OfficeQA Pro
Professional Work · 2026-03-09
Harder 133-question OfficeQA subset recommended for frontier models; default OfficeQA Pro split.
Top models (higher is better)
| Model | Score |
|---|---|
| Opus 4.7 | 80.6 |
| Claude Fable 5 | 69.9 |
| Claude Mythos 5 | 67.1 |
| Claude Opus 5 | 66.9 |
| Opus 4.8 | 66.2 |
| Kimi K3 | 63.3 |
| GPT-5.6 Sol | 63.2 |
| GPT-5.5 | 60.9 |
| Sonnet 5 | 59.4 |
| GLM-5.2 | 41.4 |
| Gemini 3.1 Pro Preview | 18.1 |