List your company

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

75Plan Execution Success RateClaude 3.5 Sonnet
38.648.0557.566.95Jan 6, 2026

Evaluation results

MethodLinks
Claude 3.5 Sonnet2026.0175
GPT-4o2026.0170
MultiMedia-AgentConfiguration=22026.0170
GPT-4o-Mini2026.0165
MultiMedia-AgentConfiguration=12026.0150
MultiMedia-AgentConfiguration=32026.0140