Workflow Orchestration on Video
93Success RateVideoAgent
Evaluation Results
| Method | Links | |
|---|---|---|
| VideoAgentBackbone=Claude-Sonnet-3.72026.06 | 93 | |
| VideoAgentBackbone=Deepseek-v32026.06 | 89 | |
| VideoAgentBackbone=GPT-4o2026.06 | 88 | |
| VideoAgentBackbone=Claude-Sonnet-42026.06 | 87 | |
| GPTSwarmBackbone=Claude-Sonnet-3.72026.06 | 86 | |
| Intelligent Go-ExploreBackbone=GPT-4o2026.06 | 86 | |
| Step BackBackbone=Claude-Sonnet-42026.06 | 85 | |
| GraphCounselorBackbone=GPT-4o2026.06 | 84 | |
| GraphCounselorBackbone=Deepseek-v32026.06 | 84 | |
| GPTSwarmBackbone=Claude-Sonnet-42026.06 | 83 | |
| FlowBackbone=Claude-Sonnet-3.72026.06 | 83 | |
| GraphCounselorBackbone=Claude-Sonnet-42026.06 | 82 | |
| GraphCounselorBackbone=Claude-Sonnet-3.72026.06 | 81 | |
| GPTSwarmBackbone=Deepseek-v32026.06 | 81 | |
| GPTSwarmBackbone=GPT-4o2026.06 | 80 | |
| CoTBackbone=Claude-Sonnet-42026.06 | 77 | |
| Step BackBackbone=Claude-Sonnet-3.72026.06 | 77 | |
| ExpertPromptingBackbone=Claude-Sonnet-42026.06 | 76 | |
| Intelligent Go-ExploreBackbone=Claude-Sonnet-3.72026.06 | 75 | |
| ExpertPromptingBackbone=Claude-Sonnet-3.72026.06 | 73 | |
| CoTBackbone=Claude-Sonnet-3.72026.06 | 72 | |
| Step BackBackbone=Deepseek-v32026.06 | 70 | |
| ExpertPromptingBackbone=Deepseek-v32026.06 | 70 | |
| DebateBackbone=GPT-4o2026.06 | 69 | |
| ExpertPromptingBackbone=GPT-4o2026.06 | 68 | |
| DebateBackbone=Claude-Sonnet-3.72026.06 | 66 | |
| CoTBackbone=GPT-4o2026.06 | 65 | |
| CoTBackbone=Deepseek-v32026.06 | 65 | |
| FlowBackbone=Claude-Sonnet-42026.06 | 64 | |
| Intelligent Go-ExploreBackbone=Claude-Sonnet-42026.06 | 63 | |
| FlowBackbone=Deepseek-v32026.06 | 61 | |
| FlowBackbone=GPT-4o2026.06 | 60 | |
| Intelligent Go-ExploreBackbone=Deepseek-v32026.06 | 53 | |
| DebateBackbone=Claude-Sonnet-42026.06 | 52 | |
| DebateBackbone=Deepseek-v32026.06 | 50 | |
| Step BackBackbone=GPT-4o2026.06 | 38 |