AgentForge-Bench measures how reliably an off-the-shelf coding agent, driving one of seven open-weight models with a shell and the stock Python PDF stack, alters one dollar amount, date or address in a real filed financial document from a single sentence of intent, graded by rules rather than by a model.
Si-Miao Ren, Ankit Raj, Tommy Duong et al.· 2 citations
An open implementation of JevLite of this readout, JevLite, on scam-call screening, with a fine-tuned ModernBERT encoder and an evaluation reporting calibration, false alarms and decision timing alongside AUROC.
The frozen collection of ChatGPT Images 2.5 supports analysis of reported model use during a product transition, with source and attribution evidence retained for interpretation, and is released at https://scam.ai/research.
D. Ng, Xing-Yu Shen, Ankit Raj et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.