Gemini 2.5 Pro and Gemini 2.5 Flash evaluation#91

Open

MyButtermilk wants to merge 3 commits intohuggingface:mainfrom

MyButtermilk:gemini-evaluation

Commits on Aug 20, 2025

Create the `run_gemini.sh` Execution Script: I have created the script to run both English and multilingual benchmarks for the Gemini models. The script also includes the logic to score the results…
google-labs-jules[bot]
committed

Commits on Aug 22, 2025

gemini: align eval with template/canary; standardize CLI flags; avoid torchcodec decode; load .env in run script

Alexander Immler
authored and
Alexander Immler
committed
gemini: docs + scripts cleanup; generic Python resolution, .env auto-load; updated README with full workflow

Alexander Immler
authored and
Alexander Immler
committed