LLaMA2 34B Benchmark Details

LLaMA2 34B currently shows benchmark results led by AGIEval (11 / 28, score 43.40), GSM8K (48 / 70, score 42.20), MMLU (89 / 124, score 62.60).

Benchmark Results

LLaMA2 34B

Benchmark Results

General Knowledge

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

62.60

89 / 124

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

42.20

48 / 70

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

33.80

60 / 70

Standard Mode

22.60

91 / 101

Other

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

43.40

11 / 28

Other

4 evaluations

Benchmark / mode

Score

Rank/total

HumanEval pass@100

Standard Mode

79.50

17 / 21

Standard Mode

77.60

10 / 13

Standard Mode

56.90

11 / 13

HumanEval pass@10

Standard Mode

47

14 / 18

Compare with other models