Mistral-Small-3.2 Benchmark Details

Mistral-Small-3.2 currently shows benchmark results led by MATH (20 / 42, score 69.42), GPQA (10 / 15, score 44.22), MMLU Pro (97 / 132, score 69.06).

Benchmark Results

Mistral-Small-3.2

Benchmark Results

General Knowledge

4 evaluations

Benchmark / mode

Score

Rank/total

80.50

49 / 66

69.06

97 / 132

46.13

165 / 187

44.22

10 / 15

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

69.42

20 / 42

Common Sense

1 evaluations

Benchmark / mode

Score

Rank/total

12.10

39 / 47

Compare with other models