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. | 400k | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
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. | $1.25Azure | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $10.00Azure | — |
| $750Azure | — | |
| These models have no shared benchmark scores. | ||
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. | 77.9% | — |
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% |
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. | 58.1% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 75.2% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 57.9% |
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% |
| Overview | ||
| Company | OpenAI | Z.ai |
| Release date | Nov 19 2025 | Jun 5 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
GPT-5.1-Codex-MaxvsClaude Fable 5.2GLM-4-AirvsClaude Fable 5.2GPT-5.1-Codex-MaxvsGemini 4 HydrogenGLM-4-AirvsGemini 4 HydrogenGPT-5.1-Codex-MaxvsMuse EmberGLM-4-AirvsMuse EmberGPT-5.1-Codex-MaxvsGrok 4.7GLM-4-AirvsGrok 4.7GPT-5.1-Codex-MaxvsDeepSeek-V4.1-Flash-1017GLM-4-AirvsDeepSeek-V4.1-Flash-1017GPT-5.1-Codex-MaxvsMistral Large 4GLM-4-AirvsMistral Large 4Frequently asked questions
GPT-5.1-Codex-Max and GLM-4-Air don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GLM-4-Air shipped 532 days before GPT-5.1-Codex-Max, so benchmark comparisons should account for the intervening progress.
Context windows are 400k (GPT-5.1-Codex-Max) vs 128k (GLM-4-Air).
Direct benchmark comparisons are unavailable — GPT-5.1-Codex-Max and GLM-4-Air don't publish scores on any of the same benchmarks.