Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeek-R1 wins overall with a score of 35 vs 24 (11 point difference).DeepSeek-R1 wins 4 out of 4 categories.
DeepSeek-R1
41.8
DeepSeek V3.1
30.8
DeepSeek-R1
36
DeepSeek V3.1
25
DeepSeek-R1
43
DeepSeek V3.1
32
DeepSeek-R1
41
DeepSeek V3.1
30
DeepSeek-R1 scores higher overall with 35 vs 24, a difference of 11 points across all benchmarks.
DeepSeek-R1 leads in knowledge tasks with an average score of 41.8 vs 30.8.
DeepSeek-R1 leads in coding with an average score of 36 vs 25.
DeepSeek-R1 leads in math with an average score of 43 vs 32.
DeepSeek-R1 leads in reasoning with an average score of 41 vs 30.