List your company

LLM Performance Estimation on Winogrande (test)

1.027MAESparseEval
0.8452.07353.3024.5305Feb 8, 2026

Evaluation results

MethodLinks
SparseEvalNumber of Anchors=1002026.021.0270.897
SparseEvalNumber of Anchors=802026.021.1820.882
SparseEvalNumber of Anchors=602026.021.3610.867
SparseEvalNumber of Anchors=402026.021.50.853
gp-IRTNumber of Anchors=1002026.021.9570.725
SparseEvalNumber of Anchors=202026.022.0880.794
gp-IRTNumber of Anchors=802026.022.2840.659
gp-IRTNumber of Anchors=602026.022.6170.63
Anchor PointsNumber of Anchors=1002026.023.0190.81
TailoredBenchNumber of Anchors=1002026.023.120.788
TailoredBenchNumber of Anchors=802026.023.130.752
TailoredBenchNumber of Anchors=202026.023.2120.705
gp-IRTNumber of Anchors=402026.023.4170.547
TailoredBenchNumber of Anchors=602026.023.4780.76
Anchor PointsNumber of Anchors=802026.023.6210.752
TailoredBenchNumber of Anchors=402026.023.740.751
Anchor PointsNumber of Anchors=402026.024.0370.737
Anchor PointsNumber of Anchors=602026.024.0380.71
gp-IRTNumber of Anchors=202026.024.9030.533
Anchor PointsNumber of Anchors=202026.025.5770.694