Compare AI models

Specifications
Parameters
—27B
Context window
1M256k
API pricing
Cheapest input
$0.03Particle AI—
Cheapest output
$0.2352DeepInfra—
$25.00Pearl Research · fp8—
Benchmarks
NL2Repo-Bench
68.2%36.2%
Humanity's Last Exam · no tools
42.6%24%
Overview
CompanyDeepSeekQwen
Release dateOct 17 2026Apr 22 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4.1-Flash-1017 leads Qwen3.6-27B on 2 of the 2 benchmarks they both report (NL2Repo-Bench, Humanity's Last Exam). Qwen3.6-27B shipped 178 days before DeepSeek-V4.1-Flash-1017, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (DeepSeek-V4.1-Flash-1017) vs 256k (Qwen3.6-27B).

On NL2Repo-Bench, DeepSeek-V4.1-Flash-1017 leads at 68.2% vs Qwen3.6-27B at 36.2%. On Humanity's Last Exam · no tools, DeepSeek-V4.1-Flash-1017 leads at 42.6% vs Qwen3.6-27B at 24%.