reasoning 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 office and productivity workflows.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
Workspace Bench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | BY | 54.7% | 100.0% | 2 | C | |
| 2 | BY | 53.0% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
Workspace Bench highlights
The top published results on this benchmark's own scale.
What is Workspace Bench?
Definition and scoring fields from the benchmark registry.
Workspace Bench evaluates AI agents on high-economic-value workplace tasks that span multi-step planning, file processing, and tool use across realistic office and productivity workflows.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Workspace Bench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- workspace-bench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Workspace Bench.
Which model scores highest on Workspace Bench?
Seed 2.1 Turbo is currently ranked first with 54.7%.
What does Workspace Bench measure?
Workspace Bench evaluates AI agents on high-economic-value workplace tasks that span multi-step planning, file processing, and tool use across realistic office and productivity workflows.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.