LLaMA2 7B Benchmark Details

LLaMA2 7B currently shows benchmark results led by AGIEval (21 / 28, score 29.30), GSM8K (63 / 70, score 14.60), MMLU (112 / 124, score 45.30).

Benchmark Results

LLaMA2 7B

Benchmark Results

General Knowledge

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

45.30

112 / 124

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

14.60

63 / 70

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

20.80

67 / 70

Standard Mode

12.20

98 / 101

Other

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

29.30

21 / 28

Other

4 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

65.50

13 / 13

HumanEval pass@100

Standard Mode

44.40

21 / 21

Standard Mode

41.80

13 / 13

HumanEval pass@10

Standard Mode

25.20

18 / 18

Compare with other models