Grok-1.5 Benchmark Details

Grok-1.5 currently shows benchmark results led by HumanEval (27 / 101, score 74.10), MMLU (51 / 124, score 81.30), MATH (32 / 42, score 50.60).

Benchmark Results

Grok-1.5

Benchmark Results

General Knowledge

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

81.30

51 / 124

Standard Mode

51

122 / 133

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

74.10

27 / 101

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

50.60

32 / 42

Other

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

35.90

213 / 224

Compare with other models