DeepSeek-V4-Pro-0813vsGemini 3.6 Flash
DeepSeek-V4-Pro-0813 | Gemini 3.6 Flash | |
|---|---|---|
| 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. | — | 39% |
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. | — | 7.3% |
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. | — | 32.2% |
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. | — | 37.3% |
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. | — | 53.5% |
Agentic coding DeepSWE 1.1Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | — | 49% |
ML engineering MLE-BenchCan the AI do the work of a machine-learning engineer? It competes in real Kaggle competitions — building, training, and tuning models end to end — and the score reflects how well it places. Higher is better. | — | 63.9% |
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% | — |
Browser agent BU BenchCan the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | — | 68% |
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% | — |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | — | 83% |
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-AA v2economically valuable knowledge work (v2, re-based Elo) | — | 1421 |
Community preference Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | — | 1482 |
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. | — | 1533 |
| Overview | ||
| Company | DeepSeek | |
| Release date | Aug 13 2026 | Jul 21 2026 |
| Access | Proprietary | Proprietary |
Which is better: DeepSeek-V4-Pro-0813 or Gemini 3.6 Flash?
DeepSeek-V4-Pro-0813 and Gemini 3.6 Flash don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Gemini 3.6 Flash shipped 23 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.
Direct benchmark comparisons are unavailable — DeepSeek-V4-Pro-0813 and Gemini 3.6 Flash don't publish scores on any of the same benchmarks.
Frequently asked questions
DeepSeek-V4-Pro-0813 was released by DeepSeek on Aug 13 2026.
Gemini 3.6 Flash was released by Google on Jul 21 2026.
Other comparisons
DeepSeek-V4-Pro-0813vsClaude Opus 5Gemini 3.6 FlashvsClaude Opus 5DeepSeek-V4-Pro-0813vsGPT-5.6-CyberGemini 3.6 FlashvsGPT-5.6-CyberDeepSeek-V4-Pro-0813vsMuse GlimmerGemini 3.6 FlashvsMuse GlimmerDeepSeek-V4-Pro-0813vsGrok 4.6Gemini 3.6 FlashvsGrok 4.6DeepSeek-V4-Pro-0813vsMistral Medium 3.5Gemini 3.6 FlashvsMistral Medium 3.5DeepSeek-V4-Pro-0813vsKimi K3Gemini 3.6 FlashvsKimi K3