List your company

Multimedia Plan Execution (MA-I) on Multimedia Content Generation Evaluation Set

100Plan Execution Success RateGPT-4o
89.692.39597.7Jan 6, 2026

Evaluation results

MethodLinks
GPT-4o2026.01100
MultiMedia-AgentConfiguration=22026.01100
Claude 3.5 Sonnet2026.0195
GPT-4o-Mini2026.0190
MultiMedia-AgentConfiguration=12026.0190
MultiMedia-AgentConfiguration=32026.0190