Gemini 4 Carbon Debuts #1 on Text Arena, #2 on Agent Arena, 72% Cheaper Than Claude Opus 5.5
altryne · x · 2026-10-29
LMArena announced that Google DeepMind's Gemini 4 Carbon (High) debuted at #1 on Text Arena, #2 on Agent Arena, and #4 on WebDev Code Arena, reshaping the Pareto frontier across all three.
Key numbers:
- +16.2% net improvement on Agent Arena across 21.9K real-world agentic sessions, surpassing GPT-6 Astra and Fable-5.1
- $1.80 median cost per task — 72% cheaper than #1-ranked Claude Opus 5.5 (Max)
- #1 in Steerability (+18.6%)
Reposter petergostev, who used Carbon before release, says it feels far better than Argon and hopes Google keeps up the release pace.
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