Side-by-side: suspected Gemini 4 Pro vs Gemini 3.8 Flash in LMArena
CodeByPoonam · x · 2026-09-18
Users report LMArena is routing "gemini-3.8-flash" traffic to a new Gemini Pro mode. A same-prompt side-by-side comparison shows the new mode outputting noticeably better results, supporting speculation that 3.8 Flash is actually a stealth Gemini 4 Pro test. Google hasn't confirmed.
Related event: Suspected Gemini 4 Pro Surfaces Anonymously on LMArena as '3.8 Flash'(13 posts)→
More from Models
- Mistral Large 4 tested on real Django CVE: 133 agents find, prove and patch the bug — MistralAI · 2026-11-04
- Google and Mercor's PLE benchmark: all frontier agents score below 50% on 85 real engineering tasks — teortaxesTex · 2026-11-04
- ValsAI: 4 of 7 frontier models keep 80%+ performance at lowest reasoning effort for half the cost — AccBalanced · 2026-11-04
- Daily AI brief: Tencent launches Hy4 with computer use, Apple opens Siri AI to all devs — testingcatalog · 2026-11-04
- WIP 'DiffusionGearvis' Project Uses DiffusionGemma to Speed Up and Privatize Computer-Use Agents — qberthet · 2026-11-04
- Musk cites unsustainable Grok Bot costs as Hermes offers one-command agent migration — Teknium · 2026-11-04