	appropriate	Language is suitable for P5 Higher Chinese. Includes good variety: MCQ, short answer, table completion, and classical Chinese (Guwen). Marks assigned to questions but total score in header (50) does not match the sum of parts (48). Answer key is excellent with clear marking logic.
Legacy generator	Quiz	5-1	Higher Chinese	speaking	8.9	Yes	9.5	9.0	8.5	10.0	9.0	-	8.0	9.0	8.5	-	-	appropriate	The content is highly appropriate for P5 Higher Chinese, featuring sophisticated vocabulary and deep discussion questions. However, the 'Picture Discussion' section relies entirely on text descriptions of images rather than actual images, which is a critical failure for an oral exam artifact. The answer key is excellent, providing high-quality model responses.
Legacy generator	Quiz	5-1	Higher Chinese	vocabulary	7.8	No	9.0	8.5	7.0	8.0	9.0	-	6.0	8.0	7.0	-	-	appropriate	Vocabulary level is appropriate for P5 Higher Chinese. Major issue: The total marks in the header (50) contradicts the actual sum in the scoring table (65). Question 21 contains a syntax error with an unmatched parenthesis. The format is more like a worksheet than a formal exam paper.
Legacy generator	Quiz	5-1	Higher Chinese	writing	8.8	Yes	9.5	9.0	8.5	10.0	9.0	-	8.0	9.0	7.0	-	-	appropriate	The content is high quality and aligns well with P5 Higher Chinese expectations for composition. However, the 'Picture Composition' section uses text descriptions instead of actual images, which is a major functional flaw for a visual task. The timeframe is unrealistic; asking a student to write two 250-word compositions (one visual, one topical) in a single sitting is too much for a standard practice session.
Legacy generator	Quiz	5-1	Mathematics	addition-subtraction	9.0	No	10.0	10.0	8.0	10.0	9.0	10.0	7.0	8.0	9.0	-	-	appropriate	Content is syllabus-aligned for P5 whole numbers. Note: Total marks in marking scheme (55) contradicts the header (50). Question structure is good but lacks the formal layout of actual MOE papers (e.g., specific instruction blocks).
Legacy generator	Quiz	3-0	Mathematics	area-perimeter	7.8	Yes	9.5	10.0	7.0	8.0	9.0	4.0	6.0	8.5	8.0	-	-	appropriate	The quiz content is syllabus-accurate for P5. Major issues: 1. Missing diagrams for composite shapes and word problems. 2. Lack of proper LaTeX for mathematical notation (uses plain text/symbols). 3. Question count (20) does not match the provided Section A/B/C breakdown (only 14 questions listed). 4. Exam format lacks standard marks distribution per question in the header.
Legacy generator	Quiz	3-0	Mathematics	data-analysis	8.4	Yes	10.0	9.0	7.0	10.0	10.0	5.0	8.0	8.0	9.0	-	-	appropriate	The quiz is well-structured and syllabus-aligned. However, it relies heavily on visual data (bar charts, pie charts, line graphs) which are provided only as text descriptions or placeholders, making it impossible for a student to actually 'see' the data. Notation for decimals and fractions is plain text rather than LaTeX. The number of questions (20) listed in the header does not match the actual number of questions provided (14).
Legacy generator	Quiz	5-1	Mathematics	data-analysis	9.1	Yes	10.0	10.0	8.0	10.0	9.0	10.0	7.0	8.5	9.0	-	-	appropriate	The quiz is well-structured and aligns with P5 Data Analysis. However, several questions (e.g., Q4 pie chart, Q8 bar graph) require visual diagrams that are missing. There is a mathematical inconsistency in the answer key for Q17: the sum calculation results in a mean of 27, but the text says 26.67. Also, the total marks in the header (50) does not match the marking scheme total (55).
Legacy generator	Quiz	3-0	Mathematics	decimals	9.3	No	10.0	10.0	8.5	10.0	9.5	10.0	9.0	8.0	9.0	-	-	appropriate	Quiz aligns well with P5 decimals syllabus. Question count in header (20) does not match actual questions provided (14). Difficulty is appropriate for P5 Standard level. Step-by-step solutions are clear and helpful.
Legacy generator	Quiz	3-0	Mathematics	fractions	8.3	No	10.0	10.0	8.0	10.0	10.0	2.0	7.0	9.0	9.0	-	-	appropriate	Content is syllabus-accurate and difficulty is well-calibrated for P5. Major issue: lacks proper LaTeX for fractions, using plain text slashes which is not standard for exam-derived materials. Question count in header (20) does not match actual questions provided (14).
