Mistral Small 3.1 24B Base

Pretrained base model version of Mistral Small 3.1. Features improved text performance, multimodal understanding, multilingual capabilities, and an expanded 128k token context window compared to Mistral Small 3. Designed for fine-tuning.

Benchmark results

Benchmark	Score	Tags	Source
GPQA	37.5%	self-reported llm-stats	link →
MMLU	81.0%	self-reported llm-stats	link →
MMLU-Pro	56.0%	self-reported llm-stats	link →
MMMU	59.3%	self-reported llm-stats	link →
TriviaQA	80.5%	self-reported llm-stats	link →