Claude Sonnet 5vsDeepSeek-V4-Flash-0731
Claude Sonnet 5 | DeepSeek-V4-Flash-0731 | |
|---|---|---|
| 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. | 80% | — |
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. | 0.6% | — |
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. | 4.7% | — |
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. | 5.9% | — |
Agentic coding SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 63.2% | — |
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. | 61.5% | — |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 61.2% | — |
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. | 14.6% | — |
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. | 80.4% | 82.7%Best |
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. | — | 70.3% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 84.7% | — |
Cybersecurity CyberGymTests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | — | 76.7% |
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. | 43.2% | — |
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. | 57.4% | — |
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. | 81.2% | — |
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. | — | 25.1% |
Knowledge work GDPval-AAMeasures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better. | 1618 | — |
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. | 1543 | — |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Jun 30 2026 | Jul 31 2026 |
| Access | Proprietary | Proprietary |
Which is better: Claude Sonnet 5 or DeepSeek-V4-Flash-0731?
DeepSeek-V4-Flash-0731 leads Claude Sonnet 5 on 1 of the 1 benchmark they both report (Terminal-Bench 2.1). Claude Sonnet 5 shipped 31 days before DeepSeek-V4-Flash-0731, 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-Flash-0731 leads at 82.7% vs Claude Sonnet 5 at 80.4%.
Frequently asked questions
Claude Sonnet 5 was released by Anthropic on Jun 30 2026.
DeepSeek-V4-Flash-0731 was released by DeepSeek on Jul 31 2026.
DeepSeek-V4-Flash-0731 leads on Terminal-Bench 2.1 — Claude Sonnet 5 80.4% vs DeepSeek-V4-Flash-0731 82.7%.
Other comparisons
Claude Sonnet 5vsGPT-5.6 SolDeepSeek-V4-Flash-0731vsGPT-5.6 SolClaude Sonnet 5vsGemini 3.6 FlashDeepSeek-V4-Flash-0731vsGemini 3.6 FlashClaude Sonnet 5vsMuse Spark 1.1DeepSeek-V4-Flash-0731vsMuse Spark 1.1Claude Sonnet 5vsGrok 4.5DeepSeek-V4-Flash-0731vsGrok 4.5Claude Sonnet 5vsMistral Medium 3.5DeepSeek-V4-Flash-0731vsMistral Medium 3.5Claude Sonnet 5vsKimi K3DeepSeek-V4-Flash-0731vsKimi K3