Work

2026 email triage benchmark: GPT-4o vs DeBERTa 95th percentile latency vs recall

Year: 2026
Type: preprint
Abstract: DeBERTa beats GPT-4o on p95 latency and cost per decision in 2026 email triage, while GPT-4o retains higher recall on threaded and ambiguous mail. Independent technical note mirroring the canonical version: https://withtai.com/blog/2026-email-triage-benchmark-gpt-4o-vs-deberta-95th-percentile-latency-vs-recall.php
Language: English
Open Access status: green
OpenAlex ID: W7225802345
Cites:
Cited by:
Related to: