DeepSeek-V4-Pro-0813vsMuse Glimmer
DeepSeek-V4-Pro-0813 | Muse Glimmer | |
|---|---|---|
| Specifications | ||
Parameters | — | 30B |
| Benchmarks | ||
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. | — | 51.2% |
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. | — | 76% |
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 | 51.7% |
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. | — | 75.5% |
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%Best | 22% |
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% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 83.5% |
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. | — | 65.9% |
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) | — | 953 |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 78.8% |
Multimodal reasoning MMMU-ProA tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 74% |
| Overview | ||
| Company | DeepSeek | Meta |
| Release date | Aug 13 2026 | Aug 10 2026 |
| Access | Proprietary | Open Weight |
Which is better: DeepSeek-V4-Pro-0813 or Muse Glimmer?
DeepSeek-V4-Pro-0813 leads Muse Glimmer on 2 of the 2 benchmarks they both report (Terminal-Bench 2.1, Humanity's Last Exam). Muse Glimmer shipped 3 days before DeepSeek-V4-Pro-0813, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Pro-0813 is proprietary, while Muse Glimmer is open weight.
On Terminal-Bench 2.1, DeepSeek-V4-Pro-0813 leads at 87.9% vs Muse Glimmer at 51.7%. On Humanity's Last Exam · no tools, DeepSeek-V4-Pro-0813 leads at 42.7% vs Muse Glimmer at 22%.
Frequently asked questions
DeepSeek-V4-Pro-0813 was released by DeepSeek on Aug 13 2026.
Muse Glimmer was released by Meta on Aug 10 2026.
DeepSeek-V4-Pro-0813 leads on Terminal-Bench 2.1 — DeepSeek-V4-Pro-0813 87.9% vs Muse Glimmer 51.7%.
DeepSeek-V4-Pro-0813 leads on Humanity's Last Exam · no tools — DeepSeek-V4-Pro-0813 42.7% vs Muse Glimmer 22%.
DeepSeek-V4-Pro-0813 is a proprietary model released by DeepSeek. Muse Glimmer is an open weight model released by Meta.