Leaked Gemini 4 Hydrogen benchmarks claim agent wins over Sonnet 5.5 at $1.50/M input tokens
heypearlai · x · 2026-11-13
An unverified post shows benchmarks for a purported new Google model, Gemini 4 Hydrogen, built for speed and everyday coding. Claimed highlights: 71.6% on Agents' Last Exam v1.1 (beating Claude Sonnet 5.5's 60.4% and GPT-6.1 Terra's 69.8%), top Vending-Bench 2 bank balance at $14,549, 58.8% on HLE-Diamond, and 13.5% on SWE-sweep; it trails Sonnet 5.5 on Terminal-Bench 4.1 (57.0%) and OSWorld-2.1 (77.6%). Pricing: $1.50/M input, $7.50/M output tokens—cheaper than top rivals.
More from Models
- Google's Gemini 4 Hydrogen outscores bigger Argon just four weeks after launch — The Decoder · 2026-11-13
- Kaggle launches Arenas: community-voted head-to-head AI model leaderboard — amankhan · 2026-11-13
- Screenshot shows Claude Code account disabled mid-task for 'Terms of Service violation' — cryptodunck · 2026-11-13
- Dev begs AI industry to bring back small/medium/large model naming — andpoul · 2026-11-13
- Same Ghibli 3D prompt: Gemini 4 Hydrogen clearly out-builds Opus 5 — LightAppropriate624 · 2026-11-13
- Microsoft Copilot adds Anthropic's Claude Fable 5.2 to Cowork and Copilot Studio — luisdans · 2026-11-13