Llama3.1-8B-Instruct Benchmark Details

Llama3.1-8B-Instruct currently shows benchmark results led by MBPP (18 / 70, score 69.40), GSM8K (21 / 70, score 82.40), HumanEval (37 / 101, score 66.50).

Benchmark Results

Llama3.1-8B-Instruct

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

68.10

78 / 124

MMLU Pro

Standard Mode

127 / 133

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

GSM8K

Standard Mode

82.40

21 / 70

MATH

Standard Mode

47.60

35 / 42

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

MBPP

Standard Mode

69.40

18 / 70

HumanEval

Standard Mode

66.50

37 / 101

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

26.30

263 / 270

Writing and Creative Capabilities

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

710.70

94 / 99

Compare with other models