Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeek-R1 wins overall with a score of 35 vs 34 (1 point difference).DeepSeek-R1 wins 4 out of 4 categories.
DeepSeek-R1
41.8
Qwen2.5-VL-32B
40.8
DeepSeek-R1
36
Qwen2.5-VL-32B
35
DeepSeek-R1
43
Qwen2.5-VL-32B
42
DeepSeek-R1
41
Qwen2.5-VL-32B
40
DeepSeek-R1 scores higher overall with 35 vs 34, a difference of 1 points across all benchmarks.
DeepSeek-R1 leads in knowledge tasks with an average score of 41.8 vs 40.8.
DeepSeek-R1 leads in coding with an average score of 36 vs 35.
DeepSeek-R1 leads in math with an average score of 43 vs 42.
DeepSeek-R1 leads in reasoning with an average score of 41 vs 40.