MAESTRO Piano Transcription
Models transcribe competition piano recordings into notes. The evaluator compares predictions with MIDI events captured by the instrument. Each composition appears in only one split.
Google scored the original 125 test performances. ByteDance evaluated version 2 with 178 test performances. The corrected version 3 has 177.
- Made by
- Google Magenta and the International Piano-e-Competition
- Released
- October 2018
- Kind
- Audio understanding and voice
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Arts
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- New versions replace it
- Run by
- Anyone
- In views
- Audio and speech
Transkun V2 (SemiCRF) tops the leaderboard with 98.3%
Best score per entry from OpenCodePapers’s leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 1 Transkun V2 (SemiCRF) 98.3%
- 2 hFT-Transformer 97.4%
- 3 YourMT3+ (YPTF.MoE+M) noPS 97%
- 4 YourMT3+ (YPTF.MoE+M) 96.5%
- 5 Semi-CRF 96.1%
- 6 MT3 single dataset 88%
Source: OpenCodePapers’s leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | Transkun V2 (SemiCRF) | 98.3% | arxiv.org | Official leaderboard | ||
| 2 | hFT-Transformer | 97.4% | arxiv.org | Official leaderboard | ||
| 3 | YourMT3+ (YPTF.MoE+M) noPS | 97% | arxiv.org | Official leaderboard | ||
| 4 | YourMT3+ (YPTF.MoE+M) | 96.5% | arxiv.org | Official leaderboard | ||
| 5 | Semi-CRF | 96.1% | proceedings.neurips.cc | Official leaderboard | ||
| 6 | MT3 | 88% | single dataset | arxiv.org | Official 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 Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy.
Qwen 3.8 Max 88.7%
- LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization.
Gemini 4 Argon 91.7%
- MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy.
Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy.
Qwen 3.8 Max 90.8%
- FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better.
Phi-4-multimodal 4.00%
- VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules.
Qwen3.5-Omni-Plus 93.1%
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 (6 entries).
- Pass Models scored 6 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom No scores yet.
Leaderboard import 3 pass
- Pass Importer We read the board on OpenCodePapers: 6 entries at the last read, none a model we track.
- 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.