AI & Machine Learning
Oct 29, 2026
Gemini 4 Carbon Achieves Top Ranking on Artificial Analysis Intelligence Index v5
Oct 29, 2026
AI Summary
Google's Gemini 4 Carbon has secured the top position on the Artificial Analysis Intelligence Index v5, scoring 59. It shows significant improvements in complex reasoning and knowledge tasks, although it remains behind in some coding and knowledge work areas compared to competitors.
- Gemini 4 Carbon ranks first on the Artificial Analysis Intelligence Index v5, excelling in four of the nine evaluations, including HLE-Diamond and AA-Omniscience.
- It scores 59 on the Intelligence Index, just behind Claude Opus 5.5 in the coding agent category, with notable gains in coding and knowledge work compared to previous Gemini models.
- The model is currently being rolled out to selected users and is not publicly available yet, with a 50% launch discount offered.
- In agentic knowledge work, Gemini 4 Carbon scores 1609 Elo, improving from Gemini 4 Argon but still trailing behind other models like Grok 4.7 and Muse Wonder.
- The cost per task for Gemini 4 Carbon is approximately $7.76, which is lower than Claude Opus 5.5 but higher than GPT-6 Astra.
- It has a context window of 1 million tokens and supports multimodal inputs, including text, image, video, and speech.
- The model's accuracy in the AA-Omniscience v1.1 evaluation is 58%, with a hallucination rate of 11%, which is relatively low compared to other models.
gemini 4 carbonartificial intelligenceindexrankingmachine learning