WorkSpaceBench
WorkSpaceBench - in-house benchmark for evaluating workspace productivity tasks.
Category
General Agents
Max Score
—
Score Type
percent
Active
Yes
Model Scores
Scores for WorkSpaceBench
| Model | Score | Date | Verified |
|---|---|---|---|
| Claude Opus 4.8 |
51.19%
|
18.08.2026 | Unverified |
| Qwen3.7-Max |
19.05%
|
18.08.2026 | Unverified |
| Qwen3.8-2.4T-A95B |
56.55%
|
18.08.2026 | Verified |
| Hy4 preview |
11.90%
|
28.08.2026 | Verified |
| DeepSeek V4 Pro |
42.86%
|
28.08.2026 | Verified |
| GLM-5.3 |
59.52%
|
28.08.2026 | Verified |
| Kimi K3 |
40.48%
|
28.08.2026 | Verified |
| Claude Opus 5 |
100.00%
|
28.08.2026 | Verified |
| Fable-5 |
62.50%
|
18.08.2026 | Unverified |
| GPT-5.6 Sol |
44.05%
|
18.08.2026 | Unverified |
| Hy3 |
58.20
|
28.08.2026 | Verified |