DeepSeek-V4-ProvsGLM-5
DeepSeek-V4-Pro | GLM-5 | |
|---|---|---|
| Specifications | ||
Parameters | — | 744B |
| 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. | 14% | 28%Best |
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. | — | 77.8% |
Multilingual coding SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 73.3% |
Competitive coding LiveCodeBenchCoding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 93.5% | — |
Agentic terminal coding Terminal-Bench 2.0Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 56.2% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4%Best | 75.9% |
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. | — | 50.4% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 90.1%Best | 86% |
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. | 1457 | — |
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. | 1446Best | 1435 |
| Overview | ||
| Company | DeepSeek | Z.ai |
| Release date | Apr 24 2026 | Feb 12 2026 |
| Access | Open Weight | Open Weight |
Which is better: DeepSeek-V4-Pro or GLM-5?
DeepSeek-V4-Pro leads GLM-5 on 3 of the 4 benchmarks they both report (BullshitBench v2, BrowseComp, GPQA Diamond, Arena Elo (Code)). GLM-5 shipped 71 days before DeepSeek-V4-Pro, 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 BullshitBench v2, GLM-5 leads at 28% vs DeepSeek-V4-Pro at 14%. On BrowseComp, DeepSeek-V4-Pro leads at 83.4% vs GLM-5 at 75.9%. On GPQA Diamond, DeepSeek-V4-Pro leads at 90.1% vs GLM-5 at 86%. On Arena Elo (Code), DeepSeek-V4-Pro leads at 1446 vs GLM-5 at 1435.
Frequently asked questions
DeepSeek-V4-Pro was released by DeepSeek on Apr 24 2026.
GLM-5 was released by Z.ai on Feb 12 2026.
DeepSeek-V4-Pro leads on GPQA Diamond — DeepSeek-V4-Pro 90.1% vs GLM-5 86%.