Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Multimodal & Grounded benchmark
Every model the catalog carries a published OfficeQA Pro v2 value for, ranked by that value.
The second version of OfficeQA Pro: grounded reasoning over real financial and office documents through retrieval, cross-document verification, and multi-step numerical reasoning. 2 models in the ModelScale catalog have a published value.
Each point is a model with a published OfficeQA Pro v2 value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
2 models with a published OfficeQA Pro v2 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Task accuracy |
|---|---|---|---|
| 1 | Baidu | 67.9 | |
| 2 | Moonshot AI | 64.4 |
Evidence key: Observed
Rows are ordered by the value Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
What the benchmark measures and how its value is published, from the source’s own record.
OfficeQA Pro v2 is a multimodal & grounded benchmark published by Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence. The second version of OfficeQA Pro: grounded reasoning over real financial and office documents through retrieval, cross-document verification, and multi-step numerical reasoning. Its evaluation set is described by the source as document and spreadsheet tasks. The source rates its difficulty as enterprise document reasoning.
Each model's result is published by Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence as task accuracy. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 2 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
All leaderboards · Multimodal & Grounded capability leaderboard