Compare models

Context, limits, capabilities, price and use cases side by side — up to 4 models at a time. The URL holds your selection, so you can share it.

Gemini 3.5 FlashGemini 3.6 FlashGemini 3.5 Flash Lite Add a modelChat with these 3

AttributeHide identical rows	Gemini 3.5 Flashgemini/gemini-3.5-flash	Gemini 3.6 Flashgemini/gemini-3.6-flash	Gemini 3.5 Flash Litegemini/gemini-3.5-flash-lite
Specs
Context window	1M	1M	1M
Max output	66K	66K	66K
Input modalities	TextImageAudioVideo	TextImageAudioVideo	TextImageAudioVideo
Output modalities	Text	Text	Text
Capabilities
Streaming	Supported	Supported	Supported
Tool calling	Supported	Supported	Supported
Structured output (JSON)	Supported	Supported	Supported
Image input	Supported	Supported	Supported
Thinking mode	Supported	Supported	Supported
Price / 1M tokens
Input	$ 1.50	$ 1.50	$ 0.30
Output	$ 9.00	$ 7.50	$ 2.50
Cache read	$ 0.15	$ 0.15	$ 0.030
Cache write	$ 1.50	$ 1.50	$ 0.30
What it is good at
Best for	Long-running coding agents Complex multimodal reasoning	Rapid agentic coding loops Efficient knowledge work Spatial and multimodal reasoning	Subagents and automation Document parsing
Published benchmarks
Terminal-Bench 2.1pass_rate	76.2%Terminus 2(setup not fully disclosed)	78%Terminus 2(setup not fully disclosed)	54%Terminus 2(setup not fully disclosed)
SWE-Bench Pro (Public)pass_ratesetups differ by: pass_k	55.1%(setup not fully disclosed)	58.7%(setup not fully disclosed)	54.2%(setup not fully disclosed)
OSWorld-Verifiedsuccess_rate	78.4%(setup not fully disclosed)	83%(setup not fully disclosed)	74%(setup not fully disclosed)
GDPval-AA v2elo	—	1421(setup not fully disclosed)	1140(setup not fully disclosed)
CharXiv Reasoning (no tools)accuracy	—	85.2%(setup not fully disclosed)	74.5%(setup not fully disclosed)
MMMU Pro (no tools)accuracy	83.6%(setup not fully disclosed)	—	—
MCP Atlas Publicscore	83.6%(setup not fully disclosed)	—	—