Since its release, FinFIRST has drawn a lot of interest. Built with finance experts, it uses atomic rubrics to assess both answers and evidence, including how agents search, handle timely real world tasks, combine sources, choose reliable evidence, calculate and make results easy to verify. 🧵
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Why it matters
Gives a rubric-based way to evaluate finance agents on how they search, calculate, and cite evidence rather than just final-answer correctness, with Ling-3.0-flash-Fin hitting 82.45% on source verification.
postToday, we’re introducing Ling-3.0-flash-Sante — an MoE model enhanced for…
postKeeping Transformed Weights Resident Cuts SGLang Cold Starts to Seconds
postLing-3.0-tiny Measured on the Phone-Class Intelligence and Speed Frontier
postLing-3.0-flash-Fin Takes Auditable Tool Chains Into Financial Work
postAnt Group opens a 124B finance MoE and a search-agent benchmarkAntLingAGI
articleFinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional DeliverablesBen Wang, Kang Zhou, Lifan Guo, Feng Chen, Chi Zhang