List your company

Human label alignment on Human expert binary labels n = 150

0.717KappaHybrid-EX
0.193880.329690.46550.60131Jun 1, 2026

Evaluation results

MethodLinks
Hybrid-EXClassification=Substantial, Rank=#12026.060.7170.687.381.593.111.6
LLM-EXClassification=Substantial, Rank=#22026.060.6210.48978.898.958.640.3
BIRD M3Classification=Fair, Rank=#32026.060.3950.2657254.489.735.3
RAGAS M4Classification=Fair, Rank=#42026.060.370.22670.257.682.825.2
IBM EvalAssist M2Classification=Fair, Rank=#52026.060.3550.20969.357.68123.4
Defog M1Classification=Fair, Rank=#62026.060.3510.20969.454.484.530.1
Dr. Spider M5Classification=Fair (low), Rank=#72026.060.2350.11360.197.822.475.4
Spider2 M6Classification=Fair (low), Rank=#82026.060.2140.1326326.110073.9