List your company

LLM Performance Estimation on ARC (test)

1.165MAE (%)SparseEval
0.78683.339655.89258.44535Feb 8, 2026

Evaluation results

MethodLinks
SparseEvalNumber of Anchors=1002026.021.1650.917
SparseEvalNumber of Anchors=802026.021.2270.91
SparseEvalNumber of Anchors=602026.021.4040.902
SparseEvalNumber of Anchors=402026.021.5810.883
SparseEvalNumber of Anchors=202026.021.7780.863
gp-IRTNumber of Anchors=1002026.022.2740.787
Anchor PointsNumber of Anchors=802026.022.2890.868
Anchor PointsNumber of Anchors=402026.022.3750.866
TailoredBenchNumber of Anchors=1002026.022.4130.873
TailoredBenchNumber of Anchors=602026.022.4480.852
gp-IRTNumber of Anchors=802026.022.6120.761
TailoredBenchNumber of Anchors=402026.022.6460.854
TailoredBenchNumber of Anchors=802026.022.8160.862
Anchor PointsNumber of Anchors=602026.022.890.867
gp-IRTNumber of Anchors=602026.022.9590.758
TailoredBenchNumber of Anchors=202026.023.4260.824
gp-IRTNumber of Anchors=402026.023.6420.698
Anchor PointsNumber of Anchors=202026.024.0040.769
gp-IRTNumber of Anchors=202026.025.3320.641
Anchor PointsNumber of Anchors=1002026.0210.620.578