LLaMA 65B Benchmark Details

LLaMA 65B currently shows benchmark results led by AGIEval (10 / 28, score 47.60), GSM8K (46 / 70, score 50.90), MMLU (87 / 124, score 63.40).

Benchmark Results

LLaMA 65B

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

63.40

87 / 124

Standard Mode

38.80

40 / 48

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

50.90

46 / 70

Other

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

47.60

10 / 28

Compare with other models