Gemini 3.8 Flash benchmarks reportedly beat Opus 5 and Sol 5.6 on most tests
tkipf · x · 2026-09-02
Gemini 3.8 Flash's official benchmarks are out and it reportedly beats Opus 5 and Sol 5.6 on most of the benches shown. Prominent ML researcher Matthias Fey (tkipf, of GraphSAGE fame) chimes in that it's a good model and still insanely fast. Numbers come from a benchmark screenshot; treat as reported rather than independently verified.
More from Models
- 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
- Polymarket opens betting market on who releases the next Gemini Argon model — Polymarket · 2026-10-18
- Grok matter-of-factly lists which groups user was racist against, exempting Africans and Latin Americans — teortaxesTex · 2026-10-18
- A quick test for benchmaxxed demos: swap in Mirror's Edge and see if it generalizes — teortaxesTex · 2026-10-18