List your company

Agent Performance on AgentInstruct HELD-IN

2.75HELD-INGPT-4
0.08760.77881.472.1612Mar 19, 2024

Evaluation results

MethodLinks
GPT-4Provider=OpenAI, Year=20232024.032.75
Agent-FLAN2024.032.01
AgentLM-7B2024.031.96
AgentTuningRe-implementation=true2024.031.89
GPT-3.5Provider=OpenAI, Year=20222024.031.59
Llama2-7B2024.030.19