Gemini 3.8 Flash full benchmarks: #16 intelligence, fastest at 305 tokens/s
ArtificialAnlys · x · 2026-09-02
Artificial Analysis published the full benchmark page for Gemini 3.8 Flash (high):
- Scores 59 on the Intelligence Index, ranking #16 of 195 models (median: 36)
- Ranks #1 in speed at 304.6 output tokens/s; 1M token context window
- Priced $0.75/$3.75, below class medians ($1.75/$10.00); generated 120M tokens across evals, notably verbose
- Supports text, image, speech, and video input
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