Leaked Gemini 3.8 Flash benchmarks claim wins over Opus 5 on Terminal Bench 2.1
kimmonismus · x · 2026-09-02
Blogger kimmonismus shared purported Gemini 3.8 Flash benchmarks showing it beating "Sol 5.6" and Opus 5 on Terminal Bench 2.1, HLE and more, declaring "Google is back." Unverified third-party leak; awaiting official confirmation.
More from Models
- Mocked benchmark shows DeepSeek's document chart grounding badly misaligned — burkov · 2026-10-18
- Dev complains Claude's habit of saying "not done" is his biggest pain point — jasonkneen · 2026-10-18
- Open-weight TYGER speech decision model makes 80ms turn-taking calls for full-duplex voice agents — solyarisoftware · 2026-10-18
- Paying Google AI subscriber blocked: custom-domain Workspace accounts can't access AI Studio — ChrisRackauckas · 2026-10-18
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- Users press OpenAI on long-delayed Adult Mode a year after it was promised — ___Patrice___ · 2026-10-18