Grok 3 Benchmark Details

Grok 3 currently shows benchmark results led by MMMU (22 / 74, score 78), AIME 2024 (22 / 61, score 84.20), LiveCodeBench (92 / 251, score 70.60).

Benchmark Results

Grok 3

Benchmark Results

Knowledge Exams

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

4.10

525 / 568

Scientific Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

80.40

232 / 461

Honesty & Factuality

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

43.40

18 / 46

Mathematics

4 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

84.20

22 / 61

Standard Mode

77.10

104 / 215

Standard Mode

3.80

45 / 60

FrontierMath - Tier 4

Standard Mode

0

72 / 80

Algorithmic Coding

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

70.60

92 / 251

Writing

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

1183.50

80 / 106

Visual Understanding

1 evaluations

Benchmark / mode

Score

Rank/total

unknown

78

22 / 74

Commonsense

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

36.10

71 / 93

Agentic Development

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

53.30

30 / 59

Terminal Bench Hard

Standard ModeTools

11.40

181 / 244

Service Workflows

1 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench - Telecom

Standard ModeTools

48.80

175 / 264

Instruction Following

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

46.90

171 / 282

Capability Indices

1 evaluations

Benchmark / mode

Score

Rank/total

unknown

138.34

102 / 167

Compare with other models