Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CRAD

Benchmarks

Task NameDataset NameSOTA ResultTrend
NegotiationCRAD
Success Rate100
22
NegotiationCRAD Debt
Success Rate100
14
NegotiationCRAD (test)
Success Rate100
7
Emotional NegotiationCRAD Qwen2.5-3B-Instruct counterparty
Success Rate85
4
Emotional NegotiationCRAD ChatGPT-4o-mini counterparty
Success Rate95
4
Emotional NegotiationCRAD DeepSeek-V3 counterparty
Success Rate100
4
Showing 6 of 6 rows