CompassArena Multimodal
Qwen3-VL-235B-A22B-Instruct 1,173 leads the models we track Users compare anonymous multimodal model answers and vote for the better response. A Bradley-Terry model estimates ratings from these votes.
The public summary API exposes ten ranked models. Its total model count is larger, and the full-table callback currently fails.
- Kind
- General visual questions
- Level
- Everyday
- Scored
- Ranked by votes
- Answers
- Open-ended
- Tasks
- All public
- Strongest model tested
- GPT-5 #70 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 12th, 2026
Doubao-Seed-1.6-Vision-250815 tops the leaderboard with 1,226
Best score per entry from the benchmark's own leaderboard, read on November 12th, 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 Qwen3-VL-235B-A22B-Instruct, at 1,173.
The newest model with a score here came out in September 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
Bars start at 1,000.
- 1 Doubao-Seed-1.6-Vision-250815 1,226
- 2 Qwen3-VL-235B-A22B-Instruct 1,173
- 3
Intern-S1 1,155 - 4 Hunyuan-Turbo-Vision 1,103
- 5 GPT-4.1 1,096
- 6 GLM-4.5V 1,089
- 7 GLM-4.1V-9B-Thinking 1,073
- 8 Qwen-VL-Max 1,071
- 9 GPT-5 1,069
- 10 Claude 3.5 Sonnet (October 2024) 1,026
Source: Official CompassArena Multimodal leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Doubao-Seed-1.6-Vision-250815 | 1,226 | Jun 2026 | Official leaderboard | |
| 2 | Qwen3-VL-235B-A22B-Instruct | 1,173 | Sep 2025 | Official leaderboard | |
| 3 | Intern-S1 | 1,155 | Jul 2025 | Official leaderboard | |
| 4 | Hunyuan-Turbo-Vision | 1,103 | Jun 2026 | Official leaderboard | |
| 5 | GPT-4.1 | 1,096 | Apr 2025 | Official leaderboard | |
| 6 | GLM-4.5V | 1,089 | Aug 2025 | Official leaderboard | |
| 7 | GLM-4.1V-9B-Thinking | 1,073 | Jul 2025 | Official leaderboard | |
| 8 | Qwen-VL-Max | 1,071 | Jan 2024 | Official leaderboard | |
| 9 | GPT-5 | 1,069 | Aug 2025 | Official leaderboard | |
| 10 | Claude 3.5 Sonnet (October 2024) | 1,026 | Oct 2024 | Official leaderboard |
4 models have held number one on the official leaderboard since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official CompassArena Multimodal 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 CompassArena Multimodal leaderboard
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 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. GPT-5.1 85.4%
- 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%
- 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%
- ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance.
Command A Vision 90.9%