Claude 3.5 Sonnet Benchmark Details

Claude 3.5 Sonnet currently shows benchmark results led by HumanEval (5 / 39, score 92), MMLU (18 / 66, score 88.30), MATH (18 / 42, score 71.10).

Benchmark Results

Claude 3.5 Sonnet

Benchmark Results

General Knowledge

3 evaluations

Benchmark / mode

Score

Rank/total

88.30

18 / 66

77.64

77 / 132

59.40

147 / 187

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

92

5 / 39

Math and Reasoning

3 evaluations

Benchmark / mode

Score

Rank/total

71.10

18 / 42

1

52 / 60

FrontierMath - Tier 4

Standard Mode

0

72 / 80

Common Sense Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

27.50

50 / 63

Compare with other models