Compare AI models
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | — | 744B |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $0.66 | $1.00 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $1.98 | $3.20 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.022 | $0.20 |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.2442Baidu | $0.60GMICloud |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $0.7326Baidu | $1.92GMICloud |
| Benchmarks | ||
BullshitBench v2Nonsense detection — Given 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. | 35% | 28% |
SWE-Bench VerifiedCoding — Real 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. | 80.6% | 77.8% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4% | 75.9% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity'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% | 50.4% |
SWE-Bench MultilingualMultilingual coding — Like 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% |
Terminal-Bench 2.1Agentic terminal coding — Can 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% | — |
Terminal-Bench 2.0Agentic terminal coding — Can 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% |
Toolathlon-VerifiedPersonal tool use — Tests 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% | — |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 83.3% | — |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity'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% | — |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 61.3% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 86% |
AutomationBenchBusiness workflows — Tests 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% | — |
| Overview | ||
| Company | DeepSeek | Z.ai |
| Release date | Aug 13 2026 | Feb 12 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-Pro-0813vsClaude Opus 5.5GLM-5vsClaude Opus 5.5DeepSeek-V4-Pro-0813vsGPT-6 SolGLM-5vsGPT-6 SolDeepSeek-V4-Pro-0813vsGemini 3.8 FlashGLM-5vsGemini 3.8 FlashDeepSeek-V4-Pro-0813vsMuse Spark 1.3GLM-5vsMuse Spark 1.3DeepSeek-V4-Pro-0813vsGrok 4.7GLM-5vsGrok 4.7DeepSeek-V4-Pro-0813vsMistral Medium 3.5GLM-5vsMistral Medium 3.5Frequently asked questions
DeepSeek-V4-Pro-0813 leads GLM-5 on 4 of the 4 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, BrowseComp, Humanity's Last Exam). DeepSeek-V4-Pro-0813 is cheaper on both input and output: $0.66 vs $1.00 per million input tokens, and $1.98 vs $3.20 per million output tokens. Figures are base-tier rates. GLM-5 shipped 182 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 BullshitBench v2, DeepSeek-V4-Pro-0813 leads at 35% vs GLM-5 at 28%. On SWE-Bench Verified, DeepSeek-V4-Pro-0813 leads at 80.6% vs GLM-5 at 77.8%. On BrowseComp, DeepSeek-V4-Pro-0813 leads at 83.4% vs GLM-5 at 75.9%. On Humanity's Last Exam · with tools, DeepSeek-V4-Pro-0813 leads at 60% vs GLM-5 at 50.4%.