Benchmark
WorldBench
What is WorldBench?
A multilingual benchmark of persona-grounded everyday workflows for agents, evaluated via sandbox actions. Benchmark Radar tracks WorldBench, cited by 1 source…
- Released
- 2026-09-01
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2609.01056
WorldBench paper
No reported scores are on record for this benchmark yet.