Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Qwen2.5-1M wins overall with a score of 66 vs 64 (2 point difference).Qwen2.5-1M wins 4 out of 4 categories.
DeepSeekMath V2
77.8
Qwen2.5-1M
81.8
DeepSeekMath V2
72
Qwen2.5-1M
76
DeepSeekMath V2
79
Qwen2.5-1M
84
DeepSeekMath V2
76
Qwen2.5-1M
80
Qwen2.5-1M scores higher overall with 66 vs 64, a difference of 2 points across all benchmarks.
Qwen2.5-1M leads in knowledge tasks with an average score of 81.8 vs 77.8.
Qwen2.5-1M leads in coding with an average score of 76 vs 72.
Qwen2.5-1M leads in math with an average score of 84 vs 79.
Qwen2.5-1M leads in reasoning with an average score of 80 vs 76.