Multimedia Plan Execution (MV-I) on Multimedia Content Generation Evaluation Set
90Plan Execution Success RateGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o2026.01 | 90 | |
| GPT-4o-Mini2026.01 | 90 | |
| MultiMedia-AgentConfiguration=22026.01 | 90 | |
| Claude 3.5 Sonnet2026.01 | 85 | |
| MultiMedia-AgentConfiguration=32026.01 | 80 | |
| MultiMedia-AgentConfiguration=12026.01 | 70 |