Legacy generator	Quiz	5-1	Mathematics	fractions	8.0	No	10.0	10.0	7.0	10.0	10.0	2.0	6.0	8.0	9.0	-	-	appropriate	The quiz content is syllabus-accurate and follows a logical progression. However, it fails significantly on notation, using plain text slashes instead of proper LaTeX for fractions, which is standard for math papers. There is also a mathematical inconsistency in the marking scheme: the total marks sum to 55, but the header states 50. The question template lacks standard exam instructions (e.g., 'Show your working').
Legacy generator	Quiz	3-0	Mathematics	geometry	7.9	Yes	10.0	9.0	6.0	10.0	9.0	10.0	5.0	4.0	8.0	-	-	too easy	Major issue: Multiple questions (Q2, Q9, Q10) refer to diagrams or grids that are missing. The difficulty is too low for P5; it focuses on P3/P4 concepts like symmetry and basic 3D shapes rather than P5-specific geometry like area of triangles or complex quadrilateral properties. The question count (20) does not match the section breakdown (5+5+4=14 questions provided).
Legacy generator	Quiz	5-1	Mathematics	geometry	7.8	Yes	9.5	9.0	7.0	8.5	9.0	4.0	7.5	7.5	8.0	-	-	uneven	The quiz includes topics slightly beyond P5 (regular hexagon/pentagon interior angles) which are typically P6 or secondary. Notation lacks proper LaTeX for geometry symbols. ASCII art is used for diagrams which is insufficient for a formal math paper. The marking scheme total (55) does not match the header total (50).
Legacy generator	Quiz	3-0	Mathematics	measurement	9.2	Yes	10.0	10.0	8.0	10.0	10.0	9.0	8.0	9.0	9.0	-	-	appropriate	The quiz aligns well with P5 volume and conversion syllabus. Question count (20) vs total marks (50) is slightly inconsistent with the provided section breakdowns (10+20+20=50, but only 14 questions are listed). Missing diagrams for cuboids and cubes which are standard for this topic. Step-by-step answers are excellent.
Legacy generator	Quiz	5-1	Mathematics	measurement	9.1	No	10.0	10.0	8.0	10.0	9.0	10.0	7.0	9.0	9.0	-	-	appropriate	Content is high quality and aligns well with P5 measurement syllabus. Note: The total marks in the marking scheme (55) contradicts the header (50). Question 4 has duplicate options B and C in the text. Section D is appropriately challenging.
Legacy generator	Quiz	5-1	Mathematics	money	9.4	No	10.0	10.0	9.0	10.0	10.0	10.0	8.0	9.0	9.0	-	-	appropriate	High quality quiz. Content aligns well with P5 Money and Percentage syllabus. Note: The total marks in the marking scheme (55) contradicts the header (50). Step-by-step solutions are excellent.
Legacy generator	Quiz	5-1	Mathematics	multiplication-division	8.2	No	10.0	10.0	8.0	10.0	7.0	10.0	6.0	5.0	8.0	-	-	uneven	Major issues with answer key accuracy: Q3 has no correct option and Q4 has two correct options. The total marks in the marking scheme (55) do not match the header (50). Difficulty is uneven; Section A is very basic while Section D is standard. Exam format lacks time allocation and specific instructions.
Legacy generator	Quiz	3-0	Mathematics	percentage	8.7	No	10.0	10.0	8.0	10.0	10.0	5.0	7.0	9.0	9.0	-	-	appropriate	Content is syllabus-accurate and difficulty is well-calibrated for P5. Major issue: The metadata claims 20 questions, but only 14 are provided. Notation lacks LaTeX for fractions and multiplication, using plain text instead. Exam format is decent but lacks formal instruction headers.
Legacy generator	Quiz	3-0	Mathematics	rate	8.0	No	10.0	9.0	8.0	10.0	9.0	5.0	8.0	6.0	7.0	-	-	too hard	The quiz is too difficult for P5 Standard. It includes unit conversions (m/s to km/h) and complex combined rate problems (pipes filling a pool) which are typically P6 or secondary level concepts. Mathematical notation lacks LaTeX for fractions and division. Answer key for Q11 has a calculation error (8 - 6.67 is 1.33, not 1.6).
Legacy generator	Quiz	3-0	Mathematics	ratio	8.2	No	10.0	10.0	8.0	10.0	9.0	9.0	7.0	6.0	5.0	-	-	uneven	The quiz has significant internal inconsistencies. The metadata claims 20 questions, but only 14 are provided. The total marks (50) do not match the sum of the sections (10+20+20=50, which is correct, but the question count is wrong). The difficulty is uneven: Section A is very basic, while Section C contains complex multi-step problems. Question 13 has a calculation error in the answer key (170 vs 155). Question 14 involves repeating decimals which is unusual for P5 without rounding instructions in the question. Timeframe is unrealistic for the complexity of Section C.
