Compare AI models
| Specifications | ||
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | 400k | — |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $0.75 | $1.25 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $4.50 | $2.50 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.075 | $0.20 |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.375OpenAI | — |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $2.25OpenAI | — |
| 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. | 32% | 56% |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 18.9% | 53.3% |
ProgramBenchProgram reconstruction — The AI receives a working program and its documentation, then builds a replacement from scratch without the original source code, internet access or decompilation. The score is the percentage of 200 programs that pass every behavioral test. We record each model's best published mini-SWE-agent result, including higher reasoning efforts where available. Partial test-pass rates and almost-solved programs do not count toward this score. Equal scores share a rank here; the official board also uses partial progress to break ties. Higher is better. | 0% | — |
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. | — | 76.7% |
Supabase Evals · with skillsSupabase coding — Supabase's own open benchmark: a coding agent is dropped into a real Supabase project and asked to do real work — set up a schema, fix a broken security policy, debug an Edge Function — and every run is checked against a live Supabase stack. This is the headline number, where the agent has Supabase's own skills loaded, as most people building on Supabase would. The score is the share of scenarios it got right. Higher is better. | 65.2% | — |
Supabase Evals · no skillsSupabase coding — The same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better. | 55.1% | — |
BU BenchBrowser agent — Can the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | 36% | — |
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. | 41.5% | — |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 72.1% | — |
| Overview | ||
| Company | OpenAI | SpaceXAI |
| Release date | Mar 17 2026 | Feb 17 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
GPT-5.4 minivsClaude Haiku 5.5Grok 4.20 BetavsClaude Haiku 5.5GPT-5.4 minivsGemini 4 ArgonGrok 4.20 BetavsGemini 4 ArgonGPT-5.4 minivsMuse Spark 1.3Grok 4.20 BetavsMuse Spark 1.3GPT-5.4 minivsDeepSeek-V4.1-FlashGrok 4.20 BetavsDeepSeek-V4.1-FlashGPT-5.4 minivsMistral Large 4Grok 4.20 BetavsMistral Large 4GPT-5.4 minivsKimi K3Grok 4.20 BetavsKimi K3Frequently asked questions
Grok 4.20 Beta leads GPT-5.4 mini on 2 of the 2 benchmarks they both report (BullshitBench v2, ARC-AGI-2). GPT-5.4 mini is cheaper on input: $0.75 vs $1.25 per million tokens. Grok 4.20 Beta is cheaper on output: $2.50 vs $4.50 per million tokens. Figures are base-tier rates. Grok 4.20 Beta shipped 28 days before GPT-5.4 mini, 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 4.20 Beta leads at 56% vs GPT-5.4 mini at 32%. On ARC-AGI-2, Grok 4.20 Beta leads at 53.3% vs GPT-5.4 mini at 18.9%.