List your company
ResearchFormerly WizWand

Reasoning on GSM8K, MATH500, HumanEval, and MBPP Suite

60.3Average AccuracyInfo-Gain
21.19631.34841.551.652Feb 20, 2026
Updated 8mo ago

Evaluation results

MethodLinks
Info-GainModel=SDAR-8B-Chat, K (Decoding Rate)=12026.0260.341
Info-GainModel=TraDo-8B-Instruct, K (Decoding Rate)=12026.0260.352.1
Info-GainModel=SDAR-8B-Chat, K (Decoding Rate)=22026.0255.874.1
Info-GainModel=TraDo-8B-Instruct, K (Decoding Rate)=22026.0255.398
KLASSModel=SDAR-8B-Chat, K (Decoding Rate)=12026.0240105.3
KLASSModel=TraDo-8B-Instruct, K (Decoding Rate)=12026.0240180.3
ConfidenceModel=SDAR-8B-Chat, K (Decoding Rate)=12026.0236.9117.4
KLASSModel=SDAR-8B-Chat, K (Decoding Rate)=22026.0235210.3
KLASSModel=TraDo-8B-Instruct, K (Decoding Rate)=22026.0235334.3
EntropyModel=SDAR-8B-Chat, K (Decoding Rate)=12026.0234.9120.4
ConfidenceModel=TraDo-8B-Instruct, K (Decoding Rate)=12026.0234.3163.5
MarginModel=SDAR-8B-Chat, K (Decoding Rate)=12026.0233138.2
ConfidenceModel=SDAR-8B-Chat, K (Decoding Rate)=22026.0232.1204.1
ConfidenceModel=TraDo-8B-Instruct, K (Decoding Rate)=22026.0229.3334.1
EntropyModel=SDAR-8B-Chat, K (Decoding Rate)=22026.0228.4238.6
EntropyModel=TraDo-8B-Instruct, K (Decoding Rate)=12026.0227.8171.4
MarginModel=TraDo-8B-Instruct, K (Decoding Rate)=12026.0227.7208
MarginModel=SDAR-8B-Chat, K (Decoding Rate)=22026.0226.7230.9
EntropyModel=TraDo-8B-Instruct, K (Decoding Rate)=22026.0222.8419.5
MarginModel=TraDo-8B-Instruct, K (Decoding Rate)=22026.0222.7398