List your company

LLM Performance Estimation on TruthfulQA (test)

1.027MAE (%)SparseEval
0.891.814752.73953.66425Feb 8, 2026

Evaluation results

MethodLinks
SparseEvalNumber of Anchors=1002026.021.0270.931
SparseEvalNumber of Anchors=802026.021.0830.922
SparseEvalNumber of Anchors=602026.021.2430.911
TailoredBenchNumber of Anchors=1002026.021.5770.895
SparseEvalNumber of Anchors=402026.021.5890.886
TailoredBenchNumber of Anchors=802026.021.7180.874
Anchor PointsNumber of Anchors=1002026.021.7330.891
SparseEvalNumber of Anchors=202026.021.7560.878
Anchor PointsNumber of Anchors=802026.021.7580.885
gp-IRTNumber of Anchors=1002026.021.8080.847
TailoredBenchNumber of Anchors=602026.021.9280.863
Anchor PointsNumber of Anchors=602026.021.9580.87
gp-IRTNumber of Anchors=802026.021.9730.836
TailoredBenchNumber of Anchors=402026.022.1050.855
gp-IRTNumber of Anchors=602026.022.250.823
Anchor PointsNumber of Anchors=402026.022.4430.838
TailoredBenchNumber of Anchors=202026.022.5540.847
gp-IRTNumber of Anchors=402026.023.0320.771
Anchor PointsNumber of Anchors=202026.023.2150.803
gp-IRTNumber of Anchors=202026.024.4520.712