Benchmark

Workspace Bench

Workspace Bench evaluates AI agents on high-economic-value workplace tasks that span multi-step planning, file processing, and tool use across realistic…

Modality
text
Categories
reasoning, general, agents
Openness
unknown
Source
llm_stats
Reported scores
3

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Qwen3.8 MaxQwen0.6772026-08-02evidence
Seed 2.1 ProByteDance0.532026-06-24evidence
Seed 2.1 TurboByteDance0.5472026-06-24evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.