Phi-2 Benchmark Details

Phi-2 currently shows benchmark results led by MBPP (29 / 70, score 59.10), GSM8K (34 / 70, score 61.10), HumanEval (53 / 101, score 48.30).

Benchmark Results

Phi-2

Benchmark Results

General Knowledge

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

56.70

96 / 124

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

61.10

34 / 70

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

59.10

29 / 70

Standard Mode

48.30

53 / 101

Compare with other models