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

Model Merging on 7 NLP tasks (test)

79.2Accuracy

EXPERTS

Updated 2mo ago

Evaluation Results

Method	Links
EXPERTS 2026.04		79.2
REGMEAN 2026.04		77.7
ACTMAT 2026.04		76.7
EXPERTS 2026.04		76.5
REGMEAN 2026.04		75.9
TSV 2026.04		75.4
TSV 2026.04		72.2
ACTMAT 2026.04		72
K-TSV 2026.04		71.1
TA 2026.04		70.9
K-ISO-C 2026.04		69.4
K-TSV 2026.04		67.6
TA 2026.04		66.7
K-ISO-C 2026.04		64.7
AVERAGE 2026.04		62.2
AVERAGE 2026.04		57.2
ISO-C 2026.04		56.1
TA 2026.04		55
TA 2026.04		54.2
ZEROSHOT 2026.04		54
ISO-C 2026.04		52.1
ZEROSHOT 2026.04		51.3