List your company

Multimedia Plan Execution (MI-T) on Multimedia Content Generation Evaluation Set

100Plan Execution Success RateClaude 3.5 Sonnet
79.284.69095.4Jan 6, 2026

Evaluation results

MethodLinks
Claude 3.5 Sonnet2026.01100
GPT-4o2026.01100
MultiMedia-AgentConfiguration=22026.01100
GPT-4o-Mini2026.0195
MultiMedia-AgentConfiguration=32026.0190
MultiMedia-AgentConfiguration=12026.0180