McStasBench
Agents design neutron scattering instruments. A simulator checks whether their designs reproduce published measurements. The authors score two additional instruments separately.
The maintainers publish scores for seven models across 16 tasks with and without tools. They update the tables from recorded trials.
- Made by
- Oak Ridge National Laboratory
- Released
- September 2026
- Kind
- Lab and data work
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- McStas
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- Claude Sonnet 5 #35 on the capability index
- Last model added
- July 2026
- Scores refreshed
- November 20th, 2026
Claude Sonnet 5 leads with 43.8% among models released by July 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
The newest model with a score here came out in July 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
- GPT-6 Astra
- and 16 more
- 1 Claude Sonnet 5 oneshot 43.8%
- 2
Gemini 3.6 Flash oneshot 37.5%
- 3 Claude Haiku 4.5 main 25%
- 4
Qwen3-32B main 18.8%
- 5
Llama 4 Maverick oneshot 12.5%
- 6
Gemini 3.5 Flash-Lite main 12.5%
- 7
Qwen3-8B main 6.25%
Source: Official McStasBench leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 5 | 43.8% | oneshot | Jun 2026 | Official leaderboard |
| 2 | | 37.5% | oneshot | Jul 2026 | Official leaderboard |
| 3 | Claude Haiku 4.5 | 25% | main | Oct 2025 | Official leaderboard |
| 4 | | 18.8% | main | Apr 2025 | Official leaderboard |
| 5 | | 12.5% | oneshot | Apr 2025 | Official leaderboard |
| 6 | | 12.5% | main | Jul 2026 | Official leaderboard |
| 7 | | 6.25% | main | Apr 2025 | Official leaderboard |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official McStasBench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Sonnet 5 | oneshot | 43.8% | |||
| oneshot | 37.5% | ||||
| Claude Sonnet 5 | main | 31.3% | |||
| Claude Haiku 4.5 | main | 25% | |||
| Claude Haiku 4.5 | oneshot | 25% | |||
| main | 25% | ||||
| main | 18.8% | ||||
| oneshot | 12.5% | ||||
| main | 12.5% | ||||
| main | 6.25% | ||||
| oneshot | 6.25% | ||||
| main | 0% | ||||
| oneshot | 0% | ||||
| oneshot | 0% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official McStasBench 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 McStasBench 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
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (7 entries).
- Pass Models scored 7 models we track.
- Pass Newest score The newest is from July 2026, for Gemini 3.5 Flash-Lite.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Sonnet 5 (#35).
- Pass Headroom The best is 43.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 14 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.