ScienceBoard-Verified - GRASS GIS: leaderboard
ScienceBoard-Verified scientific computer-use tasks across KAlgebra, Celestia, GRASS GIS, ChimeraX, Lean 4 and TeXstudio; source success rate, with Average the unweighted mean of six applications. Model-based API harness uses the latest three steps plus the current screenshot/accessibility tree; native Grok Build/Codex maintain persistent per-task sessions, with web search disabled. Resource construction and harness identities remain separate run configurations. GRASS GIS.
Metric: Success rate (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 46 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 (xhigh) (ScienceCUA Run: harness=model-based; resource=Full%20ScienceCUA; evolution=108%20additional%20tasks%3B%20frozen%20library) | 64.71 | |
| 2 | GPT-5.5 (xhigh) (ScienceCUA Run: harness=Codex; resource=ScienceCUA) | 61.76 | |
| 3 | GPT-5.5 (xhigh) (ScienceCUA Run: harness=model-based; resource=%E2%88%92Failure%20history; evolution=108%20additional%20tasks%3B%20frozen%20library) | 61.76 | |
| 4 | GPT-5.5 (xhigh) (ScienceCUA Run: harness=model-based; resource=SkillCAT; evolution=108%20additional%20tasks%3B%20frozen%20library) | 61.76 | |
| 5 | GPT-5.5 (xhigh) (ScienceCUA Run: harness=model-based; resource=%E2%88%92Knowledge%20addition; evolution=108%20additional%20tasks%3B%20frozen%20library) | 58.82 | |
| 6 | GPT-5.5 (xhigh) (ScienceCUA Run: harness=model-based; resource=Trace2Skill; evolution=108%20additional%20tasks%3B%20frozen%20library) | 58.82 | |
| 7 | GPT-5.5 (xhigh) (ScienceCUA Run: harness=model-based; resource=Direct%20injection) | 55.88 | |
| 8 | GPT-5.5 (xhigh) (ScienceCUA Run: harness=model-based; resource=ScienceCUA) | 55.88 | |
| 9 | GPT-5.5 (xhigh) (ScienceCUA Run: harness=Codex; resource=visualskill) | 55.88 | |
| 10 | GPT-5.5 (xhigh) (ScienceCUA Run: harness=Codex; resource=skillfoundry) | 55.88 |
Interactive version: theaggregate.ai/benchmark?slug=scienceboard-verified-grass-gis · How It Works · Data refreshed daily, snapshot 2026-11-05.