Compare AI models

Specifications
Parameters
671B27B/35B/122B
Context window
128k256k
Benchmarks
SWE-Bench Verified
49.2%72%
LiveCodeBench
65.9%78.9%
GPQA Diamond
71.5%86.6%
MMLU-Pro
84%86.7%
Overview
CompanyDeepSeekQwen
Release dateJan 20 2025Feb 24 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Medium leads DeepSeek R1 on 4 of the 4 benchmarks they both report (SWE-Bench Verified, LiveCodeBench, GPQA Diamond, MMLU-Pro). DeepSeek R1 shipped 400 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while Qwen3.5 Medium has 27B/35B/122B. Context windows are 128k (DeepSeek R1) vs 256k (Qwen3.5 Medium).

On SWE-Bench Verified, Qwen3.5 Medium leads at 72% vs DeepSeek R1 at 49.2%. On LiveCodeBench, Qwen3.5 Medium leads at 78.9% vs DeepSeek R1 at 65.9%. On GPQA Diamond, Qwen3.5 Medium leads at 86.6% vs DeepSeek R1 at 71.5%. On MMLU-Pro, Qwen3.5 Medium leads at 86.7% vs DeepSeek R1 at 84%.