Gemini 4 Carbon tops Artificial Analysis index; no public API yet
vitaliychiley · x · 2026-10-29
RT of @mohansolo: Google fast-followed with Gemini 4 Carbon, now #1 on Artificial Analysis' new index (59, beating GPT-6.1 and Claude Opus 4.5). People internally have enjoyed using it in Antigravity on the hardest tasks. It performs extremely well on cyber tasks like finding and patching vulnerabilities, so Google is expanding access to the Fairwind Program before wider availability in Antigravity. The chart shows Antigravity (Gemini 4 Carbon) at 59 on the Coding Agent Index, just behind Claude Code Opus 4.5.
More from Models
- Gemini 4 Carbon benchmarks prompt TheZvi to declare Gemini 4 Argon 'was' near-frontier — TheZvi · 2026-10-29
- Preprint: Human peer reviewers caught only 27% of major errors, all 15 AI models beat them (53-96%) — anshulkundaje · 2026-10-29
- Giotto launches as 'European sovereign AI,' gets exposed as Kimi-based with benchmark EULA gag — TheZachMueller · 2026-10-29
- Google ships Gemini 4 Carbon two weeks after Argon, topping AA index at 59 — The Decoder · 2026-10-29
- Google Announces Gemini 4 Carbon, Its Next Frontier Model, Starting With Cyber Defenders — Snoo26837 · 2026-10-29
- Suhail launches Particle: particle-1 matches performance with ~45% fewer tokens — ycombinator · 2026-10-29