List your company

Symbolic Reasoning on Countdown

49.61AccuracyFDM-A
6.949218.024629.140.1754Dec 3, 2025

Evaluation results

MethodLinks
FDM-ALLDM Model=LLaDA-MoE2025.1249.6110.14
ProbabilityLLDM Model=LLaDA-MoE, Threshold (T)=1282025.1244.538.8
MarginLLDM Model=LLaDA-MoE, Threshold (T)=1282025.1242.588.33
EBLLDM Model=LLaDA-MoE2025.1242.199.48
EntropyLLDM Model=LLaDA-MoE, Threshold (T)=1282025.1235.948.15
FDM-ALLDM Model=MMaDA-MixCoT2025.1226.9562.3
WINOLLDM Model=LLaDA-MoE2025.12258.23
FDM-ALLDM Model=LLaDA2025.1221.4821.98
ProbabilityLLDM Model=LLaDA-1.5, Threshold (T)=1282025.1221.0922.01
FDM-ALLDM Model=LLaDA-1.52025.1221.0922.29
WINOLLDM Model=MMaDA-MixCoT2025.1220.752.39
MarginLLDM Model=LLaDA, Threshold (T)=1282025.1220.3120.65
MarginLLDM Model=LLaDA-1.5, Threshold (T)=1282025.1219.9221.76
EBLLDM Model=LLaDA-1.52025.1219.9218.79
ProbabilityLLDM Model=LLaDA, Threshold (T)=1282025.1219.5321.19
EntropyLLDM Model=LLaDA, Threshold (T)=1282025.1219.5320.62
EBLLDM Model=LLaDA2025.1219.218.68
WINOLLDM Model=LLaDA2025.1219.1420.52
WINOLLDM Model=LLaDA-1.52025.1219.1420.38
EntropyLLDM Model=LLaDA-1.5, Threshold (T)=1282025.1218.7520.93
EBLLDM Model=MMaDA-MixCoT2025.1218.7548.51
ProbabilityLLDM Model=MMaDA-MixCoT, Threshold (T)=1282025.1212.0121.97
MarginLLDM Model=MMaDA-MixCoT, Threshold (T)=1282025.128.5921.57
EntropyLLDM Model=MMaDA-MixCoT, Threshold (T)=1282025.128.5920.52