Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Grok 4.1 wins overall with a score of 84 vs 42 (42 point difference).Grok 4.1 wins 4 out of 4 categories.
GPT-OSS 120B
48.8
Grok 4.1
96
GPT-OSS 120B
43
Grok 4.1
91
GPT-OSS 120B
50
Grok 4.1
97.1
GPT-OSS 120B
48
Grok 4.1
94
Grok 4.1 scores higher overall with 84 vs 42, a difference of 42 points across all benchmarks.
Grok 4.1 leads in knowledge tasks with an average score of 96 vs 48.8.
Grok 4.1 leads in coding with an average score of 91 vs 43.
Grok 4.1 leads in math with an average score of 97.1 vs 50.
Grok 4.1 leads in reasoning with an average score of 94 vs 48.