Mistral-7B-Instruct-v0.3 Benchmark Details

Mistral-7B-Instruct-v0.3 currently shows benchmark results led by MBPP (41 / 70, score 51.10), MMLU (85 / 124, score 64.20), GSM8K (51 / 70, score 36.20).

Benchmark Results

Mistral-7B-Instruct-v0.3

Benchmark Results

General Knowledge

3 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

64.20

85 / 124

BBH

Standard Mode

56.10

18 / 21

MMLU Pro

Standard Mode

30.90

131 / 133

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

GSM8K

Standard Mode

36.20

51 / 70

MATH

Standard Mode

10.20

41 / 42

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

MBPP

Standard Mode

51.10

41 / 70

HumanEval

Standard Mode

29.30

82 / 101

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

ARC

Standard Mode

3 / 4

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

24.70

220 / 224

Compare with other models