Gemini 2.5 ProvsGrok 4.20 Beta
Gemini 2.5 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. | $1.25 | $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. | $10.00 | $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. | $0.125 | $0.20 |
| 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. | 20% | 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. | 59.6% | 76.7% |
| BenchmarksPublished by one model only | ||
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. | 18.8% | — |
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. | — | 53.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 86.4% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 68% | — |
| Overview | ||
| Company | SpaceXAI | |
| Release date | Mar 25 2025 | Feb 17 2026 |
| Access | Proprietary | Proprietary |
Other comparisons
Gemini 2.5 ProvsClaude Fable 5.1Grok 4.20 BetavsClaude Fable 5.1Gemini 2.5 ProvsGPT-6 AstraGrok 4.20 BetavsGPT-6 AstraGemini 2.5 ProvsMuse Spark 1.3Grok 4.20 BetavsMuse Spark 1.3Gemini 2.5 ProvsDeepSeek-V4.1-FlashGrok 4.20 BetavsDeepSeek-V4.1-FlashGemini 2.5 ProvsMistral Medium 3.5Grok 4.20 BetavsMistral Medium 3.5Gemini 2.5 ProvsKimi K3Grok 4.20 BetavsKimi K3
Frequently asked questions
Grok 4.20 Beta leads Gemini 2.5 Pro on 2 of the 2 benchmarks they both report (BullshitBench v2, SWE-Bench Verified). Both charge $1.25 per million input tokens. Grok 4.20 Beta is cheaper on output: $2.50 vs $10.00 per million tokens. Figures are base-tier rates. Gemini 2.5 Pro shipped 329 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 Gemini 2.5 Pro at 20%. On SWE-Bench Verified, Grok 4.20 Beta leads at 76.7% vs Gemini 2.5 Pro at 59.6%.