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. | 1B/4B/12B/27B | — |
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 |
| 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. | $0.04DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.05Parasail | — |
| $10.50Parasail · bf16 | — | |
| 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. | 3% | 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% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 29.7% | — |
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. | 87.8% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 90.4% | — |
MATHReasoning — accuracy on the original competition mathematics test set | 89% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 42.4% | — |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 10% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 67.5% | — |
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. | 76.9% | — |
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. | 95.9% | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 67.6% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 64.9% | — |
| Overview | ||
| Company | OpenAI | |
| Release date | Mar 12 2025 | Dec 18 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Gemma 3vsClaude Fable 5.2GPT-5.2-CodexvsClaude Fable 5.2Gemma 3vsMuse EmberGPT-5.2-CodexvsMuse EmberGemma 3vsGrok 4.7GPT-5.2-CodexvsGrok 4.7Gemma 3vsDeepSeek-V4.1-Flash-1017GPT-5.2-CodexvsDeepSeek-V4.1-Flash-1017Gemma 3vsMistral Large 4GPT-5.2-CodexvsMistral Large 4Gemma 3vsKimi K3.1 ProGPT-5.2-CodexvsKimi K3.1 ProFrequently asked questions
GPT-5.2-Codex leads Gemma 3 on 1 of the 1 benchmark they both report (BullshitBench v2). Gemma 3 shipped 281 days before GPT-5.2-Codex, so benchmark comparisons should account for the intervening progress.
Gemma 3 is open weight, while GPT-5.2-Codex is closed.
On BullshitBench v2, GPT-5.2-Codex leads at 45% vs Gemma 3 at 3%.