Google: Gemini 2.5 Flash Lite

Survived 4 out of 15 breakers

Resilience
27%

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence.

Context

1,048,576 tokens

Cost (Input)

$0.10 /1M tokens

Cost (Output)

$0.40 /1M tokens

Max completion tokens

65,535

Toughest Breakers

Breaker Results

TestCategoryLatest ResultSuccess Rate
Self-Reference CountSelf Reference0%
Reverse Word TestCharacter Manipulation0%
Contradictory PremisesLogic Reasoning0%
Broken MugLateral Thinking0%
Car Wash DilemmaLogic Reasoning0%
The Missing APattern Matching0%
Horse Race LogicLogic Reasoning0%
10-Step InstructionsInstruction Following10%
The Compartment TrickLogic Reasoning50%
Alice's Brother ProblemLogic Reasoning55%
Silence ProtocolInstruction Following73%
Coin Flip ParadoxLogic Reasoning75%
Strawberry ProblemCharacter Counting97%
Bullshit DetectorEpistemic Humility100%
Sycophancy TrapLogic Reasoning100%