The Model Index
Models/Google

Gemini 3.5 Flash

GoogleClosed weightsFlagship

Gemini 3.5 Flash is a closed AI model from Google with an index score of 162 (GPT-4 = 100), rank 45 of 217.

162146–177Index score#45 of 217 models
$1.5/ $9.0Price per million tokensinput / output · via OpenRouter
1.05MContext windowtokens it reads at once
19 May 2026ReleasedReplaced by Gemini 3.6 Flash

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100Gemini 3.5 Flash

GPT-5.2 reached this score 5 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond (Epoch AI)
93%
Humanity's Last Exam
no result
Mathsevidence
FrontierMath (tiers 1-3)
63%
Codingevidence
SWE-bench Verified
79%
Terminal-Bench 4.0
6%
Agentsevidence
APEX-Agents
28%
Professional workevidence
Finance Agent (v2)
58%
Novel problemsevidence
ARC-AGI-2
72%
Long tasksno evidence yet
METR time horizon
no result

Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.

What others sayrank on 11 leaderboards

Best attop three among current models

Where to use itprices checked 18 Nov 2026

Host prices from OpenRouter; going direct can differ.

Facts and sources

Released19 May 2026
Announcementblog.google ↗
Release entryGemini 3.5 Flash (3.5 Pro announced; unreleased)
Scored asGemini 3.5 Flash
Output speed–
Hugging Faceclosed weights

Google releasesaround this one

This page as a chartDownload PNG