Benchmark Almanac

OmniScore-Bench

GPT-6.1 Sol 91.0 leads since November 2026
Not in model cards

Models read sheet music, locate symbols, and transcribe passages. The evaluator checks their responses against annotations for the relevant part of the score.

The authors compare 12 models on 3,000 questions.

Released
November 2026
Kind
Documents, charts and text in images
Level
University
Scored
Checked automatically
Answers
Short answer
Measures
Capability
Subject
Arts
Language
English
In and out
Images, Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
A host
In views
Vision
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
October 2026
Scores refreshed
November 20th, 2026
12
Models scored in its paper

GPT-6.1 Sol leads with 91.0

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper gives no overall score, so the headline is its first measure, localization F1 for noteheads and rests, in percent. Where a model ran with several settings or harnesses, we keep its best.

  1. 1 GPT-6.1 Sol 91.0
  2. 2 GPT-6 Astra 89.8
  3. 3 Gemini 4 Argon 75.1
  4. 4 Kimi K3.1 Pro 36.4
  5. 5 Kimi K3 20.9
  6. 6 Claude Opus 5.5 7.90
  7. 7 Qwen 3.8 Max 7.50
  8. 8 Claude Fable 5.1 4.10
  9. 9 DeepSeek V4.1 Flash 0.40
  10. 10 Gemini 3.8 Flash 0.20
  11. 11 GLM-5.3-Flash 0.10
  12. 12 Qwen3.7-Plus 0.00

Source: The OmniScore-Bench paper

#ModelScoreSettingDateSource
1 GPT-6.1 Sol 91.0 Sep 2026 Official leaderboard
2 GPT-6 Astra 89.8 Sep 2026 Official leaderboard
3 Gemini 4 Argon 75.1 Sep 2026 Official leaderboard
4 Kimi K3.1 Pro 36.4 Oct 2026 Official leaderboard
5 Kimi K3 20.9 Jul 2026 Official leaderboard
6 Claude Opus 5.5 7.90 Sep 2026 Official leaderboard
7 Qwen 3.8 Max 7.50 Aug 2026 Official leaderboard
8 Claude Fable 5.1 4.10 Sep 2026 Official leaderboard
9 DeepSeek V4.1 Flash 0.40 Sep 2026 Official leaderboard
10 Gemini 3.8 Flash 0.20 Sep 2026 Official leaderboard
11 GLM-5.3-Flash 0.10 Aug 2026 Official leaderboard
12 Qwen3.7-Plus 0.00 Jun 2026 Official leaderboard

Rankings by part

We read 24 parts from the benchmark’s paper, each ranking models on one part of the test, such as T1.1: Noteheads and rests, T1.2: Clefs and accidentals and T1.3: Rhythmic marks. GPT-6 Astra leads 17 of them, and 4 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

T1.1: Noteheads and rests

12 models we track have a score here.

  1. 1 GPT-6.1 Sol 91%
  2. 2 GPT-6 Astra 89.8%
  3. 3 Gemini 4 Argon 75.1%
  4. 4 Kimi K3.1 Pro 36.4%
  5. 5 Kimi K3 20.9%
  6. 6 Claude Opus 5.5 7.90%
  7. 7 Qwen 3.8 Max 7.50%
  8. 8 Claude Fable 5.1 4.10%
  9. 9 DeepSeek V4.1 Flash 0.40%
  10. 10 Gemini 3.8 Flash 0.20%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Benchmark paper 1 leader

Source: The OmniScore-Bench paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper
0.00 20.0 40.0 60.0 80.0 100.0 2026 2027 0.00 20.0 40.0 60.0 80.0 100.0 2026 2027

Source: Official OmniScore-Bench 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

All 636 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

9 of 10 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (12 entries).
  • Pass Models scored 12 models we track.
  • Pass Newest score The newest is from October 2026, for Kimi K3.1 Pro.
  • Pass Frontier models 5 of the top 10 have a score, led by GPT-6 Astra (#4).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 12 rows for models we track 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.

How we check