Compare AI models

Specifications
Parameters
671B>1T
Context window
128k256k
API pricing
Cheapest input
$0.259SiliconFlow—
Cheapest output
$0.38DeepInfra—
$71.00DeepInfra · fp4—
Benchmarks
SWE-Bench Verified
73.1%75.3%
LiveCodeBench
83.3%85.9%
Humanity's Last Exam · text only, no tools
25.1%30.2%
GPQA Diamond
82.4%87.4%
MMLU-Pro
85%85.7%
Overview
CompanyDeepSeekQwen
Release dateDec 1 2025Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads DeepSeek-V3.2 on 5 of the 5 benchmarks they both report. DeepSeek-V3.2 shipped 56 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.

DeepSeek-V3.2 has 671B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 128k (DeepSeek-V3.2) vs 256k (Qwen3-Max-Thinking). DeepSeek-V3.2 is open weight, while Qwen3-Max-Thinking is closed.

On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs DeepSeek-V3.2 at 73.1%. On LiveCodeBench, Qwen3-Max-Thinking leads at 85.9% vs DeepSeek-V3.2 at 83.3%. On Humanity's Last Exam · text only, no tools, Qwen3-Max-Thinking leads at 30.2% vs DeepSeek-V3.2 at 25.1%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs DeepSeek-V3.2 at 82.4%. On MMLU-Pro, Qwen3-Max-Thinking leads at 85.7% vs DeepSeek-V3.2 at 85%.