WorkSpaceBench
WorkSpaceBench - in-house benchmark for evaluating workspace productivity tasks.
Category
General Agents
Score type
percent
Scale
relative
higher is better
Models tested
5
What is WorkSpaceBench?
WorkSpaceBench is a benchmark for how well a model acts as a general-purpose agent. The official description says: "WorkSpaceBench - in-house benchmark for evaluating workspace productivity tasks". Below we describe in simple words what benchmarks of this type generally examine.
What does it test?
WorkSpaceBench measures how well a model acts as a general-purpose agent. In detail, it checks:
- solving long, multi-step tasks with many intermediate decisions
- using tools correctly (browsers, terminals, APIs, calendars, other apps)
- adapting when something unexpected happens mid-task
- staying on goal over long task horizons instead of wandering off
How to read the score
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.
Official methodology note: WorkSpaceBench - in-house benchmark for evaluating workspace productivity tasks.
Frequently asked questions
What is the WorkSpaceBench benchmark?
WorkSpaceBench is a benchmark for how well a model acts as a general-purpose agent. The official description says: 'WorkSpaceBench - in-house benchmark for evaluating workspace productivity tasks'. Below we describe in simple words what benchmarks of this type generally examine.
What does WorkSpaceBench test?
WorkSpaceBench mainly measures how well a model acts as a general-purpose agent. Concretely, it checks: solving long, multi-step tasks with many intermediate decisions; using tools correctly (browsers, terminals, APIs, calendars, other apps); adapting when something unexpected happens mid-task.
How is the WorkSpaceBench score calculated?
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.
Where do I get WorkSpaceBench data and scores?
The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/workspacebench/scores) or pull it directly from the Open LLM Radar API with any HTTP client.
Benchmark data & downloads
Where to get, inspect and reuse the data behind this benchmark.
Benchmark dataset
The question/task data itself — download and evaluate locally
Benchmark metadata (JSON)
This page's benchmark record from the Open LLM Radar API
All model scores (JSON download)
Full score table as JSON; paginate with limit/offset params
Open LLM Radar API docs
Swagger UI to explore and reuse all radar API endpoints
Model scores 5 models tested
| # | Model | Score | Date | Source | Verified |
|---|---|---|---|---|---|
| 1 |
GLM-5.3
Zhipu AI
|
68.2%
|
28.08.2026 | Tencent Hy4 preview model card benchmark appendix (https://huggingface.co/tencent/Hy4-preview#benchmark-appendix) (Tencent rerun) | Verified |
| 2 |
Qwen3.8-2.4T-A95B
Qwen
|
67.7%
|
18.08.2026 | Report | Verified |
| 3 |
Kimi K3
Moonshot AI
|
65%
|
28.08.2026 | Tencent Hy4 preview model card benchmark appendix (https://huggingface.co/tencent/Hy4-preview#benchmark-appendix) (Tencent rerun) | Verified |
| 4 |
Hy4 preview
Tencent
|
60.2%
|
28.08.2026 | Tencent Hy4 preview model card benchmark appendix (https://huggingface.co/tencent/Hy4-preview#benchmark-appendix) | Verified |
| 5 |
Hy3
Tencent
|
58.2%
|
28.08.2026 | Tencent Hy4 preview model card benchmark appendix (https://huggingface.co/tencent/Hy4-preview#benchmark-appendix) | Verified |