Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 284B | 744B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 1M | 200k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $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. | — | $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. | — | $0.20 |
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.0388Wafer | $0.60GMICloud |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.1599Relace | $1.92GMICloud |
| $15.96Relace · fp4 | $216StreamLake · fp8 | |
| 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. | 39% | 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. | 79% | 77.8% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 73.2% | 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. | 34.8% | 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. | 82.7% | — |
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. | 70.3% | — |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 76.7% | — |
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. | 61.4% | — |
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. | 25.1% | — |
| Overview | ||
| Company | DeepSeek | Z.ai |
| Release date | Jul 31 2026 | Feb 11 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-Flash-0731vsClaude Haiku 5.5GLM-5vsClaude Haiku 5.5DeepSeek-V4-Flash-0731vsGPT-6.1 TerraGLM-5vsGPT-6.1 TerraDeepSeek-V4-Flash-0731vsGemini 4 CarbonGLM-5vsGemini 4 CarbonDeepSeek-V4-Flash-0731vsMuse Spark OpenGLM-5vsMuse Spark OpenDeepSeek-V4-Flash-0731vsGrok 4.7GLM-5vsGrok 4.7DeepSeek-V4-Flash-0731vsMistral Large 4GLM-5vsMistral Large 4Frequently asked questions
DeepSeek-V4-Flash-0731 and GLM-5 are evenly matched across the 4 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, BrowseComp, Humanity's Last Exam). Only GLM-5 has a verified first-party price for an available API: $1.00 per million input tokens and $3.20 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek-V4-Flash-0731. GLM-5 shipped 170 days before DeepSeek-V4-Flash-0731, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Flash-0731 has 284B parameters, while GLM-5 has 744B. Context windows are 1M (DeepSeek-V4-Flash-0731) vs 200k (GLM-5).
On BullshitBench v2, DeepSeek-V4-Flash-0731 leads at 39% vs GLM-5 at 28%. On SWE-Bench Verified, DeepSeek-V4-Flash-0731 leads at 79% vs GLM-5 at 77.8%. On BrowseComp, GLM-5 leads at 75.9% vs DeepSeek-V4-Flash-0731 at 73.2%. On Humanity's Last Exam · with tools, GLM-5 leads at 50.4% vs DeepSeek-V4-Flash-0731 at 34.8%.