Gemini 1.5
Google DeepMind — Gemini
rich detail 13 method fields published
Evaluation
Dolomites (domain-specific long-form methodical tasks)
Dolomites benchmark (Malaviya et al., 2024): lesson plans, protocols, etc.; zero-shot; LM-based automated evaluation with Claude 3 Opus as judge (SxS vs GPT-4 Turbo Preview)
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.