DeepSeek-V4-Pro-0813vsGLM-5.3
DeepSeek-V4-Pro-0813 | GLM-5.3 | |
|---|---|---|
| Specifications | ||
Parameters | — | 743B |
| Benchmarks | ||
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. | — | 66.9% |
Agentic terminal coding Terminal-Bench 3.0command-line task completion (v3.0, much harder task set) | — | 28.3% |
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% | — |
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% | 84.5%Best |
Cybersecurity ExploitBenchA 'capability ladder' for security research, built by CMU researchers: the AI is given known bugs in Chrome's V8 engine and scored on how far it gets toward a working exploit inside a research sandbox — from understanding the patch to triggering a crash. Higher is better. | — | 54.4% |
Cybersecurity ExploitGym · 6-hour budgetCan an AI agent turn a known software vulnerability into a working attack in a controlled lab? Built by MPI-SP researchers, the score is how many of 898 real cases (userspace programs, the V8 engine, the Linux kernel) it cracks — here with a 6-hour compute budget per case. Higher is better. | — | 130 |
Cybersecurity ExploitGym · 2-hour budgetCan an AI agent turn a known software vulnerability into a working attack in a controlled lab? Built by MPI-SP researchers, the score is how many of 898 real cases (userspace programs, the V8 engine, the Linux kernel) it cracks — here with a 2-hour compute budget per case. Higher is better. | — | 105 |
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% | 62.5%Best |
Agentic computer use Agent's Last ExamA hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better. | — | 28.5% |
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% | 48.2%Best |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | — | 1769 |
| Overview | ||
| Company | DeepSeek | Z.ai |
| Release date | Aug 13 2026 | Aug 14 2026 |
| Access | Proprietary | Proprietary |
Which is better: DeepSeek-V4-Pro-0813 or GLM-5.3?
GLM-5.3 leads DeepSeek-V4-Pro-0813 on 3 of the 3 benchmarks they both report (CyberGym, Humanity's Last Exam, AutomationBench). DeepSeek-V4-Pro-0813 shipped 1 days before GLM-5.3, 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 CyberGym, GLM-5.3 leads at 84.5% vs DeepSeek-V4-Pro-0813 at 83.3%. On Humanity's Last Exam · with tools, GLM-5.3 leads at 62.5% vs DeepSeek-V4-Pro-0813 at 60%. On AutomationBench, GLM-5.3 leads at 48.2% vs DeepSeek-V4-Pro-0813 at 31.8%.
Frequently asked questions
DeepSeek-V4-Pro-0813 was released by DeepSeek on Aug 13 2026.
GLM-5.3 was released by Z.ai on Aug 14 2026.
GLM-5.3 leads on Humanity's Last Exam · with tools — DeepSeek-V4-Pro-0813 60% vs GLM-5.3 62.5%.
Other comparisons
DeepSeek-V4-Pro-0813vsClaude Opus 5GLM-5.3vsClaude Opus 5DeepSeek-V4-Pro-0813vsGPT-5.6-CyberGLM-5.3vsGPT-5.6-CyberDeepSeek-V4-Pro-0813vsGemini 3.7 FlashGLM-5.3vsGemini 3.7 FlashDeepSeek-V4-Pro-0813vsMuse GlimmerGLM-5.3vsMuse GlimmerDeepSeek-V4-Pro-0813vsGrok 4.6GLM-5.3vsGrok 4.6DeepSeek-V4-Pro-0813vsMistral Medium 3.5GLM-5.3vsMistral Medium 3.5