List your company

LLM Performance Estimation on HellaSwag (test)

0.827MAE (%)SparseEval
0.647161.861083.0754.28892Feb 8, 2026

Evaluation results

MethodLinks
SparseEvalNumber of Anchors=1002026.020.8270.918
SparseEvalNumber of Anchors=802026.020.9420.91
SparseEvalNumber of Anchors=602026.020.9930.906
SparseEvalNumber of Anchors=402026.021.210.89
SparseEvalNumber of Anchors=202026.021.4770.857
gp-IRTNumber of Anchors=1002026.021.750.783
TailoredBenchNumber of Anchors=602026.021.8680.861
TailoredBenchNumber of Anchors=802026.021.9570.857
Anchor PointsNumber of Anchors=802026.021.9620.847
TailoredBenchNumber of Anchors=1002026.021.9680.876
gp-IRTNumber of Anchors=802026.021.9920.784
Anchor PointsNumber of Anchors=1002026.022.0120.889
TailoredBenchNumber of Anchors=402026.022.2570.847
TailoredBenchNumber of Anchors=202026.022.3520.811
Anchor PointsNumber of Anchors=602026.022.4160.856
Anchor PointsNumber of Anchors=402026.022.6190.875
gp-IRTNumber of Anchors=602026.022.7540.745
Anchor PointsNumber of Anchors=202026.023.2720.796
gp-IRTNumber of Anchors=402026.023.5010.687
gp-IRTNumber of Anchors=202026.025.3230.661