Skip to content

Evaluation

LOFT (long-context retrieval)

LOFT long-context task at 128k context

Core capabilities Google DeepMind — Gemini

How it was run

Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.

Gemini 2.5
Google DeepMind — Gemini

rich detail 16 method fields published

See how this test was run