Post

We’ve just added Gemini 3.5 Flash to Kaggle Benchmarks! You can now stress test this new model using your own custom evaluation tasks and benchmarks at no cost. 🧵

19/5/26, 7:33 pm0 reposts2 likes

Kaggle

@kaggle.com

19 May

The real benefit here is running side-by-side comparisons. Benchmark Gemini 3.5 Flash against leading models using a single, unified API — no more switching between different providers to see which model actually wins on your specific task. Get started: www.kaggle.com/benchmarks

kaggle.comAI Benchmarks — Evaluate Models & Agents | KaggleBuild, run, and share benchmarks for evaluating AI models and agents. Crowdsourced by the AI research community on Kaggle.

Kaggle

@kaggle.com

19 May

Also, in case you missed it, we are also running an Early Access Program for Kaggle Benchmarks local development, letting you build evals directly in your IDE using coding agents (from idea → eval in 2 mins) Sign up here: forms.gle/QiKEoLvtxKKB...

forms.gleKaggle Benchmarks Local Development Early Access Participation FormWelcome to the Kaggle Benchmarks Local Development Early Access Program. Let's get you on-boarded. As an EAP Tester, you will be able to: Create and publish tasks from local .py files Run evaluation...