DataLearner logo

Grok 4 Heavy Benchmark Details

Grok 4 Heavy currently shows benchmark results led by AIME2025 (1 / 106, score 100), GPQA Diamond (28 / 182, score 88.90), HLE (43 / 169, score 44.40).

Benchmark Results

Grok 4 Heavy

Benchmark Results

Thinking
Tool usage
Internet

General Knowledge

2 evaluations
Benchmark / mode
Score
Rank/total
88.90
28 / 182
44.40
43 / 169

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
73.50
45 / 111

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
100
1 / 106
FrontierMath - Tier 4
Standard ModeToolsInternet
2.10
56 / 80