PetriBench - Boundedness (Hard): leaderboard
Metric: Exact-Match Accuracy (%). Source: arxiv.org. 36 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (xHigh) | 69 |
| 2 | GPT-5.6 Sol (High) | 65 |
| 3 | Claude Opus 5 (High) | 60 |
| 4 | Claude Sonnet 5 (Medium) | 58 |
| 5 | Gemini 3.8 Flash (High) | 55.5 |
| 6 | Claude Opus 5 (xHigh) | 54.5 |
| 7 | GLM-5 | 54 |
| 8 | Kimi K2.5 | 52.5 |
| 9 | Claude Sonnet 5 (High) | 52.5 |
| 10 | Claude Opus 5 (Medium) | 52.5 |
| 11 | Gemma 4 31B (High) | 52 |
| 12 | Gemini 3.8 Flash (Medium) | 51.5 |
| 13 | Grok 4.6 (High) | 51 |
| 14 | Claude Haiku 4.5 | 50.5 |
| 15 | Grok 4.6 (xHigh) | 50.5 |
Interactive version: theaggregate.ai/benchmark?slug=petribench-boundedness-hard · How It Works · Data refreshed daily, snapshot 2026-09-20.