Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeek-R1 wins overall with a score of 35 vs 31 (4 point difference).DeepSeek-R1 wins 4 out of 4 categories.
DeepSeek-R1
41.8
Qwen3 235B 2507 (Reasoning)
37.8
DeepSeek-R1
36
Qwen3 235B 2507 (Reasoning)
32
DeepSeek-R1
43
Qwen3 235B 2507 (Reasoning)
39
DeepSeek-R1
41
Qwen3 235B 2507 (Reasoning)
37
DeepSeek-R1 scores higher overall with 35 vs 31, a difference of 4 points across all benchmarks.
DeepSeek-R1 leads in knowledge tasks with an average score of 41.8 vs 37.8.
DeepSeek-R1 leads in coding with an average score of 36 vs 32.
DeepSeek-R1 leads in math with an average score of 43 vs 39.
DeepSeek-R1 leads in reasoning with an average score of 41 vs 37.