General Reasoning on LB V1
74.98LB V1 ScoreMistral-Small (24B)
Evaluation Results
| Method | Links | |
|---|---|---|
| Mistral-Small (24B)Variant=Base2026.03 | 74.98 | |
| Nemotron-H-8k (8B)Variant=Base2026.03 | 71.35 | |
| Mistral-Small (24B)Variant=PRISM2026.03 | 69.52 | |
| Nemotron-H-8k (8B)Variant=PRISM2026.03 | 68.84 | |
| Granite-3.3 (8B)Variant=PRISM2026.03 | 66.48 | |
| Granite-3.3 (8B)Variant=Base2026.03 | 66.15 | |
| Granite-4 Micro (3B)Variant=Base2026.03 | 66.01 | |
| LLaMA-3.1 (8B)Variant=PRISM2026.03 | 65.21 | |
| Granite-4-H Micro (3B)Variant=Base2026.03 | 64.49 | |
| Granite-4-H Micro (3B)Variant=PRISM2026.03 | 64.21 | |
| Granite-4 Micro (3B)Variant=PRISM2026.03 | 62.91 | |
| LLaMA-3.1 (8B)Variant=Base2026.03 | 62.76 | |
| Mistral-7BVariant=Base2026.03 | 60.88 | |
| Mistral-7BVariant=PRISM2026.03 | 59.99 |