Mathematical Reasoning on MATH (test) (p@k, Recall@k)
435p@6=0Mistral-Nemo-12B
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Mistral-Nemo-12BModel Family=Mistral-Nemo, Parameters=12B2026.06 | 435 | 16 | 39 | 64 | 75 | |
| Qwen-2.5-3BModel Family=Qwen-2.5, Parameters=3B2026.06 | 293 | 10 | 23 | 39 | 48 | |
| Llama-3.1-8BModel Family=Llama-3.1, Parameters=8B2026.06 | 291 | 9 | 22 | 30 | 36 | |
| Llama-3.2-3BModel Family=Llama-3.2, Parameters=3B2026.06 | 287 | 11 | 24 | 42 | 50 |