🟢Headline Benchmarks

Dataset name: Headlines_OneAI_v1.7

Dataset

Name: Headlines_OneAI_v1.7
Datapoints: 46,643 (tested & reported), 10,000 published
Sources: Various sources for news & blogs from various domains (news, politics, tech, finance, etc.)

Results Overview

GrademodelRouge1RougeLRougeLsum
🟢A+Ours (One-AI-headlines-v1.7)0.4860.4610.461
🟠CSOTA open-source model0.3710.3450.345
Did we miss a model? suggest one and we'll add it

Note: see our overview on the Rouge metrics

Detailed results

Ours (One-AI-headlines-v1.7)

SOTA open-source model


Did this page help you?