GPT-5.4-ProvsGrok 4.20 Beta
GPT-5.4-Pro | Grok 4.20 Beta | |
|---|---|---|
| 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. | $30.00 | $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. | $180.00 | $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. | — | $0.20 |
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. | $30.00Azure | — |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $180.00Azure | — |
| Benchmarks | ||
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. | 83.3% | 53.3% |
| BenchmarksPublished by one model only | ||
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. | — | 56% |
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% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 89.3% | — |
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. | 58.7% | — |
FrontierMath · Tier 1–3Advanced math — Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | 50% | — |
FrontierMath · Tier 4Advanced math — Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | 38% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 94.4% | — |
GDPval (win/tie rate)Knowledge work — How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | 82% | — |
| Overview | ||
| Company | OpenAI | SpaceXAI |
| Release date | Mar 5 2026 | Feb 17 2026 |
| Access | Proprietary | Proprietary |
Other comparisons
GPT-5.4-ProvsClaude Fable 5.1Grok 4.20 BetavsClaude Fable 5.1GPT-5.4-ProvsGemini 3.8 FlashGrok 4.20 BetavsGemini 3.8 FlashGPT-5.4-ProvsMuse Spark 1.3Grok 4.20 BetavsMuse Spark 1.3GPT-5.4-ProvsDeepSeek-V4.1-FlashGrok 4.20 BetavsDeepSeek-V4.1-FlashGPT-5.4-ProvsMistral Medium 3.5Grok 4.20 BetavsMistral Medium 3.5GPT-5.4-ProvsKimi K3Grok 4.20 BetavsKimi K3
Frequently asked questions
GPT-5.4-Pro leads Grok 4.20 Beta on 1 of the 1 benchmark they both report (ARC-AGI-2). Grok 4.20 Beta is cheaper on both input and output: $1.25 vs $30.00 per million input tokens, and $2.50 vs $180.00 per million output tokens. Figures are base-tier rates. Grok 4.20 Beta shipped 16 days before GPT-5.4-Pro, 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 ARC-AGI-2, GPT-5.4-Pro leads at 83.3% vs Grok 4.20 Beta at 53.3%.