Compare AI models
| Specifications | ||
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 | 128k |
| 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 | — |
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 | — |
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. | $30.00OpenAI | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $180.00OpenAI | — |
| $15,000OpenAI list price | — | |
| These models have no shared benchmark scores. | ||
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. | 36% | — |
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. | 64% | — |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | — | 75.7% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 75.2% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 90.1% | — |
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. | 43.1% | — |
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. | 57.2% | — |
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. | 84.2% | — |
FrontierMath · Tier 1–3Advanced math — Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | 52.4% | — |
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. | 39.6% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 57.9% |
GeneBenchReasoning — end-to-end genomics and quantitative biology analysis on the original GeneBench set | 33.2% | — |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | — | 81.9% |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | — | 90.9% |
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. | 82.3% | — |
| Overview | ||
| Company | OpenAI | Z.ai |
| Release date | Apr 23 2026 | Jun 5 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
GPT-5.5-ProvsClaude Fable 5.2GLM-4-AirvsClaude Fable 5.2GPT-5.5-ProvsGemini 4 HydrogenGLM-4-AirvsGemini 4 HydrogenGPT-5.5-ProvsMuse EmberGLM-4-AirvsMuse EmberGPT-5.5-ProvsGrok 4.7GLM-4-AirvsGrok 4.7GPT-5.5-ProvsDeepSeek-V4.1-Flash-1017GLM-4-AirvsDeepSeek-V4.1-Flash-1017GPT-5.5-ProvsMistral Large 4GLM-4-AirvsMistral Large 4Frequently asked questions
GPT-5.5-Pro and GLM-4-Air don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only GPT-5.5-Pro has a verified first-party price for an available API: $30.00 per million input tokens and $180.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for GLM-4-Air. GLM-4-Air shipped 687 days before GPT-5.5-Pro, so benchmark comparisons should account for the intervening progress.
Context windows are 1.05M (GPT-5.5-Pro) vs 128k (GLM-4-Air).
Direct benchmark comparisons are unavailable — GPT-5.5-Pro and GLM-4-Air don't publish scores on any of the same benchmarks.