STEMVerse - Physics - Thermodynamics and Statistical Physics: leaderboard
Metric: Few-shot accuracy (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen3-14B-Base | 28.45 |
| 2 | Qwen3-8B-Base | 20.22 |
| 3 | Llama 3.1 8B Instruct | 20.08 |
| 4 | Llama 3.1 8B | 17.99 |
| 5 | Qwen 2.5 3B | 16.32 |
| 6 | Llama 3.2 3B | 15.48 |
| 7 | Qwen 2.5 14B Instruct | 15.06 |
| 8 | Qwen 2.5 7B | 15.06 |
| 9 | Qwen 2.5 14B | 14.37 |
| 10 | Llama 3.2 3B Instruct | 12.13 |
| 11 | Qwen3-4B-Base | 11.58 |
| 12 | Qwen 2.5 7B Instruct | 10.46 |
| 13 | Qwen 2.5 3B Instruct | 9.92 |
Interactive version: theaggregate.ai/benchmark?slug=stemverse-physics-thermodynamics-and-statistical-physics · How It Works · Data refreshed daily, snapshot 2026-09-25.