Petri-Bench - Origin: leaderboard
LLM solvers probe simulated systems, infer hidden parameters and try to achieve target outcomes. Reports overall performance, solved cases, parameter recovery and individual simulation engines. Non-LLM search baselines remain outside the model comparison. This board reports Petri-Bench - Origin using Score.
Metric: Score. Source: huggingface.co. Saturation forecast: Not forecast. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 80.2 | #94 |
| 2 | GLM-5.1 | 79.7 | #109 |
| 3 | Claude Haiku 4.5 | 72.4 | #287 |
| 4 | Claude Opus 4.8 | 65.4 | #39 |
| 5 | Gemini 3.1 Pro (Preview) | 64.5 | #64 |
| 6 | GPT-5.6 Sol | 61.4 | #22 |
| 7 | GPT-5.5 | 60.7 | #33 |
| 8 | Claude Fable 5 | 48.3 | #20 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=petri-bench-origin · How It Works · Data refreshed daily, snapshot 2026-11-05.