Magistral Small 1.0

Magistral Small 1.0.

Mistral AI Released 10 Jun 2025

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Mistral AI Jun 2025

Open weights

133.1 #153 of 271

Epoch Capabilities Index

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
Humanity's Last Exam	6.40%		#145 of 147	Model card

Benchmark	Score	Rank	Source
MATH-500	95.9%	#35 of 67	Model card
GPQA Diamond	56.1%	#135 of 219	Epoch AI
OTIS Mock AIME 2024-2025	30%	#137 of 202	Epoch AI
AIME 2024	70.7%	#60 of 87	Model card
AIME 2025	62.8%	#124 of 143	Model card
ARC-AGI	5.00%	#87 of 92	Official leaderboard
ARC-AGI-2	0%	#95 of 95	Official leaderboard

Benchmark	Score		Rank	Source
LiveCodeBench v5	55.8%		#33 of 44	Model card
LiveCodeBench v6	47.4%		#72 of 76	Model card

Benchmark	Score		Rank	Source
Galileo Agent Leaderboard v2	16%		#21 of 21	Official leaderboard

Benchmark	Score	Rank	Source
MMMU	66%	#72 of 97	Model card
MathVista	66.8%	#50 of 64	Model card
MMMU-Pro	51.8%	#64 of 72	Model card

Mistral AI's models in color, against every other model on the Epoch Capabilities Index, by release date.

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

Every result in the longer documents the lab published with it. 6 of them aren't in the launch post.

Magistral 12 Jun 2025