Gemini 4 Carbon scores 59 on Coding Agent Index, second only to Claude Opus 5.5
ArtificialAnlys · x · 2026-10-29
Artificial Analysis detailed coding-agent results: with Antigravity CLI, Gemini 4 Carbon scores 59 on the Coding Agent Index, behind only Claude Code with Opus 5.5 (62) and 6 points above Gemini 4 Argon. It ranks second on Terminal-Bench 4.0 (64%) and FrontierCode v1.1 (51%), but sits mid-pack on SWE-Atlas-QnA-AA (64% vs 69% for Muse Code with Muse Wonder Full).
More from coding & agent
- Tobi Lütke: Shopify's Expo Mode is among the first built on Google's HTML-in-Canvas API — nicolascraske · 2026-10-29
- Researcher builds Claude-assisted transcription factor knowledge base with layered tutorials — jmschreiber91 · 2026-10-29
- Video2Game: H3 Max Generates Gameplay Video, Claude Turns It Into a Playable three.js Game — OdinLovis · 2026-10-29
- After 3 Years of Heavy AI Prompting, Domain Vocabulary Beats Prompt Tricks — Dimillian · 2026-10-29
- Agents push compute back to CPUs: $221B server CPU market seen by 2030 — BenBajarin · 2026-10-29
- Cursor removes its beloved Cmd+K command, frustrating power users — jbhuang0604 · 2026-10-29