Gemini 3.6 Flash

ModelActive

by Google · family “gemini-flash”

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and... (description from the OpenRouter listing)

in: textin: imagein: videoin: filein: audioout: textReasoningTool useStructured output

Epoch Capabilities Index

154.4 #32 of 268

90% CI 152.7 – 156.3

Listing ↗

Released

21 Jul 2026

Context window

1.05M tokens

Max output

66K tokens

Input $ / 1M tokens

$0.75

Output $ / 1M tokens

$3.75

Cached input $ / 1M

$0.075

Each benchmark shown separately with its own source

Benchmark results (17)

All benchmarks

Benchmark	Domain	Score	vs best recorded	Setting	Run	Source
Furniture Assembly	multimodal	23.3% ±5.4	28%	high	10 Sep 2026	Epoch ↗
LMCA	agents	44.9%	69%	high	—	External ↗
DTBench	reasoning	95.5%	97%	high	—	External ↗
Mystery Game Puzzles	games	30.0% ±4.6	36%	high	5 Aug 2026	Epoch ↗
FrontierMath-Tiers-1-3-v2-Private	math	58.9% ±2.9	63%	high	2 Aug 2026	Eval log ↗
FrontierMath-Tier-4-v2-Private	math	22.0% ±6.5	22%	high	2 Aug 2026	Eval log ↗
FrontierCode	coding	34.4%	64%	unknown	—	External ↗
DeepSWE	coding	46.7%	63%	high	—	External ↗
ProofBench	math	36.0%	36%	unknown	—	External ↗
APEX-Agents	agents	46.9%	68%	unknown	—	External ↗
Chess Puzzles	games	43.0% ±5.0	60%	low	7 Aug 2026	Eval log ↗
SimpleQA Verified	knowledge	66.2% ±1.5	88%	high	27 Aug 2026	Eval log ↗
ARC-AGI-2	reasoning	60.4%	64%	high	—	External ↗
WeirdML	coding	56.1% ±0.0	60%	high	—	External ↗
OTIS Mock AIME 2024-2025	math	94.2% ±3.1	94%	high	2 Aug 2026	Epoch ↗
GPQA diamond	science	94.1% ±1.4	98%	high	2 Aug 2026	Epoch ↗
ARC-AGI	reasoning	91.2%	93%	high	—	External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

3 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.