Grok-3 - Reasoning Beta Benchmark Details

Grok-3 - Reasoning Beta currently shows benchmark results led by AIME 2024 (6 / 62, score 93.30), LiveCodeBench (35 / 126, score 79.40), GPQA Diamond (89 / 224, score 84.60).

Benchmark Results

Grok-3 - Reasoning Beta

Benchmark Results

Other

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

84.60

89 / 224

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

93.30

6 / 62

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

79.40

35 / 126

Compare with other models