Google launches Gemini 4 Hydrogen: 1M context, 2.5x faster, benchmark table vs Sonnet 5.5
Saboo_Shubham_ · x · 2026-11-13
- Google released Gemini 4 Hydrogen, claiming Sonnet 5.5 / GPT-6.1 Terra-level reasoning at 2.5x the speed of 3.8 Flash, with 1M context and native video/file support, plus a dynamic multi-model orchestrator in Antigravity with Carbon.
- Benchmark table highlights: SWE-sweep 13.5% (vs Sonnet 5.5's 3.1%), Agents' Last Exam v1.1 71.6%, AutomationBench-AA 76.1%, OSWorld-2.1 77.6%, HLE-Diamond 58.8% — leading on many fronts but trailing Sonnet 5.5 on Terminal-Bench 4.1 (57.0% vs 63.9%) and Terminal-Bench-Science.
Related event: Google Launches Gemini 4 Hydrogen Across All Products(62 posts)→
More from Models
- Microsoft diagnostic AI solves 83% of NEJM cases vs 36% for physicians — realmeetjames · 2026-11-13
- Opus 5.5 generates a full Blender 3D model in seconds, wows game developer — Scobleizer · 2026-11-13
- Claude's JavaScript art demo draws praise from threepointone: 'just remarkable' — threepointone · 2026-11-13
- Leaked UI shows unreleased Google models 'Hydrogen' and 'Argon' alongside Gemini tiers — Gauri_the_great · 2026-11-13
- DeepMind researcher: AI Overviews is the world's most-used AI model — cgarciae88 · 2026-11-13
- Tencent Hy4 Tops CWE-Bench-AA, Ranks #3 on Artificial Analysis Cyber Index — ArtificialAnlys · 2026-11-13