PRL-Bench - Statistical Physics: leaderboard
Metric: Score (0-100) on the statistical physics and complex systems (Stat) tasks, research tasks built from 100 Physical Review Letters papers; a GPT-5 judge awards pre-assigned points for final answers and intermediate rubric checkpoints, summed and normalized to 0-100, mean of five runs; code interpreter allowed, search disabled; higher is better. Source: arxiv.org. Saturation forecast: Around September 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 40.76 |
| 2 | GPT-5.4 | 33.88 |
| 3 | Claude Opus 4.6 | 32.1 |
| 4 | Qwen 3.5 Plus | 25.87 |
| 5 | Kimi K2.5 | 25.71 |
| 6 | Seed 2.0 Pro | 24.94 |
Interactive version: theaggregate.ai/benchmark?slug=prl-bench-statistical-physics · How It Works · Data refreshed daily, snapshot 2026-10-07.