Surge AI Releases DAYJOB Benchmark; Top Agents Pass ~25%

Surge AI launched DAYJOB, a benchmark family for knowledge-work agents with Healthcare and Finance subsets totaling 130 expert tasks spanning up to 14-hour workflows. The best agents complete only about a quarter of the real-world professional tasks.

2026-09-24 ~ 2026-09-24 · 3 related posts

• New DAYJOB benchmark: best agents complete only ~25% of real knowledge work — echen · 2026-09-24
• Surge AI's DAYJOB benchmark: best agents pass only ~24% of real work — echen · 2026-09-24
• Surge AI launches DAYJOB benchmark: end-to-end professional judgment with 14-17 hour work horizons — echen · 2026-09-24