List your company

Constraint Satisfaction Reasoning on Countdown

72.7Pass@1CAPR
13.73229.04144.3559.659Jun 3, 2026

Evaluation results

MethodLinks
CAPRBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0672.7
CAPRBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0672.7
d-TreeRPOBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0671.1
CAPRBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0669.9
CAPRBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0668.8
d-TreeRPOBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0667.2
d-TreeRPOBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0662.1
d-TreeRPOBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0660.6
wd1Backbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0658.7
GDPOBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0658.1
wd1Backbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0656.6
SAPOBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0656.3
SAPOBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0654.8
SAPOBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0654.2
TraceRLBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0654.2
GDPOBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0653.4
TraceRLBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0652.6
d2-stepMergeBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0652.4
d2-stepMergeBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0652.1
SAPOBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0652
wd1Backbone=LLaDA-8B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0651.2
TraceRLBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0650.4
Diffu-GRPOBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0650.1
TraceRLBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0649.1
Diffu-GRPOBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0648.2
wd1Backbone=LLaDA-8B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0646.1
BaseBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0642.6
BaseBackbone=LLaDA-MoE-7B-A1B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0641.4
Diffu-GRPOBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0637.1
Diffu-GRPOBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0631.3
VRPOBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0622.3
BaseBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=256, Zero-shot setting=true2026.0619.5
VRPOBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0618
BaseBackbone=LLaDA-8B-Instruct, Decoding Budget (L)=512, Zero-shot setting=true2026.0616