UniClawBench

What is UniClawBench?

A capability-driven benchmark for proactive agents in real-world tasks, with 400 bilingual tasks across five capabilities. It evaluates agents in Docker…

Released

2026-07-09

Evaluates

General AI, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.08768

UniClawBench paper and code

• Paper https://arxiv.org/abs/2607.08768
• Code https://github.com/HKU-MMLab/UniClawBench
• Website https://uniclawbench.github.io

Which sources cite UniClawBench?

• UniClawBench

Related General AI, Language & Knowledge, cs.CL 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