LodeHQ
AI news for people who shipFree, by email

AI · arxiv.org · Friday, 20 November 2026

EverydayBench finds top agents pass only 54.55% of real-world tasks

AI agents still fail nearly half of EverydayBench’s live-web tasks, so strong demos do not yet guarantee usable results for product research, trip planning, or artifact creation. The benchmark tests 77 human-authored tasks across eight domains, checking hard constraints, verifying claims against webpages retrieved during evaluation, and judging the final deliverable. Among 23 agent-model configurations, Claude Opus 5.5 and Claude Fable 5.1 tie for the highest strict pass rate at 54.55%.

Read the source: arxiv.org ↗In the 20 November issue →