Agent Performance on AgentInstruct HELD-IN
2.75HELD-INGPT-4
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4Provider=OpenAI, Year=20232024.03 | 2.75 | |
| Agent-FLAN2024.03 | 2.01 | |
| AgentLM-7B2024.03 | 1.96 | |
| AgentTuningRe-implementation=true2024.03 | 1.89 | |
| GPT-3.5Provider=OpenAI, Year=20222024.03 | 1.59 | |
| Llama2-7B2024.03 | 0.19 |