GPT-5.2vsGrok 4.20 Beta
GPT-5.2 | 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. | $1.75 | $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. | $14.00 | $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. | $0.175 | $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. | $1.75Azure | — |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $14.00Azure | — |
| 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. | 38% | 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. | 80% | 76.7% |
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. | 52.9% | 53.3% |
| BenchmarksPublished by one model only | ||
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 65.8% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 92.4% | — |
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. | 47.3% | — |
| Overview | ||
| Company | OpenAI | SpaceXAI |
| Release date | Dec 11 2025 | Feb 17 2026 |
| Access | Proprietary | Proprietary |
Other comparisons
GPT-5.2vsClaude Fable 5.1Grok 4.20 BetavsClaude Fable 5.1GPT-5.2vsGemini 3.8 FlashGrok 4.20 BetavsGemini 3.8 FlashGPT-5.2vsMuse Spark 1.3Grok 4.20 BetavsMuse Spark 1.3GPT-5.2vsDeepSeek-V4.1-FlashGrok 4.20 BetavsDeepSeek-V4.1-FlashGPT-5.2vsMistral Medium 3.5Grok 4.20 BetavsMistral Medium 3.5GPT-5.2vsKimi K3Grok 4.20 BetavsKimi K3
Frequently asked questions
Grok 4.20 Beta leads GPT-5.2 on 2 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, ARC-AGI-2). Grok 4.20 Beta is cheaper on both input and output: $1.25 vs $1.75 per million input tokens, and $2.50 vs $14.00 per million output tokens. Figures are base-tier rates. GPT-5.2 shipped 68 days before Grok 4.20 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 4.20 Beta leads at 56% vs GPT-5.2 at 38%. On SWE-Bench Verified, GPT-5.2 leads at 80% vs Grok 4.20 Beta at 76.7%. On ARC-AGI-2, Grok 4.20 Beta leads at 53.3% vs GPT-5.2 at 52.9%.