modelgrep

DeepSeek: DeepSeek V4 Pro vs Qwen: Qwen3 Max Thinking

DDeepSeek: DeepSeek V4 Prodeepseek/deepseek-v4-proVSQQwen: Qwen3 Max Thinkingqwen/qwen3-max-thinking

DeepSeek: DeepSeek V4 Pro wins on more metrics (7 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricDeepSeek: DeepSeek V4 ProQwen: Qwen3 Max Thinking
Intelligence Index39.339.8✓
Coding Index38.4✓30.5
GPQA Diamond72%86%✓
Design Arena Elo1348✓—
Speed (tokens/sec)72✓47
Latency604ms✓1.3s
Input price /M$0.435✓$0.780
Output price /M$0.870✓$3.90
Context window1.0M✓262K
CapabilitiesReasoningToolsJSONReasoningToolsJSON
DeepSeek: DeepSeek V4 Pro details →Qwen: Qwen3 Max Thinking details →