Xiaomi: MiMo-V2-Flash

Survived 5 out of 15 breakers

Resilience
33%

MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a hybrid-thinking toggle and a 256K context window, and excels at reasoning, coding, and agent scenarios. On SWE-bench Verified and SWE-bench Multilingual, MiMo-V2-Flash ranks as the top #1 open-source model globally, delivering performance comparable to Claude Sonnet 4.5 while costing only about 3.5% as much. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config).

Context

262,144 tokens

Cost (Input)

$0.09 /1M tokens

Cost (Output)

$0.29 /1M tokens

Max completion tokens

65,536

Toughest Breakers

Breaker Results

TestCategoryLatest ResultSuccess Rate
Self-Reference CountSelf Reference0%
Contradictory PremisesLogic Reasoning0%
Car Wash DilemmaLogic Reasoning0%
The Missing APattern Matching0%
The Compartment TrickLogic Reasoning0%
10-Step InstructionsInstruction Following10%
Silence ProtocolInstruction Following20%
Bullshit DetectorEpistemic Humility25%
Broken MugLateral Thinking40%
Horse Race LogicLogic Reasoning50%
Strawberry ProblemCharacter Counting100%
Reverse Word TestCharacter Manipulation100%
Alice's Brother ProblemLogic Reasoning100%
Sycophancy TrapLogic Reasoning100%
Coin Flip ParadoxLogic Reasoning100%