Compare AI models

Specifications
Parameters
—27B
Context window
1M256k
API pricing
Cheapest input
$0.0507Baidu—
Cheapest output
$0.2028Baidu—
$20.28Baidu · fp8—
Benchmarks
NL2Repo-Bench
65.4%36.2%
Humanity's Last Exam · no tools
36.8%24%
GPQA Diamond
90.9%87.8%
Overview
CompanyDeepSeekQwen
Release dateSep 10 2026Apr 22 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4.1-Flash leads Qwen3.6-27B on 3 of the 3 benchmarks they both report (NL2Repo-Bench, Humanity's Last Exam, GPQA Diamond). Qwen3.6-27B shipped 141 days before DeepSeek-V4.1-Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (DeepSeek-V4.1-Flash) vs 256k (Qwen3.6-27B).

On NL2Repo-Bench, DeepSeek-V4.1-Flash leads at 65.4% vs Qwen3.6-27B at 36.2%. On Humanity's Last Exam · no tools, DeepSeek-V4.1-Flash leads at 36.8% vs Qwen3.6-27B at 24%. On GPQA Diamond, DeepSeek-V4.1-Flash leads at 90.9% vs Qwen3.6-27B at 87.8%.