Veeral Patel(@vral):Ashwin benchmarked Jev as a replacement for LLM-based reranking in Ramp's accounting product, and the results are very promising Jev matches current accuracy on GPT-5.6 Luna, but decreases tail latency by 10x to 300ms at 3x lower cost We're excited to get this into production for 70k customers as soon as we stop running into rate limits :)

2026.09.24 19:37

Ashwin benchmarked Jev as a replacement for LLM-based reranking in Ramp's accounting product, and the results are very promising Jev matches current accuracy on GPT-5.6 Luna, but decreases tail latency by 10x to 300ms at 3x lower cost We're excited to get this into production for 70k customers as soon as we stop running into rate limits :)