GitHub / TreeAI-Lab / NumericBench
A comprehensive benchmark to evaluate and improve the fundamental numerical reasoning abilities of large language models using diverse synthetic and real-world datasets.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TreeAI-Lab%2FNumericBench
PURL: pkg:github/TreeAI-Lab/NumericBench
Stars: 27
Forks: 0
Open issues: 0
License: None
Language:
Size: 797 KB
Dependencies parsed at: Pending
Created at: 4 months ago
Updated at: 8 days ago
Pushed at: 8 days ago
Last synced at: 8 days ago
Topics: arithmetic, benchmark, llm, numeric
Loading...