Gemini 4 Carbon benchmarks leak: tops agentic, math and security boards
zacharynado · x · 2026-10-29
The attached comparison chart shows Gemini 4 Carbon leading Gemini 4 Argon, GPT-6 Astra and Claude Opus 5.5/Fable 5.1 on most boards: SWE-sweep 9.6%, Terminal-Bench 4.0 65.2%, AutomationBench 53.9%, GraphWalks long-context 96.2%, RiemannBench 80.0%, plus cybersecurity wins on CWE-bench and ExploitGym. It trails only on FrontierSWE 2 (GPT-6 Astra 65.5%) and OSWorld-2.1 offline (Claude 87.2%). The post itself is a joking jab at Gemini's pricing, with the benchmark table as the real payload.
Related event: Google Launches Gemini 4 Carbon, Topping the Artificial Analysis Index(87 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