Grok 2 Benchmark Details

Grok 2 currently shows benchmark results led by HumanEval (14 / 101, score 88.40), MMLU (23 / 124, score 87.50), MATH (15 / 42, score 76.10).

Benchmark Results

Grok 2

Benchmark Results

Knowledge Exams

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

87.50

23 / 124

Standard Mode

75.50

87 / 175

Code Generation & Editing

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

88.40

14 / 101

Mathematics

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

76.10

15 / 42

Standard Mode

0.70

55 / 60

Scientific Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

56

220 / 253

Commonsense

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

22.70

88 / 96

Compare with other models