Mistral

Mistral Small 3.2 (2506)

Released 2025-06-20 · Data snapshot 2026-10-22

Overall score

34.8

Ranked #57

Benchmark coverage

40.9%

9 third-party benchmarks

Context window

—

tokens

Input price

—

per million tokens

Output price

—

per million tokens

Dimension performance

Human preference

53.1

Coding

34.5

Office

30.8

Above averageBelow averageAnchored at 50 (reference models’ average); every 15 points ≈ one standard deviation

Coding2 items

AA Coding Index12.5

AA Agentic Index1

Reasoning1 items

AA Intelligence Index7

Office5 items

AA Economics11.7

AA Engineering10

AA Legal8.4

AA Finance & Accounting6.5

AA Strategy & Ops4.1

Human preference1 items

LMArena Human Blind Vote1356.3174

Multiple reasoning tiers of the same benchmark take the best value; raw scores have different scales and are not comparable across benchmarks.

2026-10-202026-10-22

View daily data