Model

Gemini 2.5 Flash Preview 04-17

Google

deepmind.google

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
HLE12.1accuracyN/AIndependentlowepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
Aider Polyglot47.1percent_correctN/AIndependentmediumaider.chat

Multimodal

Multimodal
BenchmarkScoreMetricHarnessSourceConfidenceLink
GeoBench73.0acw_country_%N/AIndependentmediumgeobench.org

Reproduced by the community

Loading community runs…