Benchmark Almanac

ScienceVision

GPT-6 Astra 0.53 leads since October 2026
Not in model cards

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.

Made by
UniPat AI and Elorian
Released
October 2026
Kind
Spatial reasoning and counting
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Strongest model tested
GPT-6 Astra #3 on the capability index
Last model added
November 2026
Scores refreshed
November 12th, 2026
12
Models scored on its own leaderboard

GPT-6 Astra leads with 0.53

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

  1. 0.53 GPT-6 Astra
  2. 0.49 GPT-6.1 Sol
  3. 0.46 Claude Fable 5.1
  4. 0.45 Claude Opus 5.5
  5. 0.43 Gemini 4 Argon
  6. 0.38 Qwen3.8 Max (0902)
  7. 0.36 Qwen3.8 Flash
  8. 0.36 Kimi K3
  9. 0.28 GLM-5.3-Flash
  10. 0.27 DeepSeek-V4-Flash
  11. 0.24 Doubao Seed Evolving
  12. 0.16 Tencent Hy4 preview
  1. 1 GPT-6 Astra 0.53
  2. 2 GPT-6.1 Sol 0.49
  3. 3 Claude Fable 5.1 0.46
  4. 4 Claude Opus 5.5 0.45
  5. 5 Gemini 4 Argon 0.43
  6. 6 Qwen3.8 Max (0902) 0.38
  7. 7 Qwen3.8 Flash 0.36
  8. 8 Kimi K3 0.36
  9. 9 GLM-5.3-Flash 0.28
  10. 10 DeepSeek-V4-Flash 0.27
  11. 11 Doubao Seed Evolving Nov 2026 0.24
  12. 12 Tencent Hy4 preview 0.16

Source: Official ScienceVision leaderboard

#ModelScoreSettingDateSource
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 Nov 2026 0.24 Nov 2026 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.

OpenAI
Own leaderboard 1 leader
GPT-6 Astra 0.53

Source: Official ScienceVision leaderboard

Scores over time

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

On the benchmark’s own leaderboard
0.20 0.30 0.40 0.50 0.60 2026 2027 0.20 0.30 0.40 0.50 0.60 2026 2027

Source: Official ScienceVision 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

All 281 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%