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. | — | 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. | 1.05M | 200k |
| 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. | $30.00 | $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. | $180.00 | $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. | $15.00OpenAI | $0.60GMICloud |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $90.00OpenAI | $1.92GMICloud |
| $15,000OpenAI list price | $216GMICloud · fp8 | |
| Benchmarks | ||
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 89.3% | 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. | 58.7% | 50.4% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 94.4% | 86% |
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. | — | 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. | — | 77.8% |
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 2.0Agentic 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% |
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. | 83.3% | — |
FrontierMath · Tier 1–3Advanced math — Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | 50% | — |
FrontierMath · Tier 4Advanced math — Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | 38% | — |
ARC-AGI-1Reasoning — accuracy on the first edition of the abstract grid reasoning benchmark | 94.5% | — |
FinanceAgent v1.1Finance — performance on financial research tasks in the v1.1 evaluation | 61.5% | — |
GDPval (win/tie rate)Knowledge work — How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | 82% | — |
| Overview | ||
| Company | OpenAI | Z.ai |
| Release date | Mar 5 2026 | Feb 11 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
GPT-5.4-ProvsClaude Fable 5.2GLM-5vsClaude Fable 5.2GPT-5.4-ProvsGemini 4 HydrogenGLM-5vsGemini 4 HydrogenGPT-5.4-ProvsMuse EmberGLM-5vsMuse EmberGPT-5.4-ProvsGrok 4.7GLM-5vsGrok 4.7GPT-5.4-ProvsDeepSeek-V4.1-Flash-1017GLM-5vsDeepSeek-V4.1-Flash-1017GPT-5.4-ProvsMistral Large 4GLM-5vsMistral Large 4Frequently asked questions
GPT-5.4-Pro leads GLM-5 on 3 of the 3 benchmarks they both report (BrowseComp, Humanity's Last Exam, GPQA Diamond). GLM-5 is cheaper on both input and output: $1.00 vs $30.00 per million input tokens, and $3.20 vs $180.00 per million output tokens. Figures are base-tier rates. GLM-5 shipped 22 days before GPT-5.4-Pro, so benchmark comparisons should account for the intervening progress.
Context windows are 1.05M (GPT-5.4-Pro) vs 200k (GLM-5). GPT-5.4-Pro is closed, while GLM-5 is open weight.
On BrowseComp, GPT-5.4-Pro leads at 89.3% vs GLM-5 at 75.9%. On Humanity's Last Exam · with tools, GPT-5.4-Pro leads at 58.7% vs GLM-5 at 50.4%. On GPQA Diamond, GPT-5.4-Pro leads at 94.4% vs GLM-5 at 86%.