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 | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $2.50 | $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. | $15.00 | $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. | $0.25 | $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. | $1.25OpenAI | $0.60GMICloud |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $7.50OpenAI | $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. | 48% | 28% |
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. | 75.1% | 56.2% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 82.7% | 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. | 52.1% | 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. | 92.8% | 86% |
ProgramBenchProgram reconstruction — The AI receives a working program and its documentation, then builds a replacement from scratch without the original source code, internet access or decompilation. The score is the percentage of 200 programs that pass every behavioral test. We record each model's best published mini-SWE-agent result, including higher reasoning efforts where available. Partial test-pass rates and almost-solved programs do not count toward this score. Equal scores share a rank here; the official board also uses partial progress to break ties. Higher is better. | 0% | — |
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% |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 65% | — |
Expert-SWE (Internal)Software engineering — OpenAI's private set of expert-level software-engineering problems. Higher is better. | 68.5% | — |
ToolathlonGeneral tool use — Tests how well the AI uses everyday real-world tools and apps to get things done. Higher is better. | 54.6% | — |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 79% | — |
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. | 73.95% | — |
FrontierMath · Tier 1–3Advanced math — Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | 47.6% | — |
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. | 27.1% | — |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 75% | — |
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. | 83% | — |
| Overview | ||
| Company | OpenAI | Z.ai |
| Release date | Mar 5 2026 | Feb 12 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Frequently asked questions
GPT-5.4 leads GLM-5 on 5 of the 5 benchmarks they both report. GLM-5 is cheaper on both input and output: $1.00 vs $2.50 per million input tokens, and $3.20 vs $15.00 per million output tokens. GLM-5 shipped 21 days before GPT-5.4, so benchmark comparisons should account for the intervening progress.
GPT-5.4 is closed, while GLM-5 is open weight.
On BullshitBench v2, GPT-5.4 leads at 48% vs GLM-5 at 28%. On Terminal-Bench 2.0, GPT-5.4 leads at 75.1% vs GLM-5 at 56.2%. On BrowseComp, GPT-5.4 leads at 82.7% vs GLM-5 at 75.9%. On Humanity's Last Exam · with tools, GPT-5.4 leads at 52.1% vs GLM-5 at 50.4%. On GPQA Diamond, GPT-5.4 leads at 92.8% vs GLM-5 at 86%.