Google officially unveils Gemini 4 Carbon: strongest frontier model yet, leading most evals
OlivierBachem · x · 2026-10-29
Google DeepMind (via Olivier Bachem retweeting the official announcement) introduced Gemini 4 Carbon, billed as its strongest frontier model yet, with next-level cybersecurity and long-horizon task performance and an emphasis on advancing the frontier safely.
The attached eval table shows AA Index v5.0 at 59 (vs Argon 50, Claude Opus 5.5 58, GPT-6 Astra 57), plus leads on SWE-sweep 9.6%, Terminal-Bench 4.0 65.2%, GraphWalks 96.2%, SEC-bench Pro 88.2% and ExploitGym 54.8%; it trails only on FrontierSWE 2 and OSWorld-2.1. Methodology at deepmind.google/models/evals-methodology/gemini-4-carbon.
Related event: Google launches Gemini 4 Carbon, topping the Artificial Analysis index(84 posts)→
More from Models
- New benchmarks suggest Kimi K3.1 improves on hard tasks despite skipping SWE-maxxing — teortaxesTex · 2026-10-29
- Insider claims Anthropic is sandbagging a bigger lab announcement due Q4-end or Q1 — ChrisGPT · 2026-10-29
- Information-theoretic scaling laws predict memorization and FID in diffusion models — LucaAmb · 2026-10-29
- Early Hands-On: Google's Carbon Beats Argon With Less Slop, Better Constraint Adherence — legit_api · 2026-10-29
- LMArena tests Gemini 4 Carbon preview: strong on 3D worlds and creativity, gaps in detail — arena · 2026-10-29
- Gemini 3.1 Pro split-persona breakdown: two selves fight over the browser — davidad · 2026-10-29