Mungert/Olmo-3-1025-7B-GGUF
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| WinoGrande | knowledge | 88.6 | low | | Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 | | |
| PIQA | knowledge | 85.7 | low | | Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 | | |
| HellaSwag | knowledge | 84.0 | low | | Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 | | |
| DROP | reasoning | 63.7 | low | | Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 | | |
| MMLU | knowledge | 58.1 | low | | Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 | | |
| BBH | reasoning | 55.6 | low | | Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 | | |
| MedQA | domain | 47.3 | low | | Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 | | |
| MATH | math | 39.6 | low | | Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 | | |
| MMLU-Pro | knowledge | 38.8 | low | | Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 | | |
| MBPP | coding | 36.5 | low | | Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 | | |
| HumanEval | coding | 31.6 | low | | Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 | | |
| BigCodeBench | coding | 21.5 | low | | Marin-8B | 39.6 | 21.5 | 31.6 | 0.5 | 16.5 | 36.5 | 15.6 | 27.6 | 21.4 | 89.2 | 58.1 | 52.7 | 47.3 | 93.2 | 68.1 | 71.4 | 77.4 | 68.3 | 75.3 | 85.7 | 79.8 | 86.2 | 63.7 | 90.8 | |
none scraped.