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 | — |
| 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. | 45% | 50% |
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% | — |
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. | — | 35% |
| Overview | ||
| Company | OpenAI | SpaceXSI |
| Release date | Dec 18 2025 | Apr 17 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
GPT-5.2-CodexvsClaude Fable 5.2Grok 4.3 BetavsClaude Fable 5.2GPT-5.2-CodexvsGemini 4 CarbonGrok 4.3 BetavsGemini 4 CarbonGPT-5.2-CodexvsMuse EmberGrok 4.3 BetavsMuse EmberGPT-5.2-CodexvsDeepSeek-V4.1-Flash-1017Grok 4.3 BetavsDeepSeek-V4.1-Flash-1017GPT-5.2-CodexvsMistral Large 4Grok 4.3 BetavsMistral Large 4GPT-5.2-CodexvsKimi K3.1 ProGrok 4.3 BetavsKimi K3.1 ProFrequently asked questions
Grok 4.3 Beta leads GPT-5.2-Codex on 1 of the 1 benchmark they both report (BullshitBench v2). GPT-5.2-Codex shipped 120 days before Grok 4.3 Beta, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On BullshitBench v2, Grok 4.3 Beta leads at 50% vs GPT-5.2-Codex at 45%.