← Models
Gemini 3.6 Flash
Google · proprietary · gemini-3.6-flash
Gemini 3.6 Flash is Google's workhorse multimodal reasoning model for agentic coding, knowledge work, and spatial reasoning. It supports text, image, video, audio, and PDF inputs, a 1 million-token context window, and a 65,536-token text output. It improves quality and token efficiency over Gemini 3.5 Flash.
Benchmark scores
| Benchmark | Score |
|---|---|
| CharXiv-R | 0.89 |
| OSWorld-Verified | 0.83 |
| Terminal-Bench 2.1 | 0.78 |
Pricing
- Google$1.50 / $7.50
Input / output per 1M tokens
AA metrics
No Artificial Analysis link yet.
Arena Elo
- No Arena snapshot linked.