Skip to project content

Models Agents Image, Speech, Video ^Pending Architecture & Cases Leaderboards Research Cognition & Interaction

MODEL COMPARISON

MarioEval casebook · V3
76 conversations · 10 modelsMethod & definitions ↗

Cognition & Interaction

76 cases · 10 models

Loading recorded evaluations…

interactevalRecorded conversations. Case-level evidence.Methodology ↗

EVALUATION DETAIL

Search models and cases