Compare AI models

Specifications
Parameters
671B27B
Context window
128k256k
API pricing
Cheapest input
$0.25DeepInfra—
Cheapest output
$0.95DeepInfra—
$97.50DeepInfra · fp4—
Benchmarks
SWE-Bench Verified
66%77.2%
SWE-Bench Multilingual
54.5%71.3%
LiveCodeBench
74.8%83.9%
GPQA Diamond
80.1%87.8%
MMLU-Pro
84.8%86.2%
Overview
CompanyDeepSeekQwen
Release dateAug 21 2025Apr 22 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.6-27B leads DeepSeek V3.1 on 5 of the 5 benchmarks they both report. DeepSeek V3.1 shipped 244 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

DeepSeek V3.1 has 671B parameters, while Qwen3.6-27B has 27B. Context windows are 128k (DeepSeek V3.1) vs 256k (Qwen3.6-27B).

On SWE-Bench Verified, Qwen3.6-27B leads at 77.2% vs DeepSeek V3.1 at 66%. On SWE-Bench Multilingual, Qwen3.6-27B leads at 71.3% vs DeepSeek V3.1 at 54.5%. On LiveCodeBench, Qwen3.6-27B leads at 83.9% vs DeepSeek V3.1 at 74.8%. On GPQA Diamond, Qwen3.6-27B leads at 87.8% vs DeepSeek V3.1 at 80.1%. On MMLU-Pro, Qwen3.6-27B leads at 86.2% vs DeepSeek V3.1 at 84.8%.