Synthetic Sheet Music Reasoning Benchmark
Models answer questions about rhythm, chords, intervals, and scales. Each test question appears in text notation and as an image.
The authors provide 1,600 test questions per format. The Legato 2 team ran Gemini 3.1 Pro and GPT-5 on the visual test.
- Made by
- Zhilin Wang, Zhe Yang, and collaborators
- Released
- September 2025
- Kind
- Documents, charts and text in images
- Level
- School
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Arts
- Language
- English
- Interaction
- Single turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
- Strongest model tested
- GPT-5.4 #28 on the capability index
- Last model added
- March 2026
- Scores refreshed
- November 20th, 2026
gemini-3.1-flash tops the leaderboard with 95.5% Claude Opus 4.6 leads with 90.5% among models released by March 2026
Best score per entry from MuTheoryEval’s leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Claude Opus 4.6, at 90.5%. This view shows only models we track, each at its best.
The newest model with a score here came out in March 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 gemini-3.1-flash lite, temperature=0, max_output_tokens=4096, thinking={"level":"default"}, answer_format=MCQ 95.5%
- 2 Claude Opus 4.6 lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ 90.5%
- 3 gemini-3.1-flash (minimal) lite, temperature=0, max_output_tokens=4096, thinking={"level":"minimal"}, answer_format=MCQ 89%
- 4 Claude Sonnet 4.6 lite, temperature=0, max_output_tokens=8256, thinking={"budget_tokens":8000}, answer_format=MCQ 84%
- 5 deepseek-reasoner lite, max_output_tokens=4096, thinking=native, answer_format=MCQ 80%
- 6
Gemini 3.1 Flash-Lite lite, temperature=0, max_output_tokens=4096, thinking={"level":"default"}, answer_format=MCQ 78%
- 7 GPT-5.4 lite, max_output_tokens=1024, thinking=native, answer_format=MCQ 67.5%
- 8
Qwen3-Max lite, max_output_tokens=1024, thinking=native, answer_format=MCQ 67%
- 9 GLM-5 lite, max_output_tokens=4096, thinking=enabled, answer_format=MCQ 66%
- 10 Claude Haiku 4.5 lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ 63.5%
- 11 deepseek-chat lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ 59%
- 12 GPT-5.4 Mini lite, max_output_tokens=1024, thinking=native, answer_format=MCQ 54%
- 13 glm-z1-flash lite, max_output_tokens=4096, thinking=native, answer_format=MCQ 50.5%
Source: MuTheoryEval’s leaderboard
- 1 Claude Opus 4.6 lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ 90.5%
- 2 Claude Sonnet 4.6 lite, temperature=0, max_output_tokens=8256, thinking={"budget_tokens":8000}, answer_format=MCQ 84%
- 3
Gemini 3.1 Flash-Lite lite, temperature=0, max_output_tokens=4096, thinking={"level":"default"}, answer_format=MCQ 78%
- 4 GPT-5.4 lite, max_output_tokens=1024, thinking=native, answer_format=MCQ 67.5%
- 5
Qwen3-Max lite, max_output_tokens=1024, thinking=native, answer_format=MCQ 67%
- 6 GLM-5 lite, max_output_tokens=4096, thinking=enabled, answer_format=MCQ 66%
- 7 Claude Haiku 4.5 lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ 63.5%
- 8 GPT-5.4 Mini lite, max_output_tokens=1024, thinking=native, answer_format=MCQ 54%
Source: MuTheoryEval’s leaderboard
| # | Entry | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | gemini-3.1-flash | 95.5% | lite, temperature=0, max_output_tokens=4096, thinking={"level":"default"}, answer_format=MCQ | Apr 2026 | Official leaderboard | |
