National Policy Generation (test)
29Count AgreeMegaAgent
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MegaAgentModel=o1-mini, Policy Count=312024.08 | 29 | 2 | 0 | |
| MegaAgentModel=o1-preview, Policy Count=312024.08 | 29 | 1 | 1 | |
| MegaAgentModel=gpt-4o-mini, Policy Count=312024.08 | 28 | 0 | 3 | |
| MegaAgentModel=Claude-3.5, Policy Count=312024.08 | 26 | 1 | 4 | |
| MegaAgentModel=gpt-4o, Policy Count=312024.08 | 25 | 2 | 4 | |
| CAMELModel=Claude-3.5, Policy Count=122024.08 | 4 | 8 | 1 | |
| CAMELModel=gpt-4o-mini, Policy Count=122024.08 | 3 | 7 | 2 | |
| CAMELModel=o1-mini, Policy Count=122024.08 | 3 | 8 | 1 | |
| CAMELModel=o1-preview, Policy Count=122024.08 | 3 | 8 | 1 | |
| AgentVerseModel=gpt-4o-mini, Policy Count=132024.08 | 3 | 10 | 0 | |
| CAMELModel=gpt-4o, Policy Count=122024.08 | 2 | 10 | 0 | |
| AgentVerseModel=Claude-3.5, Policy Count=132024.08 | 2 | 10 | 1 | |
| AgentVerseModel=gpt-4o, Policy Count=132024.08 | 2 | 9 | 2 | |
| AgentVerseModel=o1-mini, Policy Count=132024.08 | 2 | 9 | 2 | |
| AgentVerseModel=o1-preview, Policy Count=132024.08 | 2 | 10 | 1 | |
| AutoGenModel=Claude-3.5, Policy Count=52024.08 | 0 | 5 | 0 | |
| AutoGenModel=gpt-4o-mini, Policy Count=52024.08 | 0 | 4 | 1 | |
| AutoGenModel=gpt-4o, Policy Count=52024.08 | 0 | 5 | 0 | |
| AutoGenModel=o1-mini, Policy Count=52024.08 | 0 | 4 | 1 | |
| AutoGenModel=o1-preview, Policy Count=52024.08 | 0 | 5 | 0 |