List your company

Mathematical Reasoning on Countdown-4

60.77AccuracyDS (Oracle)
38.56644.330550.09555.8595Mar 11, 2026

Evaluation results

MethodLinks
DS (Oracle)Backbone=Qwen2.5-7B, Rollouts=1006k, Finetuned=true2026.0360.77
DPSBackbone=Qwen2.5-7B, Rollouts=246k, Finetuned=true2026.0359.61
HRBackbone=Qwen2.5-7B, Rollouts=246k, Finetuned=true2026.0354.54
USBackbone=Qwen2.5-7B, Rollouts=246k, Finetuned=true2026.0353.27
DPSBackbone=Qwen2.5-3B, Rollouts=246k, Finetuned=true2026.0347.78
DS (Oracle)Backbone=Qwen2.5-3B, Rollouts=1141k, Finetuned=true2026.0347.67
HRBackbone=Qwen2.5-3B, Rollouts=246k, Finetuned=true2026.0342.1
USBackbone=Qwen2.5-3B, Rollouts=246k, Finetuned=true2026.0339.42