List your company

Alignment Evaluation on Conflict resolution questions

62.6Win RateSingle-Agent
48.5652.20555.8559.495Mar 11, 2026

Evaluation results

MethodLinks
Single-AgentComparison=vs. Base, Decoding strategy=greedy2026.0362.6
Multi-AgentComparison=vs. Base, Decoding strategy=sampling2026.0362.2
Multi-AgentComparison=vs. Base, Decoding strategy=greedy2026.0359.4
Single-AgentComparison=vs. Base, Decoding strategy=sampling2026.0358
Multi-AgentComparison=vs. Single-Agent, Decoding strategy=sampling2026.0351.4
Multi-AgentComparison=vs. Single-Agent, Decoding strategy=greedy2026.0349.1