Compare AI models

Specifications
Parameters
671B>1T
Context window
128k256k
Benchmarks
SWE-Bench Verified
49.2%75.3%
LiveCodeBench
65.9%85.9%
GPQA Diamond
71.5%87.4%
MMLU-Pro
84%85.7%
Overview
CompanyDeepSeekQwen
Release dateJan 20 2025Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads DeepSeek R1 on 4 of the 4 benchmarks they both report (SWE-Bench Verified, LiveCodeBench, GPQA Diamond, MMLU-Pro). DeepSeek R1 shipped 371 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 128k (DeepSeek R1) vs 256k (Qwen3-Max-Thinking). DeepSeek R1 is open weight, while Qwen3-Max-Thinking is closed.

On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs DeepSeek R1 at 49.2%. On LiveCodeBench, Qwen3-Max-Thinking leads at 85.9% vs DeepSeek R1 at 65.9%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs DeepSeek R1 at 71.5%. On MMLU-Pro, Qwen3-Max-Thinking leads at 85.7% vs DeepSeek R1 at 84%.