Gemini 3.0 ProvsGrok 4.20 Beta
Gemini 3.0 Pro | Grok 4.20 Beta | |
|---|---|---|
| Benchmarks | ||
Nonsense detection BullshitBench v2Given 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% |
Coding SWE-Bench VerifiedReal 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. | 76.2% | — |
Next.js coding Next.js EvalsVercel'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. | 67% | — |
Abstract reasoning ARC-AGI-2Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 31.1% | 53.3%Best |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.9% | — |
Multimodal MMMUTests the AI on understanding images and text together across many college subjects. Higher is better. | 81% | — |
Community preference Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | 1486Best | 1475 |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1439 | — |
| Overview | ||
| Company | SpaceXAI | |
| Release date | Nov 18 2025 | Feb 17 2026 |
| Access | Proprietary | Proprietary |
Which is better: Gemini 3.0 Pro or Grok 4.20 Beta?
Gemini 3.0 Pro and Grok 4.20 Beta are evenly matched across the 2 benchmarks they both report (ARC-AGI-2, Arena Elo (Text)). Gemini 3.0 Pro shipped 91 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 ARC-AGI-2, Grok 4.20 Beta leads at 53.3% vs Gemini 3.0 Pro at 31.1%. On Arena Elo (Text), Gemini 3.0 Pro leads at 1486 vs Grok 4.20 Beta at 1475.
Frequently asked questions
Gemini 3.0 Pro was released by Google on Nov 18 2025.
Grok 4.20 Beta was released by SpaceXAI on Feb 17 2026.
Grok 4.20 Beta leads on ARC-AGI-2 — Gemini 3.0 Pro 31.1% vs Grok 4.20 Beta 53.3%.
Other comparisons
Gemini 3.0 ProvsClaude Opus 5Grok 4.20 BetavsClaude Opus 5Gemini 3.0 ProvsGPT-5.6 SolGrok 4.20 BetavsGPT-5.6 SolGemini 3.0 ProvsMuse Spark 1.1Grok 4.20 BetavsMuse Spark 1.1Gemini 3.0 ProvsDeepSeek-V4-Flash-0731Grok 4.20 BetavsDeepSeek-V4-Flash-0731Gemini 3.0 ProvsMistral Medium 3.5Grok 4.20 BetavsMistral Medium 3.5Gemini 3.0 ProvsKimi K3Grok 4.20 BetavsKimi K3