Multimedia Plan Execution (MA-V) on Multimedia Content Generation Evaluation Set
65Plan Execution Success RateClaude 3.5 Sonnet
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude 3.5 Sonnet2026.01 | 65 | |
| GPT-4o2026.01 | 60 | |
| GPT-4o-Mini2026.01 | 55 | |
| MultiMedia-AgentConfiguration=22026.01 | 40 | |
| MultiMedia-AgentConfiguration=32026.01 | 30 | |
| MultiMedia-AgentConfiguration=12026.01 | 10 |