Llama3.1-70B-Instruct Benchmark Details

Llama3.1-70B-Instruct currently shows benchmark results led by MBPP (9 / 96, score 86), MMLU (35 / 124, score 86), HumanEval (41 / 140, score 80.50).

Benchmark Results

Llama3.1-70B-Instruct

Benchmark Results

General Knowledge

3 evaluations

Benchmark / mode

Score

Rank/total

MMLU

Standard Mode

35 / 124

MMLU-Pro

Standard Mode

66.40

111 / 176

MMLU-Pro

unknown

62.84

119 / 176

Coding and Software Engineer

4 evaluations

Benchmark / mode

Score

Rank/total

MBPP

Standard Mode

9 / 96

HumanEval

Standard Mode

80.50

41 / 140

LiveCodeBench

Standard Mode

33.30

207 / 251

WeirdML v2

Standard ModeTools

8.97

52 / 52

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

MATH

Standard Mode

67.80

26 / 42

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

416 / 463

Writing and Creative Capabilities

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

781.90

96 / 106

Agent Level Benchmark

1 evaluations

Benchmark / mode

Score

Rank/total

BALROG

Standard ModeTools

27.90

11 / 12

Claw-style Agent Evaluation

1 evaluations

Benchmark / mode

Score

Rank/total

PinchBench v2

unknown

10.70

44 / 45

Compare with other models