DeepSeek-V4-Pro-0813vsGPT-5.5-Cyber

DeepSeek-V4-Pro-0813
GPT-5.5-Cyber
Benchmarks
Agentic terminal coding
Terminal-Bench 2.1
87.9%
Personal tool use
Toolathlon-Verified
74.1%
Cybersecurity
CyberGym
83.3%
85.6%Best
Multidisciplinary reasoning
Humanity's Last Exam · no tools
42.7%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
60%
Business workflows
AutomationBench
31.8%
Overview
CompanyDeepSeekOpenAI
Release dateAug 13 2026Jun 22 2026
AccessProprietaryProprietary

Which is better: DeepSeek-V4-Pro-0813 or GPT-5.5-Cyber?

GPT-5.5-Cyber leads DeepSeek-V4-Pro-0813 on 1 of the 1 benchmark they both report (CyberGym). GPT-5.5-Cyber shipped 52 days before DeepSeek-V4-Pro-0813, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On CyberGym, GPT-5.5-Cyber leads at 85.6% vs DeepSeek-V4-Pro-0813 at 83.3%.

Frequently asked questions

DeepSeek-V4-Pro-0813 was released by DeepSeek on Aug 13 2026.

GPT-5.5-Cyber was released by OpenAI on Jun 22 2026.

Other comparisons