Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeek-R1 wins overall with a score of 35 vs 25 (10 point difference).DeepSeek-R1 wins 4 out of 4 categories.
DeepSeek-R1
41.8
DeepSeek V3.1 (Reasoning)
31.8
DeepSeek-R1
36
DeepSeek V3.1 (Reasoning)
26
DeepSeek-R1
43
DeepSeek V3.1 (Reasoning)
33
DeepSeek-R1
41
DeepSeek V3.1 (Reasoning)
31
DeepSeek-R1 scores higher overall with 35 vs 25, a difference of 10 points across all benchmarks.
DeepSeek-R1 leads in knowledge tasks with an average score of 41.8 vs 31.8.
DeepSeek-R1 leads in coding with an average score of 36 vs 26.
DeepSeek-R1 leads in math with an average score of 43 vs 33.
DeepSeek-R1 leads in reasoning with an average score of 41 vs 31.