Mistral-Small-3.1-24B-Base-2503

Home/Models/mistralai/Mistral-Small-3.1-24B-Base-2503

mistralai/Mistral-Small-3.1-24B-Base-2503

kind: original
quant: bf16 (16-bit)
family: mistral
modality: —
root model: mistralai/Mistral-Small-3.1-24B-Base-2503
provider: mistralai
license: apache-2.0
language: en, fr, de, es, pt, it, ja, ko, ru, zh, ar, fa
context: —
library: vllm
vRAM (GB): —
size on disk: —
downloads: 1,126
likes: 272
created: —
last modified: 2025-07-28T17:25:54+00:00 (2025)
huggingface: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503
tags: vllmsafetensorsmistral3mistral-commonenfrdeesptitjakoruzharfaidmsneplrosrsvtr

benchmark	category	score	context	conf	evidence
MMLU	knowledge	81.01	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT)	low	`\| Small 3.1 24B Base \| 81.01% \| 56.03% \| 80.50% \| 37.50% \| 59.27% \|`
TriviaQA	knowledge	80.5	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT)	low	`\| Small 3.1 24B Base \| 81.01% \| 56.03% \| 80.50% \| 37.50% \| 59.27% \|`
MMMU	multimodal	59.27	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT)	low	`\| Small 3.1 24B Base \| 81.01% \| 56.03% \| 80.50% \| 37.50% \| 59.27% \|`
MMLU-Pro	knowledge	56.03	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT)	low	`\| Small 3.1 24B Base \| 81.01% \| 56.03% \| 80.50% \| 37.50% \| 59.27% \|`
GPQA	reasoning	37.5	MMLU Pro (5-shot CoT) \| GPQA Main (5-shot CoT)	low	`\| Small 3.1 24B Base \| 81.01% \| 56.03% \| 80.50% \| 37.50% \| 59.27% \|`

none scraped.