DeepSeek-V4-Pro-0813vsQwen3-Coder-Next

DeepSeek-V4-Pro-0813
Qwen3-Coder-Next
Specifications
Parameters
80B
Context window
256k
API pricing
Input price
$0.66$0.30
Output price
$1.98$1.50
Cached input price
$0.022
Cheapest input
$0.5782Baidu$0.12Parasail
Cheapest output
$1.7345Baidu$0.80Parasail
Benchmarks
SWE-Bench Verified
80.6%70.6%
Benchmarks
BullshitBench v2
35%
SWE-Bench Pro
44.3%
SWE-Bench Multilingual
62.8%
Terminal-Bench 2.1
87.9%
Terminal-Bench 2.0
36.2%
Toolathlon-Verified
74.1%
BrowseComp
83.4%
CyberGym
83.3%
Humanity's Last Exam · no tools
42.7%
Humanity's Last Exam · with tools
60%
AutomationBench
31.8%
Overview
CompanyDeepSeekQwen
Release dateAug 13 2026Feb 3 2026
AccessProprietaryOpen Weight

Other comparisons

DeepSeek-V4-Pro-0813vsClaude Fable 5.1Qwen3-Coder-NextvsClaude Fable 5.1DeepSeek-V4-Pro-0813vsGPT-6 AstraQwen3-Coder-NextvsGPT-6 AstraDeepSeek-V4-Pro-0813vsGemini 3.8 FlashQwen3-Coder-NextvsGemini 3.8 FlashDeepSeek-V4-Pro-0813vsMuse Spark 1.3Qwen3-Coder-NextvsMuse Spark 1.3DeepSeek-V4-Pro-0813vsGrok 4.6Qwen3-Coder-NextvsGrok 4.6DeepSeek-V4-Pro-0813vsMistral Medium 3.5Qwen3-Coder-NextvsMistral Medium 3.5

Frequently asked questions

DeepSeek-V4-Pro-0813 leads Qwen3-Coder-Next on 1 of the 1 benchmark they both report (SWE-Bench Verified). Qwen3-Coder-Next is cheaper on both input and output: $0.30 vs $0.66 per million input tokens, and $1.50 vs $1.98 per million output tokens. Figures are base-tier rates. Qwen3-Coder-Next shipped 191 days before DeepSeek-V4-Pro-0813, so benchmark comparisons should account for the intervening progress.

DeepSeek-V4-Pro-0813 is proprietary, while Qwen3-Coder-Next is open weight.

On SWE-Bench Verified, DeepSeek-V4-Pro-0813 leads at 80.6% vs Qwen3-Coder-Next at 70.6%.