DataLearner logo

Grok 4 Code Benchmark Details

Grok 4 Code currently shows benchmark results led by SWE-bench Verified (55 / 114, score 72), SWE-bench (2 / 2, score 72).

Benchmark Results

Grok 4 Code

Benchmark Results

Thinking

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
SWE-bench
Standard Mode
72
2 / 2
SWE-bench Verified
Standard Mode
72
55 / 114