TELBench

What is TELBench?

Evaluates span-level error localization in deep-research agent trajectories. TELBench comprises 1,000 instances with annotations of harmful error spans among…

Released

2026-06-01

Evaluates

Agents, General AI, Language & Knowledge

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.02060

TELBench paper and code

• Paper https://arxiv.org/abs/2606.02060
• Code https://github.com/NJU-LINK/DRIFT

Which sources cite TELBench?

• TELBench

Related Agents, General AI, Language & Knowledge benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench