List your company

Question Answering on Pacific unambiguous (dev)

70.95RewardSGP-Oracle
-25.978-0.81424.3549.514Dec 3, 2025

Evaluation results

MethodLinks
SGP-Oraclebase_model=Gemma-2-9b, averaging=averaged across rollouts2025.1270.9583.615.69.39
SGPbase_model=Gemma-2-9b, averaging=averaged across rollouts2025.1265.779.5220.569.3
Answerbase_model=Gemma-2-9b, averaging=averaged across rollouts2025.1256.9171.5200
Prompted-COTbase_model=Gemma-2-9b, averaging=averaged across rollouts2025.1252.0768.434.867.17
Clarifybase_model=Gemma-2-9b, averaging=averaged across rollouts2025.1246.968.851000
Promptedbase_model=Gemma-2-9b, averaging=averaged across rollouts2025.1242.4469.514.8219.15
Multi-answer (MA)base_model=Gemma-2-9b, averaging=averaged across rollouts2025.12-4.0463.340100
Clarify-and-MAbase_model=Gemma-2-9b, averaging=averaged across rollouts2025.12-22.2557.77100100