Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Grok 4.1 wins overall with a score of 84 vs 50 (34 point difference).Grok 4.1 wins 4 out of 4 categories.
GPT-4 Turbo
58.5
Grok 4.1
96
GPT-4 Turbo
52
Grok 4.1
91
GPT-4 Turbo
59
Grok 4.1
97.1
GPT-4 Turbo
57
Grok 4.1
94
Grok 4.1 scores higher overall with 84 vs 50, a difference of 34 points across all benchmarks.
Grok 4.1 leads in knowledge tasks with an average score of 96 vs 58.5.
Grok 4.1 leads in coding with an average score of 91 vs 52.
Grok 4.1 leads in math with an average score of 97.1 vs 59.
Grok 4.1 leads in reasoning with an average score of 94 vs 57.