PitchBench
Models listen to recordings and identify notes, intervals, chords, or melodies. The authors vary the instrument, timing, and background noise.
The authors publish task scores for six audio-language models and two specialist baselines. Three audio-language models have results for all 28 tasks.
- Made by
- University of California, Berkeley and Thoughtful Lab
- Released
- May 2026
- Kind
- Audio understanding and voice
- Level
- University
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Subject
- Arts
- Language
- English
- Interaction
- Single turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Audio and speech
- Strongest model tested
-
Gemini 3.1 Pro #40 on the capability index
- Last model added
- February 2026
- Scores refreshed
- November 20th, 2026
baseline/basic-pitch tops the leaderboard with 75.2% Gemini 3.1 Pro leads with 19.8%
Best score per entry from the benchmark's own 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. The best model we track is Gemini 3.1 Pro, at 19.8%. This view shows only models we track, each at its best.
- 1 baseline/basic-pitch 75.2%
- 2 baseline/dsp 73.2%
- 3
Gemini 3.1 Pro 19.8%
- 4 audio_flamingo_next_instruct 18.6%
- 5 openrouter_google_gemini_flash_latest 15.7%
Source: Official PitchBench leaderboard
- 1
Gemini 3.1 Pro 19.8%
Source: Official PitchBench leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | baseline/basic-pitch | 75.2% | Official leaderboard | ||
| 2 | baseline/dsp | 73.2% | Official leaderboard | ||
| 3 | | 19.8% | Feb 2026 | Official leaderboard | |
| 4 | audio_flamingo_next_instruct | 18.6% | Official leaderboard | ||
| 5 | openrouter_google_gemini_flash_latest | 15.7% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 19.8% | Feb 2026 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official PitchBench 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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 9 months ago, in February 2026, for Gemini 3.1 Pro. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the official leaderboard (5 entries).
- Pass Models scored 1 model we track, plus 4 other entries on its leaderboard.
- Warning Newest score The newest came 9 months ago, in February 2026, for Gemini 3.1 Pro.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3.1 Pro (#40).
- Pass Headroom The best is 19.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 1 row for models we track and 4 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.