Llama 1
Meta
partial detail 9 method fields published
Evaluation
WinoGender
Winogender benchmark measuring representational harm (bias or toxicity) in text-to-text outputs
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 1.0
Google DeepMind — Gemini
rich detail 7 method fields published