AI Now Beats Licensed CPAs on Speed and Accuracy, but Still Can't Close the Books
The Decoder · rss · 2026-10-02
A Mercor study finds current AI models now outperform licensed CPAs on structured accounting tasks in both speed and accuracy — a reversal from 18 months ago when they lagged far behind. However, on the more demanding APEX Benchmark no model completes all tasks, and AI still cannot close the books without human oversight.
More from Models
- Google's real moat is compute infrastructure, not just Gemini benchmark scores — haider1 · 2026-10-02
- giffmana: current models are great at precision but really bad at recall — giffmana · 2026-10-02
- After a week of testing, user finds Claude overly rigid vs ChatGPT — Redstra · 2026-10-02
- A 3-step guide to open models: picking, hosting locally or via OpenRouter — every · 2026-10-02
- Zero-shot classifiers rebranded as 'decision models' surprises HF engineer — mervenoyann · 2026-10-02
- Developer Says Anthropic's Claudebot Hits His Site 280K+ Times Per Day — TejasKumar_ · 2026-10-02