Gemini 3.6 Flash
Gemini 3.6 Flash is a closed AI model from Google with an index score of 161 (GPT-4 = 100), rank 52 of 217.
161145–176Index score#52 of 217 models
$0.75/ $3.75Price per million tokensinput / output · via OpenRouter
1.05MContext windowtokens it reads at once
21 Jul 2026ReleasedReplaced by Gemini 3.7 Flash
Where it sitson the frontier
GPT-5.2 reached this score 7 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workevidence
Novel problemsevidence
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 11 leaderboards
The Model Indexthird-party tests, our method#52of 217 · 161
LMArena · Mathsmaths questions in chat#15of 346 · 1501LMArena · Creative writingcreative writing#16of 360 · 1471LMArena · Textoverall chat quality, judged by people#23of 362 · 1483LMArena · Instruction followingfollowing detailed instructions#31of 362 · 1473LMArena · Long promptslong, complex requests#34of 340 · 1485LMArena · Codingcoding questions in chat#36of 357 · 1518LMArena · Visionunderstanding images#23of 145 · 1280Epoch Capabilities Indexoverall capability from many benchmarks#44of 231 · 155.2LMArena · WebDevbuilding web apps and front ends#52of 133 · 1538LMArena · Documentsworking with long documents#20of 40 · 1456Best attop three among current models
Where to use itprices checked 18 Nov 2026
API providers 2 · per 1M tokens, in / out
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released21 Jul 2026
Announcementblog.google ↗
Release entryGemini 3.6 Flash + 3.5 Flash-Lite
Scored asGemini 3.6 Flash
Output speed–
Hugging Faceclosed weights