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. | 8k | 400k |
| 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. | $30.00Azure | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $60.00Azure | — |
| $9,000Azure | — | |
| 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. | — | 45% |
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. | — | 46% |
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. | 67% | — |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | 80.9 | — |
ARC-ChallengeReasoning — multiple-choice science questions from the AI2 Reasoning Challenge; unrelated to ARC-AGI | 96.3% | — |
HellaSwagReasoning — commonsense completion of short scenarios | 95.3% | — |
WinoGrandeReasoning — resolving ambiguous pronouns in context | 87.5% | — |
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. | 86.4% | — |
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. | 92% | — |
| Overview | ||
| Company | OpenAI | OpenAI |
| Release date | Mar 14 2023 | Dec 18 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
GPT-4vsClaude Fable 5.2GPT-5.2-CodexvsClaude Fable 5.2GPT-4vsGemini 4 CarbonGPT-5.2-CodexvsGemini 4 CarbonGPT-4vsMuse EmberGPT-5.2-CodexvsMuse EmberGPT-4vsGrok 4.7GPT-5.2-CodexvsGrok 4.7GPT-4vsDeepSeek-V4.1-Flash-1017GPT-5.2-CodexvsDeepSeek-V4.1-Flash-1017GPT-4vsMistral Large 4GPT-5.2-CodexvsMistral Large 4Frequently asked questions
GPT-4 and GPT-5.2-Codex don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GPT-4 shipped 1010 days before GPT-5.2-Codex, so benchmark comparisons should account for the intervening progress.
Context windows are 8k (GPT-4) vs 400k (GPT-5.2-Codex).
Direct benchmark comparisons are unavailable — GPT-4 and GPT-5.2-Codex don't publish scores on any of the same benchmarks.