ScienceVision
Agents inspect 3D scientific data such as proteins, crystals, CAD assemblies, buildings and CT volumes, then answer 250 expert questions. A rule-based scorer grades each answer field.
Three settings: source files with code, source files plus an inspection MCP, and rendered 2D views only. Scores are mean answer_score from 0 to 1. GPT-6 Astra leads at 0.53.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
GPT-6 Astra leads with 0.53
Best score per entry from the benchmark's own leaderboard, read on 2 Nov 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 GPT-6 Astra 0.53
- 2 GPT-6.1 Sol 0.49
- 3 Claude Fable 5.1 0.46
- 4 Claude Opus 5.5 0.45
- 5
Gemini 4 Argon 0.43 - 6
Qwen3.8 Max (0902) 0.38 - 7 Qwen3.8 Flash 0.36
- 8 Kimi K3 0.36
- 9 GLM-5.3-Flash 0.28
- 10
DeepSeek-V4-Flash 0.27 - 11 Doubao Seed Evolving 0.24
- 12
Tencent Hy4 preview 0.16
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 0.53 | Sep 2026 | Official leaderboard | |
| 2 | GPT-6.1 Sol | 0.49 | Sep 2026 | Official leaderboard | |
| 3 | Claude Fable 5.1 | 0.46 | Sep 2026 | Official leaderboard | |
| 4 | Claude Opus 5.5 | 0.45 | Sep 2026 | Official leaderboard | |
| 5 | Gemini 4 Argon | 0.43 | Sep 2026 | Official leaderboard | |
| 6 | Qwen3.8 Max (0902) | 0.38 | Sep 2026 | Official leaderboard | |
| 7 | Qwen3.8 Flash | 0.36 | Aug 2026 | Official leaderboard | |
| 8 | Kimi K3 | 0.36 | Jul 2026 | Official leaderboard | |
| 9 | GLM-5.3-Flash | 0.28 | Aug 2026 | Official leaderboard | |
| 10 | DeepSeek-V4-Flash | 0.27 | Apr 2026 | Official leaderboard | |
| 11 | Doubao Seed Evolving | 0.24 | Official leaderboard | ||
| 12 | Tencent Hy4 preview | 0.16 | Aug 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No lab model card reports it yet
We read the headline results of 479 launch posts from 51 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. Kimi K3.1 Pro 84.1%
- 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%
- 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% - DocVQA In use Models answer 50,000 questions about 12,000 scanned document images by reading their text and layout. Scoring is ANLS, a string similarity to reference answers.
Seed1.5-VL 96.9%