Rumored Gemini 4 Krypton spotted in Arena grey tests, nailing 20 art styles in one prompt
gaganghotra_ · x · 2026-11-15
Unverified community report: a model believed to be Gemini 4 Krypton has appeared in LMArena grey testing, generating the "pelican riding a bicycle" prompt across 20 art styles in one go — cave paintings, Egyptian murals, Song dynasty landscapes, pixel Mario, Win95, vaporwave, terminal code and more, with precise style adaptation. It follows the just-launched Gemini 4 Hydrogen, and some say Krypton's output rivals GPT's Fable 5.2. Model names and comparisons are community speculation, not confirmed by Google.
More from Models
- Vincent Conitzer Shares a Model's Structured Answer on Bias and Identification — conitzer · 2026-11-15
- Forecast Chart Projects GPT-7.5 by Oct 2027 and Claude 7 by Apr 2028 — flowersslop · 2026-11-15
- Codex Pro users petition OpenAI to let unused weekly usage roll over — InTeGeR78 · 2026-11-15
- "Phonebook-trained models can't write Shakespeare": data distribution beats any harness — gerardsans · 2026-11-15
- Harness skeptic: model training-data support drives performance, not the harness — gerardsans · 2026-11-15
- Security veteran: traditional tooling is obsolete, run an agentic hacker against your own systems — Kyrannio · 2026-11-15