Legacy generator	Quiz	3-0	Mathematics	whole-numbers	8.8	No	10.0	10.0	8.0	10.0	10.0	5.0	9.0	8.0	9.0	-	-	appropriate	The quiz aligns well with P5 Whole Numbers syllabus. Question 13 asks for 'standard form' which is a P6/Secondary concept, not P5. Notation lacks LaTeX for mathematical expressions and symbols. Answer key is excellent with clear step-by-step working.
Legacy generator	Quiz	5-1	Mathematics	whole-numbers	8.4	No	10.0	10.0	8.0	10.0	7.0	10.0	6.0	7.0	8.0	-	-	uneven	Major issue: Question 2 in Section A has no correct option among the choices. The answer key also admits the error. The total marks in the header (50) do not match the marking scheme total (55). Difficulty is uneven; Section A is very basic, while Section D is appropriate. Step-by-step answers are provided but the logic for Question 2 is broken.
Legacy generator	Quiz	5-1	Science	diversity	8.5	Yes	9.5	9.0	7.0	10.0	8.5	10.0	6.0	8.5	8.0	-	-	appropriate	Language and syllabus alignment are strong. However, the exam format is flawed: the total marks in the header (50) do not match the marking scheme total (46). Several questions (e.g., Q11, Q13) describe diagrams or tables that are text-based but would typically require visual aids in a real PSLE-style paper. The difficulty is well-calibrated for P5 Pre-PSLE.
Legacy generator	Quiz	5-1	Science	heat	9.2	Yes	9.5	10.0	8.5	9.0	9.5	10.0	8.0	9.0	9.0	-	-	appropriate	High quality quiz. Content aligns perfectly with P5 Heat syllabus. Uses ASCII art for diagrams which is a functional placeholder but real diagrams are required for actual exams. Marks total 47 instead of 50 as stated in header. Answer key is excellent with clear scientific reasoning.
Legacy generator	Quiz	5-1	Science	life-cycles	8.2	Yes	9.5	9.0	7.0	9.0	8.5	-	6.0	8.5	8.0	-	-	appropriate	The quiz covers the P5 life cycles syllabus well. However, it relies heavily on ASCII diagrams (flower and mosquito life cycle) which are poor substitutes for actual scientific diagrams required in Singapore exams. The total marks in the marking scheme (47) do not match the header (50). Section A uses 2 marks per MCQ, whereas standard PSLE format uses 1 mark per MCQ.
Legacy generator	Quiz	5-1	Science	light	8.1	Yes	9.5	6.0	8.0	9.0	9.0	10.0	7.0	5.0	9.0	-	-	too hard	Major syllabus misalignment: Light (refraction, reflection angles, solar eclipses) is typically a Secondary School topic in Singapore, not Primary 5. P5 Science focuses on Cycles and Systems. The difficulty is too high for the intended level due to this content mismatch.
Legacy generator	Quiz	5-1	Science	magnets	9.1	Yes	9.5	10.0	8.5	9.0	9.5	10.0	7.5	9.0	9.0	-	-	appropriate	High quality quiz. Content aligns well with P5 magnets syllabus. Major issue: relies heavily on ASCII diagrams (magnetic fields, magnet orientation) which are poor substitutes for actual scientific diagrams required in Science papers. Marks total 47 instead of 50 as stated in header. Answer key is excellent and provides clear reasoning.
Legacy generator	Quiz	5-1	Science	materials	9.1	No	10.0	10.0	8.0	10.0	9.0	10.0	7.0	9.0	9.0	-	-	appropriate	High quality quiz. Content aligns well with P5 Materials syllabus. Question templates are mostly standard, though Section B (True/False) is less common in modern PSLE-style papers compared to MCQ and Open-Ended. Marks total 47 instead of 50 as stated in header. Answer key is excellent with clear explanations.
Legacy generator	Quiz	5-1	Science	systems	7.3	Yes	9.0	4.0	6.0	10.0	9.0	10.0	7.0	3.0	8.0	-	-	too hard	Major syllabus misalignment: The content covers advanced secondary school biology (alveoli, blood components, heart chambers, bile, peristalsis) which is explicitly excluded from the P5 MOE syllabus. P5 should focus on basic parts and functions without detailed cellular or biochemical mechanisms. The quiz is too difficult for the intended level.

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

Latex/notation format

Exam paper format

Difficulty appropriateness

Doable within timeframe

Cheatsheet 3-point summaries

Parent guide syllabus fit