List your company

LLM Performance Estimation on GSM8K (test)

1.619MAE (%)SparseEval
1.467282.491393.51554.53961Feb 8, 2026

Evaluation results

MethodLinks
SparseEvalNumber of Anchors=1002026.021.6190.936
SparseEvalNumber of Anchors=802026.021.7540.931
SparseEvalNumber of Anchors=602026.021.960.925
SparseEvalNumber of Anchors=402026.022.3210.908
gp-IRTNumber of Anchors=1002026.022.4240.887
gp-IRTNumber of Anchors=802026.022.7740.88
Anchor PointsNumber of Anchors=802026.022.7780.906
gp-IRTNumber of Anchors=602026.023.1610.871
SparseEvalNumber of Anchors=202026.023.3050.872
Anchor PointsNumber of Anchors=602026.023.6310.916
Anchor PointsNumber of Anchors=402026.023.7560.878
gp-IRTNumber of Anchors=402026.023.9840.832
TailoredBenchNumber of Anchors=802026.024.0030.9
TailoredBenchNumber of Anchors=402026.024.1570.885
TailoredBenchNumber of Anchors=1002026.024.2030.912
TailoredBenchNumber of Anchors=602026.024.2710.892
Anchor PointsNumber of Anchors=202026.024.4330.844
gp-IRTNumber of Anchors=202026.025.2750.802
Anchor PointsNumber of Anchors=1002026.025.2950.842
TailoredBenchNumber of Anchors=202026.025.4120.833