AI Benchmark Model

Mistral Small 3.1

Benchmark scores, pricing, speed, and model comparisons for Mistral Small 3.1.

Key scores

Intelligence7.1Index score
Coding26.3Index score
Math3.7Index score
Blended Cost$0.13Per 1M tokens

Review benchmark scores, pricing, performance data, and generated comparisons for this AI model.

Benchmark results

12 tracked benchmark rows for Mistral Small 3.1.

MATH 500 Math
70.7%
MMLU Pro Knowledge
65.9%
GPQA Reasoning
45.4%
IFBench Other
29.9%
SciCode Other
27.8%
TAU2 Other
25.1%
LCR Other
22.3%
LiveCodeBench Code
21.2%
AIME Math
9.3%
TerminalBench Hard Other
7.6%
HLE Other
4.3%
AIME 2025 Math
3.7%