Google ships Gemini 4 Carbon two weeks after Argon, posts 59 on AA Index v5.0
kimmonismus · x · 2026-10-29
Sundar Pichai announced Gemini 4 Carbon just two weeks after Gemini 4 Argon. Official evals show 59 on AA Index v5.0 (vs Claude Opus 5.5's 58, GPT-6 Astra's 57), with major gains in long-running tasks and cybersecurity.
- Security: CWE-bench 71.0%, ExploitGym 54.8%, SEC-bench Pro 88.2% — all ahead of GPT-6 Astra and Claude Opus 5.5
- Computer use: Agents' Last Exam 77.4%, OSWorld-21 81.5%
- Long context GraphWalks (256k–1M): 96.2%, well ahead of rivals
- Vending-Bench 2 bank balance $16,484, highest among compared models
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