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

Mistral-7B-Instruct-v0.3 currently shows benchmark results led by ARC (3 / 4, score 60), GSM8K (22 / 26, score 36.20), BBH (17 / 20, score 56.10).

Benchmark Results

Mistral-7B-Instruct-v0.3

Benchmark Results

General Knowledge

4 evaluations

Benchmark / mode

Score

Rank/total

MMLU

64.20

64 / 65

BBH

56.10

17 / 20

MMLU Pro

30.90

124 / 126

GPQA Diamond

24.70

175 / 179

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

GSM8K

36.20

22 / 26

MATH

10.20

41 / 42

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

MBPP

51.10

26 / 28

HumanEval

29.30

37 / 39

常识推理

1 evaluations

Benchmark / mode

Score

Rank/total

ARC

3 / 4

Compare with other models