| 2 | Claude Opus 4.6 | 90.5% | lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ | Feb 2026 | Apr 2026 | Official leaderboard |
| 3 | gemini-3.1-flash (minimal) | 89% | lite, temperature=0, max_output_tokens=4096, thinking={"level":"minimal"}, answer_format=MCQ | Apr 2026 | Official leaderboard | |
| 4 | Claude Sonnet 4.6 | 84% | lite, temperature=0, max_output_tokens=8256, thinking={"budget_tokens":8000}, answer_format=MCQ | Feb 2026 | Apr 2026 | Official leaderboard |
| 5 | deepseek-reasoner | 80% | lite, max_output_tokens=4096, thinking=native, answer_format=MCQ | Apr 2026 | Official leaderboard | |
| 6 | | 78% | lite, temperature=0, max_output_tokens=4096, thinking={"level":"default"}, answer_format=MCQ | Mar 2026 | Apr 2026 | Official leaderboard |
| 7 | GPT-5.4 | 67.5% | lite, max_output_tokens=1024, thinking=native, answer_format=MCQ | Mar 2026 | Apr 2026 | Official leaderboard |
| 8 | | 67% | lite, max_output_tokens=1024, thinking=native, answer_format=MCQ | Sep 2025 | Apr 2026 | Official leaderboard |
| 9 | GLM-5 | 66% | lite, max_output_tokens=4096, thinking=enabled, answer_format=MCQ | Feb 2026 | Apr 2026 | Official leaderboard |
| 10 | Claude Haiku 4.5 | 63.5% | lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ | Oct 2025 | Apr 2026 | Official leaderboard |
| 11 | deepseek-chat | 59% | lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ | Apr 2026 | Official leaderboard | |
| 12 | GPT-5.4 Mini | 54% | lite, max_output_tokens=1024, thinking=native, answer_format=MCQ | Mar 2026 | Apr 2026 | Official leaderboard |
| 13 | glm-z1-flash | 50.5% | lite, max_output_tokens=4096, thinking=native, answer_format=MCQ | Apr 2026 | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 4.6 | 90.5% | lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ | Feb 2026 | Apr 2026 | Official leaderboard |
| 2 | Claude Sonnet 4.6 | 84% | lite, temperature=0, max_output_tokens=8256, thinking={"budget_tokens":8000}, answer_format=MCQ | Feb 2026 | Apr 2026 | Official leaderboard |
| 3 | | 78% | lite, temperature=0, max_output_tokens=4096, thinking={"level":"default"}, answer_format=MCQ | Mar 2026 | Apr 2026 | Official leaderboard |
| 4 | GPT-5.4 | 67.5% | lite, max_output_tokens=1024, thinking=native, answer_format=MCQ | Mar 2026 | Apr 2026 | Official leaderboard |
| 5 | | 67% | lite, max_output_tokens=1024, thinking=native, answer_format=MCQ | Sep 2025 | Apr 2026 | Official leaderboard |
| 6 | GLM-5 | 66% | lite, max_output_tokens=4096, thinking=enabled, answer_format=MCQ | Feb 2026 | Apr 2026 | Official leaderboard |
| 7 | Claude Haiku 4.5 | 63.5% | lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ | Oct 2025 | Apr 2026 | Official leaderboard |
| 8 | GPT-5.4 Mini | 54% | lite, max_output_tokens=1024, thinking=native, answer_format=MCQ | Mar 2026 | Apr 2026 | Official leaderboard |
Rankings by part
We read 9 parts from MuTheoryEval’s leaderboard, each ranking models on one part of the test, such as BarLinePlacementQuestion, ChordIdentificationQuestion and ChordKeyRootIdentificationQuestion. Claude Opus 4.6 leads 5 of them, and 3 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
BarLinePlacementQuestion
8 models we track have a score here.
- 1 Claude Opus 4.6 100%
- 2
Gemini 3.1 Flash-Lite ↑1 87%
- 3 GPT-5.4 ↑1 82.6%
- 4 Claude Sonnet 4.6 ↓2 73.9%
- 5
Qwen3-Max 69.6%
- 6 GLM-5 69.6%
- 7 GPT-5.4 Mini ↑1 34.8%
- 8 Claude Haiku 4.5 ↓1 26.1%
ChordIdentificationQuestion
8 models we track have a score here.
