Gemini 3.8 Flash scores 59 on AA Index, cheapest model at its intelligence at $0.58 per task
ArtificialAnlys · x · 2026-09-02
Artificial Analysis benchmarks Gemini 3.8 Flash, Google's fourth Flash model in under four months:
- Scores 59 on the AA Intelligence Index (high reasoning), up 3 points from 3.7 Flash, matching GPT-5.6 Sol (xhigh) and Grok 4.6 (medium)
- Keeps 3.7 Flash discounted pricing ($0.75/$3.75 per M tokens) through year-end; $0.58 per task, cheapest at its intelligence level but 40% costlier than its predecessor due to 30% more output tokens (48k avg) and more agentic turns
- Gains driven by agentic evals: +12 points on 𝜏³-Banking to 45%
- 300 tok/s, 2.5 min per task (high reasoning); 0.8 min on low reasoning
- 1M context, text/image/video/speech 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