reasoning · gpqa · 6 scores
https://huggingface.co/spaces/gpqa
| rank | variant | root | org | score | conf | context |
|---|---|---|---|---|---|---|
| 1 | Mistral-Small-24B-Instruct-2501 | mistralai/Mistral-Small-24B-Base-2501 | mistralai | 45.3 | medium | gpqa_main_cot_5shot_instruct |
| 2 | Mistral-Small-24B-Instruct-2501-bnb-4bit | mistralai/Mistral-Small-24B-Instruct-2501 | unsloth | 45.3 | medium | gpqa_main_cot_5shot_instruct |
| 3 | Mistral-Small-24B-Instruct-2501-GGUF | mistralai/Mistral-Small-24B-Instruct-2501 | unsloth | 45.3 | medium | gpqa_main_cot_5shot_instruct |
| 4 | Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit | mistralai/Mistral-Small-24B-Instruct-2501 | unsloth | 45.3 | medium | gpqa_main_cot_5shot_instruct |
| 5 | Mistral-Small-24B-Instruct-2501 | mistralai/Mistral-Small-24B-Instruct-2501 | unsloth | 45.3 | medium | gpqa_main_cot_5shot_instruct |
| 6 | Mistral-Small-24B-Base-2501-unsloth-bnb-4bit | mistralai/Mistral-Small-24B-Base-2501 | unsloth | 45.3 | medium | gpqa_main_cot_5shot_instruct |