facebook/cwm-pretrain
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| MATH-500 | math | 97.2 | low | | Qwen3-32B | 65.7 | 61.9 | 97.2 | 81.4 | 72.9 | | |
| AIME 2024 | math | 86.1 | low | | Magistral-small-2509-24B | 70.0 | 61.6 | -- | 86.1 | 77.3 | | |
| AIME 2025 | math | 77.3 | low | | Magistral-small-2509-24B | 70.0 | 61.6 | -- | 86.1 | 77.3 | | |
| SWE-bench Verified | swe | 53.6 | low | | Devstral-1.1-2507-24B | 53.6 | |
none scraped.