Compare AI models

Specifications
Parameters
671B>1T
Context window
128k256k
API pricing
Cheapest input
$0.25DeepInfra—
Cheapest output
$0.95DeepInfra—
$97.50DeepInfra · fp4—
Benchmarks
SWE-Bench Verified
66%75.3%
LiveCodeBench
74.8%85.9%
Humanity's Last Exam · text only, no tools
15.9%30.2%
GPQA Diamond
80.1%87.4%
MMLU-Pro
84.8%85.7%
Overview
CompanyDeepSeekQwen
Release dateAug 21 2025Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads DeepSeek V3.1 on 5 of the 5 benchmarks they both report. DeepSeek V3.1 shipped 158 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.

DeepSeek V3.1 has 671B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 128k (DeepSeek V3.1) vs 256k (Qwen3-Max-Thinking). DeepSeek V3.1 is open weight, while Qwen3-Max-Thinking is closed.

On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs DeepSeek V3.1 at 66%. On LiveCodeBench, Qwen3-Max-Thinking leads at 85.9% vs DeepSeek V3.1 at 74.8%. On Humanity's Last Exam · text only, no tools, Qwen3-Max-Thinking leads at 30.2% vs DeepSeek V3.1 at 15.9%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs DeepSeek V3.1 at 80.1%. On MMLU-Pro, Qwen3-Max-Thinking leads at 85.7% vs DeepSeek V3.1 at 84.8%.