OmegaUse-OfficeVal

What is OmegaUse-OfficeVal?

Evaluates LLM agents on long-horizon office-suite tasks from 100 practitioner-derived scenarios, scoring deliverable quality through code-based verifiers and…

Released

2026-07-29

Evaluates

General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.27155

OmegaUse-OfficeVal paper and code

• Paper https://arxiv.org/abs/2607.27155
• Code https://github.com/baidu-frontier-research/OmegaUse-OfficeVal
• Website https://omegause-officeval.github.io

Which sources cite OmegaUse-OfficeVal?

• OmegaUse-OfficeVal

Related General AI, Language & Knowledge, cs.AI 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