[KongchangAI]
Model

Gemini 3.5 Flash Lite

A lightweight, fast model in the Google Gemini series, intended for low-latency, high-throughput inference tasks.

Timeline (last 90 days)

Oct 19

The experiment was based on 15 research papers, 18 evaluation questions, and a retrieval setting of k=8; the generator used gpt-oss-20b on Groq, the judge was Gemini 3.5 Flash Lite, and the four metrics were computed via RAGAS 0.2.15.

Unverified50%

All Facts (1)

Unverified

The experiment was based on 15 research papers, 18 evaluation questions, and a retrieval setting of k=8; the generator used gpt-oss-20b on Groq, the judge was Gemini 3.5 Flash Lite, and the four metrics were computed via RAGAS 0.2.15.

50%

Source Articles

Gemini API Pricing Overview: Cost per Million Tokens Across 11 ModelsOct 19Where Does RAG Evaluation Noise Come From? The Judge or the Generator?Oct 19