Grok-1.5 Benchmark Details

Grok-1.5 currently shows benchmark results led by HumanEval (25 / 39, score 74.10), MMLU (47 / 65, score 81.30), MATH (32 / 42, score 50.60).

Benchmark Results

Grok-1.5

Benchmark Results

General Knowledge

3 evaluations

Benchmark / mode

Score

Rank/total

81.30

47 / 65

51

116 / 126

35.90

169 / 179

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

74.10

25 / 39

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

50.60

32 / 42

Compare with other models