List your company

Dialogue Agent Interaction on DEMO

8.447Goal AchievementQwen2-72B-Instruct
4.637485.626496.61557.60451Dec 6, 2024

Evaluation results

MethodLinks
Qwen2-72B-InstructModel Category=Open-sourced LLM, Temperature=12024.128.4479.2048.6998.1758.6316.608
GPT-4oModel Category=Proprietary LLM, Temperature=12024.128.199.1818.6148.5378.6316.793
Claude-3.5-SonnetModel Category=Proprietary LLM, Temperature=12024.127.5719.1748.4328.848.5046.599
GPT-4o-miniModel Category=Proprietary LLM, Temperature=12024.127.5519.0828.3168.1638.2786.449
DEMO-Qwen2-7BModel Category=DEMO Agent, Backbone=Qwen2-7B-Instruct, Temperature=12024.127.458.8648.0737.8648.0636.625
Claude-3.5-HaikuModel Category=Proprietary LLM, Temperature=12024.127.3619.1158.4027.9688.2126.358
Qwen2-72B-InstructModel Category=Open-sourced LLM, Evaluator=Gemini-1.5-Pro2024.127.3356.2136.9675.4046.482—
Llama-3.1-70B-InstructModel Category=Open-sourced LLM, Temperature=12024.127.2237.9147.2226.7537.2786.154
GPT-4oModel Category=Proprietary LLM, Evaluator=Gemini-1.5-Pro2024.127.2157.0327.9426.3287.132—
DEMO-Llama3.1-8BModel Category=DEMO Agent, Backbone=Llama3.1-8B-Instruct, Temperature=12024.126.9457.6887.0156.3787.7076.341
Qwen2-7B-InstructModel Category=Backbone LLM, Temperature=12024.126.6988.1126.8956.2786.9965.828
Claude-3.5-SonnetModel Category=Proprietary LLM, Evaluator=Gemini-1.5-Pro2024.126.557.2847.6646.5267.006—
DEMO-Qwen2-7BModel Category=DEMO Agent, Evaluator=Gemini-1.5-Pro2024.126.3066.28775.5866.296—
Llama-3.1-70B-InstructModel Category=Open-sourced LLM, Evaluator=Gemini-1.5-Pro2024.126.255.1635.8984.4615.45—
GPT-4o-miniModel Category=Proprietary LLM, Evaluator=Gemini-1.5-Pro2024.126.1596.677.2345.9446.503—
Claude-3.5-HaikuModel Category=Proprietary LLM, Evaluator=Gemini-1.5-Pro2024.126.0496.7197.2685.7426.446—
DEMO-Llama3.1-8BModel Category=DEMO Agent, Evaluator=Gemini-1.5-Pro2024.125.8594.8145.5493.9485.051—
Llama3.1-8B-InstructModel Category=Backbone LLM, Temperature=12024.125.8316.1665.5194.9745.6235.335
Qwen2-7B-InstructModel Category=Backbone LLM, Evaluator=Gemini-1.5-Pro2024.125.5285.2745.0434.2095.018—
Llama3.1-8B-InstructModel Category=Backbone LLM, Evaluator=Gemini-1.5-Pro2024.124.7844.1954.5363.5734.274—