GPT-3.5 Benchmark Details

GPT-3.5 currently shows benchmark results led by GSM8K (37 / 70, score 57.10), C-Eval (27 / 48, score 54.40), MMLU (73 / 124, score 70).

Benchmark Results

GPT-3.5

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

70

73 / 124

Standard Mode

54.40

27 / 48

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

57.10

37 / 70

Coding and Software Engineer

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

52.20

63 / 96

Standard Mode

48.10

87 / 140

Compare with other models