Gemini 4 Hydrogen Benchmarks Leak with 13.5% on SWE-sweep

Google DeepMind's Gemini 4 Hydrogen scored 13.5% on SWE-sweep, about 2.3x GPT-6.1 Terra, and 58.8% on HLE-Diamond. Early testers called it fun and fast, with many noting it far outperforms models in its size class.

2026-11-13 ~ 2026-11-13 · 3 related posts