OfficeQA (Anthropic Internal Harness): leaderboard
Anthropic internal OfficeQA document-agent benchmark, requiring grounded search and numerical reasoning over office documents.
Metric: Exact Match (%). Source: www-cdn.anthropic.com. Saturation forecast: Around January 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 77.6 | #37 |
| 2 | Claude Opus 4.7 | 76.3 | #49 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=officeqa-anthropic-internal-harness · How It Works · Data refreshed daily, snapshot 2026-10-20.