Compare AI models

Specifications
Parameters
236B>1T
Context window
128k256k
Benchmarks
SWE-Bench Verified
16.8%75.3%
LiveCodeBench
41.8%85.9%
Overview
CompanyDeepSeekQwen
Release dateSep 5 2024Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads DeepSeek V2.5 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, LiveCodeBench). DeepSeek V2.5 shipped 508 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.

DeepSeek V2.5 has 236B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 128k (DeepSeek V2.5) vs 256k (Qwen3-Max-Thinking). DeepSeek V2.5 is open weight, while Qwen3-Max-Thinking is closed.

On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs DeepSeek V2.5 at 16.8%. On LiveCodeBench, Qwen3-Max-Thinking leads at 85.9% vs DeepSeek V2.5 at 41.8%.