STEMVerse - Mathematics - Differential Equations and Dynamical Systems: leaderboard
Metric: Few-shot accuracy (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen3-8B-Base | 59.09 |
| 2 | Qwen3-14B-Base | 54.99 |
| 3 | Qwen3-4B-Base | 53.52 |
| 4 | Qwen 2.5 3B Instruct | 51.91 |
| 5 | Qwen 2.5 7B | 50.44 |
| 6 | Qwen 2.5 14B | 49.56 |
| 7 | Qwen 2.5 7B Instruct | 49.41 |
| 8 | Qwen 2.5 14B Instruct | 42.23 |
| 9 | Llama 3.1 8B Instruct | 41.94 |
| 10 | Llama 3.2 3B Instruct | 36.51 |
| 11 | Qwen 2.5 3B | 36.22 |
| 12 | Llama 3.1 8B | 21.85 |
| 13 | Llama 3.2 3B | 9.24 |
Interactive version: theaggregate.ai/benchmark?slug=stemverse-mathematics-differential-equations-and-dynamical-systems · How It Works · Data refreshed daily, snapshot 2026-09-25.