DeepSeek-V4-Pro-0813vsGPT-5.6 Luna
DeepSeek-V4-Pro-0813 | GPT-5.6 Luna | |
|---|---|---|
| Benchmarks | ||
Nonsense detection BullshitBench v2Given 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. | — | 40% |
Prompt injection robustness Gray Swan IPI · k = 1Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better. | — | 8.3% |
Prompt injection robustness Gray Swan IPI · k = 10Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 10 tries and counts an attack as successful if any of them works. Lower is better. | — | 38.6% |
Prompt injection robustness Gray Swan IPI · k = 15Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | — | 43.9% |
Agentic coding CursorBench v3.2Cursor's own test of harder, real-world coding tasks inside a code editor, on the refreshed v3.2 task set. Scores aren't comparable with v3.1. Higher is better. | — | 61.1% |
Agentic computer work Frontier-Bench v0.1A hard, ever-evolving set of real computer tasks — coding, system administration, data work, and more — that an AI agent has to complete on its own. Run by the Harbor / Laude Institute team as the successor to Terminal-Bench (v0.1 is the first release of the task set). The score is the share of tasks solved. Higher is better. | — | 14.3% |
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%Best | 82.5% |
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% | — |
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% | — |
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% | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | — | 1523 |
| Overview | ||
| Company | DeepSeek | OpenAI |
| Release date | Aug 13 2026 | Jun 26 2026 |
| Access | Proprietary | Proprietary |
Which is better: DeepSeek-V4-Pro-0813 or GPT-5.6 Luna?
DeepSeek-V4-Pro-0813 leads GPT-5.6 Luna on 1 of the 1 benchmark they both report (Terminal-Bench 2.1). GPT-5.6 Luna shipped 48 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 Terminal-Bench 2.1, DeepSeek-V4-Pro-0813 leads at 87.9% vs GPT-5.6 Luna at 82.5%.
Frequently asked questions
DeepSeek-V4-Pro-0813 was released by DeepSeek on Aug 13 2026.
GPT-5.6 Luna was released by OpenAI on Jun 26 2026.
DeepSeek-V4-Pro-0813 leads on Terminal-Bench 2.1 — DeepSeek-V4-Pro-0813 87.9% vs GPT-5.6 Luna 82.5%.
Other comparisons
DeepSeek-V4-Pro-0813vsClaude Opus 5GPT-5.6 LunavsClaude Opus 5DeepSeek-V4-Pro-0813vsGemini 3.6 FlashGPT-5.6 LunavsGemini 3.6 FlashDeepSeek-V4-Pro-0813vsMuse GlimmerGPT-5.6 LunavsMuse GlimmerDeepSeek-V4-Pro-0813vsGrok 4.6GPT-5.6 LunavsGrok 4.6DeepSeek-V4-Pro-0813vsMistral Medium 3.5GPT-5.6 LunavsMistral Medium 3.5DeepSeek-V4-Pro-0813vsKimi K3GPT-5.6 LunavsKimi K3