CG-AL-M029

medium Pages, Reports & UI content c01bfc2ee677…

Description

Per-model results

Models that have attempted this task
ModelAttempt 1Attempt 2Avg scoreRuns
Claude Fable 550.0 / 1003
Claude Haiku 4 5 2025100150.0 / 1003
Claude Opus 4.650.0 / 1003
Claude Opus 4.750.0 / 1006
Claude Sonnet 4 650.0 / 1006
GPT-5.550.0 / 1003
Claude Opus 4.841.7 / 1006
Gemini 3.5 Flash25.0 / 1006
Gemini 3.1 Pro Preview16.7 / 1003