Unsatz
Agents design experiments and propose equations for an unknown simulated system. Their final program must predict held-out interventions and conditions beyond the original experiments.
Nine language models attempt 80 systems in 20 domains.
- Made by
- University of California, Los Angeles
- Released
- October 2026
- Kind
- Research science
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Measures
- Capability
- Language
- English
- In and out
- Text, Time series, Code → Code, Actions
- Interaction
- Agentic
- Environment
- A simulator
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
GPT-6 Astra leads with 60% among models released by September 2026
Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- Claude Opus 5.5
- and 14 more
- 1 GPT-6 Astra 60%
- 2 Claude Fable 5.1 47.5%
- 3
Muse Spark 1.3 30%
- 4
Qwen 3.8 Max 28.8%
- 5 Grok 4.6 28.8%
- 6 GLM-5.3 27.5%
- 7
DeepSeek V4.1 Flash 22.5%
- 8 Kimi K3 21.3%
- 9
Gemini 3.8 Flash 21.3%
Source: The Unsatz paper
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 60% | Sep 2026 | Official leaderboard | |
| 2 | Claude Fable 5.1 | 47.5% | Sep 2026 | Official leaderboard | |
| 3 | | 30% | Sep 2026 | Official leaderboard | |
| 4 | | 28.8% | Aug 2026 | Official leaderboard | |
| 5 | Grok 4.6 | 28.8% | Aug 2026 | Official leaderboard | |
| 6 | GLM-5.3 | 27.5% | Aug 2026 | Official leaderboard | |
| 7 | | 22.5% | Sep 2026 | Official leaderboard | |
| 8 | Kimi K3 | 21.3% | Jul 2026 | Official leaderboard | |
| 9 | | 21.3% | Sep 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The Unsatz paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Unsatz 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 Science and reasoning
- GPQA Diamond In use 198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics.
Gemini 4 Carbon 97%
- Terminal-Bench-Science In use 70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate. GPT-6 Astra 68.1%
- BioMysteryBench In use Bioinformatics problems on anonymized real datasets that require real analysis with tools. Rubric-graded, with human-solvable and human-difficult splits. Claude Fable 5.2 83.7%
- FrontierScience In use Models solve physics, chemistry, and biology problems in an Olympiad track graded by short answer and a Research track graded by 10-point rubrics.
Intern-S2-397B 87%
- HiPhO In use Models solve theory problems from 2024 and 2025 physics olympiad exams, some with diagrams. Official marking schemes grade answers and steps, mapped to medal levels.
Gemini 3 Pro 78.3%
- LABBench2 In use 11 biology research sub-tasks (literature, figures, tables, patents, trials and more) with tool access. Macro-averaged accuracy. GPT-5.2 60.9%
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 (9 entries).
- Pass Models scored 9 models we track.
- Pass Newest score The newest is from September 2026, for DeepSeek V4.1 Flash.
- Note Frontier models Only 2 of the top 10 have a score. The strongest tested is GPT-6 Astra (#4).
- Pass Headroom The best is 60%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 9 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.