Coinbase fine-tunes Qwen3.5-9B model for fraud prevention, beating frontier models
Photo: Crypto Briefing
A small open model trained for under $100 outperformed Opus 4.5 on Coinbase's Onramp fraud benchmark while answering in less than half the time Coinbase has spent the past stretch teaching a relatively small AI model to catch fraudsters. According to the exchange, the small model now does that job better than some of the most expensive AI systems on the market. In its “Owning Intelligence” blog series, published October 7-8, 2026, Coinbase said a fine-tuned version of Alibaba’s Qwen3.5-9B model outperformed frontier models on fraud detection for its Onramp service. It was faster and far cheaper to train.
Source: Crypto Briefing
