List your company

Logical Reasoning on Countdown CD4

59.4Avg@16GPS
-1.02414.66330.3546.037Feb 2, 2026

Evaluation results

MethodLinks
GPSBackbone=Qwen3-8B, Finetuning=Yes, Runtime=5.0h2026.0259.4
DSBackbone=Qwen3-8B, Finetuning=Yes, Runtime=6.9h2026.0258.7
GPSBackbone=Qwen3-4B, Finetuning=Yes, Runtime=3.4h2026.0257.2
DSBackbone=Qwen3-4B, Finetuning=Yes, Runtime=4.9h2026.0256.1
MoPPSBackbone=Qwen3-8B, Finetuning=Yes, Runtime=4.3h2026.0255.5
GRESOBackbone=Qwen3-8B, Finetuning=Yes, Runtime=6.2h2026.0254.1
GRESOBackbone=Qwen3-4B, Finetuning=Yes, Runtime=4.9h2026.0253.8
PCLBackbone=Qwen3-8B, Finetuning=Yes, Runtime=5.1h2026.0253.5
MoPPSBackbone=Qwen3-4B, Finetuning=Yes, Runtime=2.8h2026.0252.9
UniformBackbone=Qwen3-8B, Finetuning=Yes, Runtime=4.3h2026.0252.5
UniformBackbone=Qwen3-4B, Finetuning=Yes, Runtime=2.9h2026.0251.1
PCLBackbone=Qwen3-4B, Finetuning=Yes, Runtime=3.2h2026.0251
Qwen3-8BBackbone=Qwen3-8B, Finetuning=None2026.022.1
Qwen3-4BBackbone=Qwen3-4B, Finetuning=None2026.021.3