Compare AI models

Specifications
Parameters
—>1T
Context window
1M256k
API pricing
Cheapest input
$0.0507Baidu—
Cheapest output
$0.2028Baidu—
$20.28Baidu · fp8—
Benchmarks
Humanity's Last Exam · text only, no tools
39.1%30.2%
Humanity's Last Exam · with tools
63.9%49.8%
GPQA Diamond
90.9%87.4%
Overview
CompanyDeepSeekQwen
Release dateSep 10 2026Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4.1-Flash leads Qwen3-Max-Thinking on 3 of the 3 benchmarks they both report (Humanity's Last Exam, GPQA Diamond). Qwen3-Max-Thinking shipped 227 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-Max-Thinking). DeepSeek-V4.1-Flash is open weight, while Qwen3-Max-Thinking is closed.

On Humanity's Last Exam · text only, no tools, DeepSeek-V4.1-Flash leads at 39.1% vs Qwen3-Max-Thinking at 30.2%. On Humanity's Last Exam · with tools, DeepSeek-V4.1-Flash leads at 63.9% vs Qwen3-Max-Thinking at 49.8%. On GPQA Diamond, DeepSeek-V4.1-Flash leads at 90.9% vs Qwen3-Max-Thinking at 87.4%.