Share your thoughts, 1 month free Claude Pro on usSee more

High-stakes specialized classification on DDI (test)

61.12Macro-F1

EvoPool

Updated 1d ago

Evaluation Results

Method	Links
EvoPool 2026.06		61.12
EvoPool 2026.06		59.74
Self-Train 2026.06		57.82
Golden 2026.06		57.74
EvoPool 2026.06		57.45
EvoPool 2026.06		53.79
EvoPool 2026.06		53.4
EvoPool 2026.06		52.93
Self-Train 2026.06		45.92
Self-Train 2026.06		45.81
LLM-Annotation 2026.06		45.49
EvoPool 2026.06		45.39
Golden 2026.06		44.91
LLM-Annotation 2026.06		39.46
Golden 2026.06		38.63
DataSculpt 2026.06		34.63
DataSculpt 2026.06		29.55
Alchemist 2026.06		27.16
LLM-Annotation 2026.06		27.07
Alchemist 2026.06		26.87
Alchemist 2026.06		26.71
LLM annotation 2026.06		23.45
LLM-Eval 2026.06		23.45
LLM-Eval 2026.06		23.45
LLM-Eval 2026.06		23.45
LLM-Annotation 2026.06		23.05
LLM-Annotation 2026.06		22.34
LLM-Annotation 2026.06		22.06
Alchemist 2026.06		21.55
Alchemist 2026.06		21.21
Alchemist 2026.06		18.06
DataSculpt 2026.06		17.78
DataSculpt 2026.06		17.56
DataSculpt 2026.06		17.46
DataSculpt 2026.06		17.46
Alchemist 2026.06		11.89
DataSculpt 2026.06		11.34