DeepSeek-V4-Pro-0813vsMuse Spark
DeepSeek-V4-Pro-0813 | Muse Spark | |
|---|---|---|
| Benchmarks | ||
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. | — | 2.9% |
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. | — | 14.3% |
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. | — | 16.5% |
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. | — | 55% |
Coding SWE-Bench VerifiedReal 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. | — | 77.4% |
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. | — | 10% |
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 | 67.3% |
Multi-step tool use MCP AtlasCan the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | — | 82.2% |
Professional tool use JobBenchTests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | — | 17% |
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%Best | 49.4% |
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 | 50.4% |
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. | — | 42.5% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 89.5% |
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. | — | 53.3% |
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% | — |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 88.9% |
Visual reasoning BabyVisionTests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better. | — | 39.9% |
Multimodal MMMUTests the AI on understanding images and text together across many college subjects. Higher is better. | — | 80.4% |
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. | — | 1488 |
| Overview | ||
| Company | DeepSeek | Meta |
| Release date | Aug 13 2026 | Apr 8 2026 |
| Access | Proprietary | Proprietary |
Which is better: DeepSeek-V4-Pro-0813 or Muse Spark?
DeepSeek-V4-Pro-0813 leads Muse Spark on 3 of the 3 benchmarks they both report (Terminal-Bench 2.1, Toolathlon-Verified, Humanity's Last Exam). Muse Spark shipped 127 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 Muse Spark at 67.3%. On Toolathlon-Verified, DeepSeek-V4-Pro-0813 leads at 74.1% vs Muse Spark at 49.4%. On Humanity's Last Exam · with tools, DeepSeek-V4-Pro-0813 leads at 60% vs Muse Spark at 50.4%.
Frequently asked questions
DeepSeek-V4-Pro-0813 was released by DeepSeek on Aug 13 2026.
Muse Spark was released by Meta on Apr 8 2026.
DeepSeek-V4-Pro-0813 leads on Terminal-Bench 2.1 — DeepSeek-V4-Pro-0813 87.9% vs Muse Spark 67.3%.
DeepSeek-V4-Pro-0813 leads on Humanity's Last Exam · with tools — DeepSeek-V4-Pro-0813 60% vs Muse Spark 50.4%.
Other comparisons
DeepSeek-V4-Pro-0813vsClaude Opus 5Muse SparkvsClaude Opus 5DeepSeek-V4-Pro-0813vsGPT-5.6-CyberMuse SparkvsGPT-5.6-CyberDeepSeek-V4-Pro-0813vsGemini 3.6 FlashMuse SparkvsGemini 3.6 FlashDeepSeek-V4-Pro-0813vsGrok 4.6Muse SparkvsGrok 4.6DeepSeek-V4-Pro-0813vsMistral Medium 3.5Muse SparkvsMistral Medium 3.5DeepSeek-V4-Pro-0813vsKimi K3Muse SparkvsKimi K3