- 1 GPT-5.4 ↑3 100%
- 2
Qwen3-Max ↑3 83.3%
- 3 GLM-5 ↑3 83.3%
- 4 Claude Sonnet 4.6 ↓2 83.3%
- 5 GPT-5.4 Mini ↑3 83.3%
- 6 Claude Haiku 4.5 ↑1 66.7%
- 7 Claude Opus 4.6 ↓6 66.7%
- 8
Gemini 3.1 Flash-Lite ↓5 66.7%
ChordKeyRootIdentificationQuestion
8 models we track have a score here.
- 1 Claude Opus 4.6 83.3%
- 2 GLM-5 ↑4 70%
- 3 Claude Sonnet 4.6 ↓1 63.3%
- 4
Gemini 3.1 Flash-Lite ↓1 60%
- 5 GPT-5.4 ↓1 60%
- 6 Claude Haiku 4.5 ↑1 53.3%
- 7 GPT-5.4 Mini ↑1 46.7%
- 8
Qwen3-Max ↓3 43.3%
ChordsCompletionQuestion
8 models we track have a score here.
- 1 Claude Sonnet 4.6 ↑1 100%
- 2 Claude Opus 4.6 ↓1 88.9%
- 3
Qwen3-Max ↑2 83.3%
- 4 Claude Haiku 4.5 ↑3 83.3%
- 5
Gemini 3.1 Flash-Lite ↓2 83.3%
- 6 GLM-5 77.8%
- 7 GPT-5.4 ↓3 61.1%
- 8 GPT-5.4 Mini 44.4%
IntervalNumberQuestion
8 models we track have a score here.
- 1 Claude Opus 4.6 100%
- 2 Claude Sonnet 4.6 100%
- 3
Qwen3-Max ↑2 69.6%
- 4 GLM-5 ↑2 69.6%
- 5 GPT-5.4 Mini ↑3 60.9%
- 6 Claude Haiku 4.5 ↑1 56.5%
- 7 GPT-5.4 ↓3 56.5%
- 8
Gemini 3.1 Flash-Lite ↓5 47.8%
NoteCompletionByInterval
8 models we track have a score here.
- 1 Claude Opus 4.6 87%
- 2 Claude Sonnet 4.6 82.6%
- 3
Gemini 3.1 Flash-Lite 78.3%
- 4
Qwen3-Max ↑1 73.9%
- 5 Claude Haiku 4.5 ↑2 69.6%
- 6 GLM-5 60.9%
- 7 GPT-5.4 ↓3 60.9%
- 8 GPT-5.4 Mini 56.5%
ScaleIdentificationFromAbcQuestion
8 models we track have a score here.
- 1 Claude Sonnet 4.6 ↑1 92%
- 2
Gemini 3.1 Flash-Lite ↑1 92%
- 3 Claude Opus 4.6 ↓2 90%
- 4 GLM-5 ↑2 84%
- 5 Claude Haiku 4.5 ↑2 80%
- 6 GPT-5.4 ↓2 76%
- 7
Qwen3-Max ↓2 62%
- 8 GPT-5.4 Mini 62%
ScaleSelectionQuestion
8 models we track have a score here.
- 1
Qwen3-Max ↑4 100%
- 2 Claude Haiku 4.5 ↑5 100%
- 3 Claude Opus 4.6 ↓2 100%
- 4 GLM-5 ↑2 100%
- 5 Claude Sonnet 4.6 ↓3 100%
- 6 GPT-5.4 ↓2 100%
- 7
Gemini 3.1 Flash-Lite ↓4 50%
- 8 GPT-5.4 Mini 50%
TimeSignatureQuestion
8 models we track have a score here.
