DeepSeek-V4-Pro-0813vsGPT-5.4-Pro
DeepSeek-V4-Pro-0813 | GPT-5.4-Pro | |
|---|---|---|
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $0.66 | $30.00 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $1.98 | $180.00 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.022 | — |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.5782Baidu | $30.00Azure |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $1.7345Baidu | $180.00Azure |
| Benchmarks | ||
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4% | 89.3% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity'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% | 58.7% |
| BenchmarksPublished by one model only | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 35% | — |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 80.6% | — |
Terminal-Bench 2.1Agentic terminal coding — Can 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% | — |
Toolathlon-VerifiedPersonal tool use — Tests 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% | — |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 83.3% | — |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity'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% | — |
ARC-AGI-2Abstract reasoning — Puzzle-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% |
FrontierMath · Tier 1–3Advanced math — Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | — | 50% |
FrontierMath · Tier 4Advanced math — Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | — | 38% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 94.4% |
AutomationBenchBusiness workflows — Tests 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% | — |
GDPval (win/tie rate)Knowledge work — 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 |
Other comparisons
DeepSeek-V4-Pro-0813vsClaude Fable 5.1GPT-5.4-ProvsClaude Fable 5.1DeepSeek-V4-Pro-0813vsGemini 3.8 FlashGPT-5.4-ProvsGemini 3.8 FlashDeepSeek-V4-Pro-0813vsMuse Spark 1.3GPT-5.4-ProvsMuse Spark 1.3DeepSeek-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
Frequently asked questions
DeepSeek-V4-Pro-0813 and GPT-5.4-Pro are evenly matched across the 2 benchmarks they both report (BrowseComp, Humanity's Last Exam). DeepSeek-V4-Pro-0813 is cheaper on both input and output: $0.66 vs $30.00 per million input tokens, and $1.98 vs $180.00 per million output tokens. Figures are base-tier rates. 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 BrowseComp, GPT-5.4-Pro leads at 89.3% vs DeepSeek-V4-Pro-0813 at 83.4%. On Humanity's Last Exam · with tools, DeepSeek-V4-Pro-0813 leads at 60% vs GPT-5.4-Pro at 58.7%.