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
- Gemini 4 Hydrogen bench table: leads on HLE-Diamond and agent evals, trails Claude Sonnet 5.5 on some — fofrAI · 2026-11-13
- Gemini 4 Hydrogen scores 13.5% on SWE-sweep, 2.3x GPT-6.1 Terra, but leads unevenly — ChrisGPT · 2026-11-13
- Gemini 4 Hydrogen posts 13.5% on SWE-sweep, an standout result for a small-class model — marktenenholtz · 2026-11-13