- 1 Claude Opus 4.6 92%
- 2
Gemini 3.1 Flash-Lite ↑1 92%
- 3
Qwen3-Max ↑2 76%
- 4 Claude Sonnet 4.6 ↓2 76%
- 5 Claude Haiku 4.5 ↑2 60%
- 6 GLM-5 60%
- 7 GPT-5.4 ↓3 56%
- 8 GPT-5.4 Mini 56%
The best score, 90.5%, costs $0.17 for the full run
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: MuTheoryEval’s leaderboard
| Model | Effort | Harness | Score | Cost of the full run | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 4.6 | lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ | 90.5% | $0.17 | 4 | |
| Claude Sonnet 4.6 | lite, temperature=0, max_output_tokens=8256, thinking={"budget_tokens":8000}, answer_format=MCQ | 84% | $0.10 | 189 | |
| lite, temperature=0, max_output_tokens=4096, thinking={"level":"default"}, answer_format=MCQ | 78% | $0.008 | 1 | ||
| Claude Sonnet 4.6 | lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ | 71.5% | $0.10 | 4 | |
| GPT-5.4 | lite, max_output_tokens=1024, thinking=native, answer_format=MCQ | 67.5% | $0.08 | 4 | |
| lite, max_output_tokens=1024, thinking=native, answer_format=MCQ | 67% | $0.03 | 1 | ||
| GLM-5 | lite, max_output_tokens=4096, thinking=enabled, answer_format=MCQ | 66% | $0.03 | 1,963 | |
| Claude Haiku 4.5 | lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ | 63.5% | $0.03 | 4 | |
| GLM-5 | lite, temperature=0, max_output_tokens=1024, thinking=false, answer_format=MCQ | 63.5% | $0.03 | 2 | |
| GPT-5.4 Mini | lite, max_output_tokens=1024, thinking=native, answer_format=MCQ | 54% | $0.03 | 6 |
The best score, 90.5%, costs $0.17 for the full run
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: MuTheoryEval’s leaderboard
| Model | Effort | Harness | Score | Cost of the full run | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 4.6 | lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ | 90.5% | $0.17 | 4 | |
| Claude Sonnet 4.6 | lite, temperature=0, max_output_tokens=8256, thinking={"budget_tokens":8000}, answer_format=MCQ | 84% | $0.10 | 189 | |
| lite, temperature=0, max_output_tokens=4096, thinking={"level":"default"}, answer_format=MCQ | 78% | $0.008 | 1 | ||
| Claude Sonnet 4.6 | lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ | 71.5% | $0.10 | 4 | |
| GPT-5.4 | lite, max_output_tokens=1024, thinking=native, answer_format=MCQ | 67.5% | $0.08 | 4 | |
| lite, max_output_tokens=1024, thinking=native, answer_format=MCQ | 67% | $0.03 | 1 | ||
| GLM-5 | lite, max_output_tokens=4096, thinking=enabled, answer_format=MCQ | 66% | $0.03 | 1,963 | |
| Claude Haiku 4.5 | lite, temperature=0, max_output_tokens=16, thinking=false, answer_format=MCQ | 63.5% | $0.03 | 4 | |
| GLM-5 | lite, temperature=0, max_output_tokens=1024, thinking=false, answer_format=MCQ | 63.5% | $0.03 | 2 | |
| GPT-5.4 Mini | lite, max_output_tokens=1024, thinking=native, answer_format=MCQ | 54% | $0.03 | 6 |
2 models have held number one on MuTheoryEval’s leaderboard since its release in September 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: MuTheoryEval’s leaderboard
Claude Opus 4.6 on the official leaderboard passed 85% in February 2026
That was 5 months after its release. By the same age, 14% of the benchmarks from 2025 had passed 85%. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: MuTheoryEval’s leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy.
Qwen 3.6 Plus 86%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy.
Seed2.1 Pro 90.7%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7%
- MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy.
Qwen 3.8 Max 85.9%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (13 entries).
- Pass Models scored 8 models we track, plus 5 other entries on its leaderboard.
- Note Newest score The newest came 8 months ago, in March 2026, for GPT-5.4 Mini. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.4 (#28).
- Note Headroom Saturated. The best is 90.5%, past 85% since February 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on MuTheoryEval: 10 rows for models we track and 5 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.