Mistral-Small-24B-Instruct-2501

Home/Models/mistralai/Mistral-Small-24B-Instruct-2501

mistralai/Mistral-Small-24B-Instruct-2501

kind: original
quant: bf16 (16-bit)
family: mistral
modality: —
root model: mistralai/Mistral-Small-24B-Base-2501
provider: mistralai
license: apache-2.0
language: en, fr, de, es, it, pt, zh, ja, ru, ko
context: —
library: vllm
vRAM (GB): —
size on disk: —
downloads: 85,437
likes: 962
created: —
last modified: 2025-07-28T17:26:22+00:00 (2025)
huggingface: https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501
tags: vllmsafetensorsmistralenfrdeesitptzhjarukobase_model:mistralai/Mistral-Small-24B-Base-2501base_model:finetune:mistralai/Mistral-Small-24B-Base-2501license:apache-2.0eval-resultsregion:us

benchmark	category	score	context	conf	evidence
Chatbot Arena	chat	87.3	arena_hard	medium	`\| arena_hard \| 0.873 \| 0.788 \| 0.840 \| 0.860 \| 0.897 \|`
HumanEval	coding	84.8	_instruct_pass@1	medium	`\| humaneval_instruct_pass@1 \| 0.848 \| 0.732 \| 0.854 \| 0.909 \| 0.890 \|`
IFEval	instruction-following	82.9	ifeval	medium	`\| ifeval \| 0.829 \| 0.8065 \| 0.8835 \| 0.8401 \| 0.8499 \|`
MMLU-Pro	knowledge	66.3	mmlu_pro_5shot_cot_instruct	medium	`\| mmlu_pro_5shot_cot_instruct \| 0.663 \| 0.536 \| 0.666 \| 0.683 \| 0.617 \|`
WildBench	chat	52.27		medium	`\| wildbench \| 52.27 \| 48.21 \| 50.04 \| 52.73 \| 56.13 \|`
GPQA-Main	reasoning	45.3	gpqa_main_cot_5shot_instruct	medium	`\| gpqa_main_cot_5shot_instruct \| 0.453 \| 0.344 \| 0.531 \| 0.404 \| 0.377 \|`
MT-Bench	chat	8.35	mtbench_dev	medium	`\| mtbench_dev \| 8.35 \| 7.86 \| 7.96 \| 8.26 \| 8.33 \|`

none scraped.