Google launches Gemini 4 Carbon: tops AA Index v5 at 59, runs for days
rseroter · x · 2026-10-29
Google released Gemini 4 Carbon just two weeks after Argon, claiming SOTA on cyber and long-horizon tasks and #1 on Artificial Analysis V5 (59 vs GPT-6 Astra's 57 and Claude Opus 5.5's 58).
- Key scores: SWE-sweep 9.6%, Terminal-Bench 4.0 65.2%, GraphWalks 96.2%, CWE-bench 71%, SEC-bench Pro 88.2%, Vending-Bench 2 bank balance $16,484
- Internal teams report Carbon runs for days, persisting through dead ends on multi-step engineering like root-causing and patching subtle bugs across large codebases
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