List your company

Reasoning on MuSiQue (OOD)

0Degeneracy ScoreBase
-26.04149.73325.5501.27Feb 26, 2026

Evaluation results

MethodLinks
BaseModel Scale=0.6B2026.020731575785731
PromptModel Scale=0.6B2026.020697551744697
MBT-SModel Scale=4B2026.020471449514471
BaseModel Scale=1.7B2026.0211,1868491,4471,173
GRPOModel Scale=1.7B2026.0211,3791,0241,8011,366
MBT-RModel Scale=1.7B2026.021728686771715
MBT-RModel Scale=4B2026.021724688784711
PromptModel Scale=1.7B2026.0221,1348011,3861,108
MBT-SModel Scale=1.7B2026.022521462582494
BaseModel Scale=4B2026.0221,3681,0151,9331,342
MBT-RModel Scale=0.6B2026.025750658804684
PromptModel Scale=4B2026.0251,3249901,7891,259
MBT-SModel Scale=0.6B2026.026561451633481
RSModel Scale=0.6B2026.02129435781,049784
GRPOModel Scale=0.6B2026.02162,1671,4882,5441,963
RSModel Scale=1.7B2026.02191,5339341,9811,286
GRPOModel Scale=4B2026.02732,4331,1264,0041,488
RSModel Scale=4B2026.021333,0971,0484,6751,369
TokenSkipModel Scale=0.6B2026.021743,2206883,619928
gpt-oss-distillModel Scale=4B2026.022855,4371,44310,4891,784
LIMOProModel Scale=0.6B2026.023865,6974797,430552
TokenSkipModel Scale=1.7B2026.024717,4379429,8891,306
gpt-oss-distillModel Scale=0.6B2026.025849,4651,55514,3292,040
gpt-oss-distillModel Scale=1.7B2026.025859,3221,45416,2901,835
LIMOProModel Scale=1.7B2026.025858,39351611,539610
LIMOProModel Scale=4B2026.025908,47856012,193634
TokenSkipModel Scale=4B2026.026519,9321,04013,5561,514