Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5
Web page · https://artificialanalysis.ai/articles/gemini-4-carbon-new-number-1
First seen by Oriel on .
AI summary
Google’s Gemini 4 Carbon ranks first on the Artificial Analysis Intelligence Index v5, with strong reasoning and science results and improved coding, but it trails leaders in some areas.
- It leads 4 of 9 Index evaluations: HLE-Diamond, Terminal-Bench-Science, AA-Omniscience, and AutomationBench-AA.
- On the Coding Agent Index, it scores 59 with Antigravity CLI, three points behind Claude Opus 5.5; it ranks second on Terminal-Bench 4.0 and FrontierCode v1.1.
- Its AA-Briefcase score of 1609 Elo improves 126 points over Gemini 4 Argon, but remains behind several competing models.
- At standard pricing, Intelligence Index tasks cost $7.76, about 23% less than Claude Opus 5.5; its 123k output tokens per task are 29% fewer.
- The model has a 1M-token context window and accepts text, image, video, and speech input; it is rolling out to selected users and is not publicly available.
#gemini #llm benchmarks #coding agents #ai pricing
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Points
Score reported by the source.
- Hacker News: 336, latest observation ; +318 over observed period since
Comments
Comment count reported by the source.
- Hacker News: 242, latest observation ; +233 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hacker News | 50288019 | https://artificialanalysis.ai/articles/gemini-4-carbon-new-number-1 Read discussion |