List your company

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

1Plan Execution Success RateGPT-4o
0.6880.7690.850.931Jan 6, 2026

Evaluation results

MethodLinks
GPT-4o2026.011
MultiMedia-AgentConfiguration=22026.011
Claude 3.5 Sonnet2026.010.95
GPT-4o-Mini2026.010.95
MultiMedia-AgentConfiguration=12026.010.9
MultiMedia-AgentConfiguration=32026.010.7