List your company

Multimedia Plan Execution (IV-V) on Multimedia Content Generation Evaluation Set

1Plan Execution Success RateClaude 3.5 Sonnet
0.3760.5380.70.862Jan 6, 2026

Evaluation results

MethodLinks
Claude 3.5 Sonnet2026.011
GPT-4o2026.011
MultiMedia-AgentConfiguration=22026.011
GPT-4o-Mini2026.010.95
MultiMedia-AgentConfiguration=12026.010.8
MultiMedia-AgentConfiguration=32026.010.4