Alleged Gemini 4 Hydrogen benchmark table leaks, pitted against Claude Sonnet 5.5
ColbyHawker · x · 2026-11-13
An X account posted what appears to be an unverified benchmark table for "Gemini 4 Hydrogen", compared against Claude Sonnet 5.5 and GPT-6.1 Terra, with a deepmind.google methodology link. The model has not been officially announced, so treat as rumor.
Claimed wins for Gemini 4 Hydrogen: SWE-sweep 13.5%, Agents' Last Exam v1.1 71.6%, AutomationBench-AA 76.1%, Vending-Bench 2 ($14,549), MKA 53.4%, Chartography 66.6%, HLE-Diamond 58.8%. Losses: Terminal-Bench 4.1 (57.0% vs Claude's 63.9%), OSWorld-2.1 (77.6% vs 83.9%), Terminal-Bench-Science 0.1 (51.4% vs 59.9%).
More from Models
- Unverified claim: hidden GPU fingerprints show top Chinese labs trained on banned Blackwell chips — cis_female · 2026-11-13
- Chinese major models reportedly trained on Blackwell-class chips, though scale disappoints — teortaxesTex · 2026-11-13
- One user burned $4,988 of API-priced tokens on a $200 Claude subscription last month — jonathan_wilke · 2026-11-13
- Gemini 4 Hydrogen tops Google models on AA-Robotics v0.1, ranking fourth overall — ArtificialAnlys · 2026-11-13
- 4,689-trial agent test: DeepSeek V4 argues its way into failures, Gemini 3.8 Flash fails silently — Kindly-Bag763 · 2026-11-13
- Analyst: DeepSeek V4's Flash variant is winning, and a hyper-efficient 2B V5 could be the real play — teortaxesTex · 2026-11-13