DeepSeek-V4-Pro-0813vsGPT-5.4-Pro
DeepSeek-V4-Pro-0813 | GPT-5.4-Pro | |
|---|---|---|
| Benchmarks | ||
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 87.9% | — |
Personal tool use Toolathlon-VerifiedTests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | 74.1% | — |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | — | 89.3% |
Cybersecurity CyberGymTests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 83.3% | — |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 42.7% | — |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | 60%Best | 58.7% |
Abstract reasoning ARC-AGI-2Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 83.3% |
Advanced math FrontierMath · Tier 1–3Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | — | 50% |
Advanced math FrontierMath · Tier 4Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | — | 38% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 94.4% |
Business workflows AutomationBenchTests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | 31.8% | — |
Knowledge work GDPval (win/tie rate)How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | — | 82% |
| Overview | ||
| Company | DeepSeek | OpenAI |
| Release date | Aug 13 2026 | Mar 5 2026 |
| Access | Proprietary | Proprietary |
Which is better: DeepSeek-V4-Pro-0813 or GPT-5.4-Pro?
DeepSeek-V4-Pro-0813 leads GPT-5.4-Pro on 1 of the 1 benchmark they both report (Humanity's Last Exam). GPT-5.4-Pro shipped 161 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 Humanity's Last Exam · with tools, DeepSeek-V4-Pro-0813 leads at 60% vs GPT-5.4-Pro at 58.7%.
Frequently asked questions
DeepSeek-V4-Pro-0813 was released by DeepSeek on Aug 13 2026.
GPT-5.4-Pro was released by OpenAI on Mar 5 2026.
DeepSeek-V4-Pro-0813 leads on Humanity's Last Exam · with tools — DeepSeek-V4-Pro-0813 60% vs GPT-5.4-Pro 58.7%.
Other comparisons
DeepSeek-V4-Pro-0813vsClaude Opus 5GPT-5.4-ProvsClaude Opus 5DeepSeek-V4-Pro-0813vsGemini 3.6 FlashGPT-5.4-ProvsGemini 3.6 FlashDeepSeek-V4-Pro-0813vsMuse GlimmerGPT-5.4-ProvsMuse GlimmerDeepSeek-V4-Pro-0813vsGrok 4.6GPT-5.4-ProvsGrok 4.6DeepSeek-V4-Pro-0813vsMistral Medium 3.5GPT-5.4-ProvsMistral Medium 3.5DeepSeek-V4-Pro-0813vsKimi K3GPT-5.4-ProvsKimi K3