Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Grok 4.1 wins overall with a score of 84 vs 64 (20 point difference).Grok 4.1 wins 4 out of 4 categories.
DeepSeekMath V2
77.8
Grok 4.1
96
DeepSeekMath V2
72
Grok 4.1
91
DeepSeekMath V2
79
Grok 4.1
97.1
DeepSeekMath V2
76
Grok 4.1
94
Grok 4.1 scores higher overall with 84 vs 64, a difference of 20 points across all benchmarks.
Grok 4.1 leads in knowledge tasks with an average score of 96 vs 77.8.
Grok 4.1 leads in coding with an average score of 91 vs 72.
Grok 4.1 leads in math with an average score of 97.1 vs 79.
Grok 4.1 leads in reasoning with an average score of 94 vs 76.