STEMVerse - Chemistry - Inorganic Chemistry: leaderboard
Metric: Few-shot accuracy (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen3-14B-Base | 32.95 |
| 2 | Qwen3-4B-Base | 27.46 |
| 3 | Qwen 2.5 14B Instruct | 27.17 |
| 4 | Qwen 2.5 7B | 25.14 |
| 5 | Qwen 2.5 7B Instruct | 24.57 |
| 6 | Qwen3-8B-Base | 24.28 |
| 7 | Llama 3.1 8B Instruct | 22.25 |
| 8 | Llama 3.1 8B | 21.39 |
| 9 | Qwen 2.5 14B | 21.39 |
| 10 | Qwen 2.5 3B | 18.21 |
| 11 | Qwen 2.5 3B Instruct | 16.47 |
| 12 | Llama 3.2 3B | 16.47 |
| 13 | Llama 3.2 3B Instruct | 15.9 |
Interactive version: theaggregate.ai/benchmark?slug=stemverse-chemistry-inorganic-chemistry · How It Works · Data refreshed daily, snapshot 2026-09-25.