HyperAIHyperAI

Command Palette

Search for a command to run...

Leistungsergebnisse verschiedener Modelle auf diesem Benchmark

Metriken

F1
GPT-4o-mini (Total)
GPT-4o-mini (Boolean)
GPT-4o-mini (Extractive)
GPT-4o-mini (Abstractive)
DeepSeek-V2-Lite-Chat (Total)
DeepSeek-V2-Lite-Chat (Boolean)
DeepSeek-V2-Lite-Chat (Extractive)
DeepSeek-V2-Lite-Chat (Abstractive)
DTCRS (Evidence Node Coverage)
DTCRS (Average Number of Nodes)
RAPTOR (Evidence Node Coverage)
RAPTOR (Average Number of Nodes)
5 Zeilen insgesamt
QASPER | SOTA | HyperAI