Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Both models are tied with an overall score of 65.
Gemini 2.5 Pro
81.5
Qwen3.5 397B
80.8
Gemini 2.5 Pro
75
Qwen3.5 397B
75
Gemini 2.5 Pro
83
Qwen3.5 397B
82
Gemini 2.5 Pro
80
Qwen3.5 397B
79
Gemini 2.5 Pro and Qwen3.5 397B are tied with identical overall scores of 65.
Gemini 2.5 Pro leads in knowledge tasks with an average score of 81.5 vs 80.8.
Gemini 2.5 Pro and Qwen3.5 397B are tied for coding with average scores of 75.
Gemini 2.5 Pro leads in math with an average score of 83 vs 82.
Gemini 2.5 Pro leads in reasoning with an average score of 80 vs 79.