HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Pulze AI Evals | Hacker News Reader
Pulze AI Evals
github.com
1 point
·
fbnbr
·
·
1 comment
Open article
Save
View on HN
fbnbr
(original poster)
·
Benchmark AI models on standard datasets like FinanceBench and MMLU.
Reply on news.ycombinator.com