all the models — AI benchmark observatory
← Models

Gemini 2.5 Flash

Google · proprietary · gemini-2.5-flash

A thinking model designed for a balance between price and performance. It builds upon Gemini 2.0 Flash with upgraded reasoning, hybrid thinking control, multimodal capabilities (text, image, video, audio input), and a 1M token input context window.

AIME 2024GPQAMMMUAIME 2025SWE-Bench VeHumanity's L

Benchmark scores

Pricing

  • DeepInfra$0.30 / $2.50

Input / output per 1M tokens

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.