Compare AI models

Specifications
Parameters
284B>1T
Context window
1M256k
API pricing
Cheapest input
$0.0466Baidu—
Cheapest output
$0.1399Baidu—
$16.32Baidu · fp8—
Benchmarks
SWE-Bench Verified
79%75.3%
Humanity's Last Exam · with tools
51.5%49.8%
Overview
CompanyDeepSeekQwen
Release dateJul 31 2026Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4-Flash-0731 leads Qwen3-Max-Thinking on 2 of the 2 benchmarks they both report (SWE-Bench Verified, Humanity's Last Exam). Qwen3-Max-Thinking shipped 186 days before DeepSeek-V4-Flash-0731, so benchmark comparisons should account for the intervening progress.

DeepSeek-V4-Flash-0731 has 284B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 1M (DeepSeek-V4-Flash-0731) vs 256k (Qwen3-Max-Thinking). DeepSeek-V4-Flash-0731 is open weight, while Qwen3-Max-Thinking is closed.

On SWE-Bench Verified, DeepSeek-V4-Flash-0731 leads at 79% vs Qwen3-Max-Thinking at 75.3%. On Humanity's Last Exam · with tools, DeepSeek-V4-Flash-0731 leads at 51.5% vs Qwen3-Max-Thinking at 49.8%.