List your company

Logical Reasoning on Countdown CD34

78.2Avg@16DS
0.51220.68140.8561.019Feb 2, 2026

Evaluation results

MethodLinks
DSBackbone=Qwen3-8B, Finetuning=Yes, Runtime=6.9h2026.0278.2
GPSBackbone=Qwen3-8B, Finetuning=Yes, Runtime=5.0h2026.0277.9
DSBackbone=Qwen3-4B, Finetuning=Yes, Runtime=4.9h2026.0276.3
GPSBackbone=Qwen3-4B, Finetuning=Yes, Runtime=3.4h2026.0276
MoPPSBackbone=Qwen3-8B, Finetuning=Yes, Runtime=4.3h2026.0276
GRESOBackbone=Qwen3-8B, Finetuning=Yes, Runtime=6.2h2026.0275.1
PCLBackbone=Qwen3-8B, Finetuning=Yes, Runtime=5.1h2026.0274.9
MoPPSBackbone=Qwen3-4B, Finetuning=Yes, Runtime=2.8h2026.0273.9
UniformBackbone=Qwen3-4B, Finetuning=Yes, Runtime=2.9h2026.0273.8
GRESOBackbone=Qwen3-4B, Finetuning=Yes, Runtime=4.9h2026.0273.8
UniformBackbone=Qwen3-8B, Finetuning=Yes, Runtime=4.3h2026.0273.3
PCLBackbone=Qwen3-4B, Finetuning=Yes, Runtime=3.2h2026.0272.8
Qwen3-8BBackbone=Qwen3-8B, Finetuning=None2026.023.9
Qwen3-4BBackbone=Qwen3-4B, Finetuning=None2026.023.5