General Reasoning on LB V2
27.42LB V2 ScoreMistral-Small (24B)
Evaluation Results
| Method | Links | |
|---|---|---|
| Mistral-Small (24B)Variant=PRISM2026.03 | 27.42 | |
| Mistral-Small (24B)Variant=Base2026.03 | 27.29 | |
| Nemotron-H-8k (8B)Variant=PRISM2026.03 | 26.08 | |
| Nemotron-H-8k (8B)Variant=Base2026.03 | 23.84 | |
| Granite-3.3 (8B)Variant=PRISM2026.03 | 23.03 | |
| Granite-4 Micro (3B)Variant=Base2026.03 | 21.82 | |
| LLaMA-3.1 (8B)Variant=PRISM2026.03 | 21.46 | |
| Granite-4 Micro (3B)Variant=PRISM2026.03 | 20.53 | |
| Granite-3.3 (8B)Variant=Base2026.03 | 20.1 | |
| Mistral-7BVariant=PRISM2026.03 | 19.68 | |
| Granite-4-H Micro (3B)Variant=Base2026.03 | 18.99 | |
| Granite-4-H Micro (3B)Variant=PRISM2026.03 | 18.75 | |
| Mistral-7BVariant=Base2026.03 | 14.89 | |
| LLaMA-3.1 (8B)Variant=Base2026.03 | 14.09 |