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.

MiMo V2.6 FlashMiMo V2.6 Pro Add a modelChat with these 2

AttributeHide identical rows	MiMo V2.6 Flashxiaomi/mimo-v2.6-flash	MiMo V2.6 Proxiaomi/mimo-v2.6-pro
Specs
Context window	1M	1M
Max output	131K	131K
Input modalities	TextImageAudioVideo	TextImageAudioVideo
Output modalities	Text	Text
Capabilities
Streaming	Supported	Supported
Tool calling	Supported	Supported
Structured output (JSON)	Supported	Supported
Image input	Supported	Supported
Thinking mode	Supported	Supported
Price / 1M tokens
Input	$ 0.16	$ 0.47
Output	$ 0.32	$ 0.94
Cache read	$ 0.0040	$ 0.0050
Cache write	$ 0.16	$ 0.47
What it is good at
Best for	High-frequency professional workloads Coding agents Omni-modal understanding	Long-horizon coding agents Cybersecurity and scientific research Omni-modal agents
Published benchmarks
Terminal-Bench 2.1pass_rate	87.6%(setup not fully disclosed)	89.9%(setup not fully disclosed)
Terminal-Bench 4.0pass_rate	28.8%(setup not fully disclosed)	34.9%(setup not fully disclosed)
AutomationBench v1.0.6score	52.3%(setup not fully disclosed)	53.1%(setup not fully disclosed)
DeepSWE 1.1resolved_rate	67.9%(setup not fully disclosed)	71.9%(setup not fully disclosed)
ProgramBenchscore	26%(setup not fully disclosed)	26.5%(setup not fully disclosed)
OSWorld-Verifiedsuccess_rate	80.8%(setup not fully disclosed)	82%(setup not fully disclosed)
CyberGymscore	95.1%(setup not fully disclosed)	94%(setup not fully disclosed)
ExploitBenchscore	25.3%(setup not fully disclosed)	47.9%(setup not fully disclosed)
Toolathlon Verifiedpass_rate	73.6%(setup not fully disclosed)	76.9%(setup not fully disclosed)