Gemini 3.8 Flash outputs 48k tokens per task on high reasoning, 30% more than predecessor
ArtificialAnlys · x · 2026-09-02
Artificial Analysis notes Gemini 3.8 Flash averages 48k output tokens per task on high reasoning, up 30% from 3.7 Flash, at 300 tok/s; Time per Task rises from 2.2 to 2.5 minutes, behind Claude Fable 5.1 (2.1 min). Low reasoning outputs 14k tokens per task in 0.8 minutes.
Related event: Google Launches Gemini 3.8 Flash and Cyber Variant(110 posts)→
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