Mistral-Small-3.1-24B-Instruct-2503 Benchmark Details

Mistral-Small-3.1-24B-Instruct-2503 currently shows benchmark results led by HumanEval (13 / 101, score 88.41), MBPP (15 / 69, score 74.71), MMLU (52 / 124, score 80.62).

Benchmark Results

Mistral-Small-3.1-24B-Instruct-2503

Benchmark Results

Knowledge Exams

2 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

80.62

52 / 124

MMLU-Pro

Standard Mode

66.76

110 / 175

Code Generation & Editing

2 evaluations

Benchmark / mode

Score

Rank/total

HumanEval

Standard Mode

88.41

13 / 101

MBPP

Standard Mode

74.71

15 / 69

Mathematics

1 evaluations

Benchmark / mode

Score

Rank/total

MATH

Standard Mode

69.30

21 / 42

Scientific Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

45.96

235 / 253

GPQA

Standard Mode

44.42

11 / 17

Honesty & Factuality

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

10.43

41 / 46

Writing

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

760.90

102 / 110

Compare with other models