Google Gemini 4 Carbon has released its ARC-AGI benchmark scores.
Automated summary · Based on collected summaries; not individually verified
Prepared by HotAI
What happened
ARC Prize has released results for Gemini 4 Carbon on the ARC-AGI (Verified) benchmark. It scored 65.1% on the ARC-AGI-3 standard test with a cost of $7,200; 49.6% on ARC-AGI-2 at $0.10 per task; and 98.5% on ARC-AGI-1 at $0.16 per task. This outperforms its predecessor, Argon, by 18 percentage points on the standard test.
Background
What Is Gemini? Multimodal Models and App Features
Gemini is Google’s generative AI model family, with particular versions accepting text and multiple media types. Gemini Apps is the application for chatting and uploading files. Multimodality must distinguish input types from generated content. For example, Gemini 4 Argon accepts audio and video but outputs text; understanding video does not imply generating it. Readers seeking local model weights should also distinguish the separate Gemma family.
What is artificial general intelligence? Understanding AGI definitions and disputes
AGI means artificial general intelligence and concerns systems capable across a broad range of tasks rather than one specialty. There is no single attainment criterion adopted by all researchers and institutions. Identify the definition and task scope before judging progress; a demonstration, model name, or individual benchmark score is insufficient.
Reading notes
The event summary comes from collected excerpts. Background passages quote existing HotAI articles to explain terms and do not establish new facts about this event. Check the original sources for product results, conditions and subsequent updates.
Original source
Sources and collection timeline
| Source | Report title | Original publication time | Collected by HotAI |
|---|---|---|---|
| x.com | Google Gemini 4 Carbon has released its ARC-AGI benchmark scores. | 2026-11-11 04:31 | 2026-11-11 05:07 |