Mistral AI's flagship dense 123B model, released under the non-commercial Mistral Research License. The MMLU figure is reported for the pretrained checkpoint.

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

benchmark	published	measured
MMLU-Pro	—	68.3
GPQA	—	47.2
AIME 2025	—	0
HLE	—	3.2

Lineage

No recorded lineage — root or standalone model.

view in full graph →

Metadata

org	Mistral AI
released	2024-07-24
params	123B
license	proprietary
hf id	mistralai/Mistral-Large-Instruct-2407