List your company

Question Answering on Pacific (dev)

65.24RewardSGP-Oracle
-24.8552-1.465121.92545.3151Dec 3, 2025

Evaluation results

MethodLinks
SGP-Oraclebase_model=Gemma-2-9b, averaging=averaged across rollouts2025.1265.2473.8943.4614.05
SGPbase_model=Gemma-2-9b, averaging=averaged across rollouts2025.1254.3265.7342.8614.6
Clarifybase_model=Gemma-2-9b, averaging=averaged across rollouts2025.1245.4862.71000
Answerbase_model=Gemma-2-9b, averaging=averaged across rollouts2025.1242.4452.2500
Prompted-COTbase_model=Gemma-2-9b, averaging=averaged across rollouts2025.123350.0416.4516.17
Promptedbase_model=Gemma-2-9b, averaging=averaged across rollouts2025.1211.4655.2817.9947.18
Clarify-and-MAbase_model=Gemma-2-9b, averaging=averaged across rollouts2025.12-16.1856.66100100
Multi-answer (MA)base_model=Gemma-2-9b, averaging=averaged across rollouts2025.12-21.3954.630100