Magistral Medium 1.0

Magistral Medium 1.0.

Mistral AI Released 10 Jun 2025 Family Magistral The lab's model card

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Mistral AI Jun 2025

Mid-size

No Epoch Capabilities Index score yet

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Benchmark	Score	Rank	Source
IFEval (Mistral internal version)	87.4%	#1 of 2	Model card
LMArena (Elo)	1,305	#225 of 333	Official leaderboard
Phare	62.3%	#43 of 62	Official leaderboard
Humanity's Last Exam	9.00%	#137 of 147	Model card

Benchmark	Score	Rank	Source
AIME 2024	90%	#18 of 87	Model card
Misguided Attention	51.7%	#17 of 45	Official leaderboard
AIME 2025	83.3%	#79 of 143	Model card
GPQA Diamond	70.8%	#169 of 284	Model card
MATH-500	94.3%	#44 of 67	Model card
ARC-AGI	6.12%	#84 of 92	Official leaderboard
ARC-AGI-2	0%	#94 of 95	Official leaderboard

Benchmark	Score	Rank	Source
LiveCodeBench v5	59.4%	#26 of 44	Model card
Aider Polyglot	47.1%	#22 of 29	Model card
LiveCodeBench v6	50.3%	#69 of 76	Model card

Benchmark	Score	Rank	Source
SnakeBench	26	#67 of 183	Official leaderboard
Galileo Agent Leaderboard v2	32%	#16 of 21	Official leaderboard
Mistral internal function calling benchmark	87.4%	#1 of 1	Model card

Benchmark	Score		Rank	Source
Vals Finance Agent v1	7.46%		#42 of 47	Official leaderboard

Benchmark	Score	Rank	Source
MMMU	70%	#60 of 97	Model card
MathVista	70.1%	#42 of 64	Model card
MMMU-Pro	57.9%	#58 of 72	Model card

The benchmarks the lab chose to headline, with the scores it gave.

Every result in the longer documents the lab published with it. 9 of them aren't in the launch post.

Magistral 12 Jun 2025