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. | 1M | 400k |
| 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. | — | 32% |
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. | 9.6% | — |
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. | 74.3% | — |
MATHReasoning — accuracy on the original competition mathematics test set | 54.9% | — |
HellaSwagReasoning — commonsense completion of short scenarios | 86.5% | — |
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. | 78.9% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 82.6% | — |
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. | 86.2% | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 58.4% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 56.1% | — |
| Overview | ||
| Company | OpenAI | |
| Release date | May 14 2024 | Nov 13 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Gemini 1.5 FlashvsClaude Fable 5.2GPT-5.1-CodexvsClaude Fable 5.2Gemini 1.5 FlashvsMuse EmberGPT-5.1-CodexvsMuse EmberGemini 1.5 FlashvsGrok 4.7GPT-5.1-CodexvsGrok 4.7Gemini 1.5 FlashvsDeepSeek-V4.1-Flash-1017GPT-5.1-CodexvsDeepSeek-V4.1-Flash-1017Gemini 1.5 FlashvsMistral Large 4GPT-5.1-CodexvsMistral Large 4Gemini 1.5 FlashvsKimi K3.1 ProGPT-5.1-CodexvsKimi K3.1 ProFrequently asked questions
Gemini 1.5 Flash and GPT-5.1-Codex don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Gemini 1.5 Flash shipped 548 days before GPT-5.1-Codex, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 1.5 Flash) vs 400k (GPT-5.1-Codex).
Direct benchmark comparisons are unavailable — Gemini 1.5 Flash and GPT-5.1-Codex don't publish scores on any of the same benchmarks.