Benchmark Radar™
Star —

TELBench

Explore score history ↗

Evaluates span-level error localization in deep-research agent trajectories. TELBench comprises 1,000 instances with annotations of harmful error spans among normal exploration, failed searches, tentative hypotheses, and harmless noise, scored by span-level localization and first-error accuracy.

Released
2026-06-01
Institutions
Nanjing University
Evaluates
Agents, General AI, Language & Knowledge
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

TELBench paper and code

No reported scores are on record for this benchmark yet.

Which sources cite TELBench?

Related Agents, General AI, Language & Knowledge benchmarks