DualEntry's benchmark tested 19 AI models on 101 accounting tasks; GPT-5.4 led with 77.3% accuracy but failed on roughly 1 in 4 real-world accounting workflows.
Continue reading
Indian CA institute highlights AI upskilling platform Kyra and inaugural AI Innovation Challenge with 12 shortlisted chartered accountant proposals, focusing on practical implementation of copilots...
Meridian releases Spreadsheet Arena, an open benchmarking platform co-developed with Cornell, CMU, and Scale AI to evaluate LLM performance in generating spreadsheet workbooks through blind pairwis...
An audit of 1 billion tokens reveals a major gap between token compression rates (99%) and actual billing, suggesting potential overcharges or token counting inconsistencies in LLM API pricing.
Harvey CEO reports AI token consumption jumped from 1 trillion to 12–13 trillion monthly in five months, signaling rapid adoption of the legal AI platform among law firms.
New multi-agent framework DuMate-DeepResearch addresses hallucination and verification challenges in deep research tasks through recursive search and rubric-grounded reasoning, with direct applicat...