Add Decision model row to What's here table

README.md

@@ -39,6 +39,7 @@ We publish narrow models for those tasks and the benchmarks that show where each
 | **Form field understanding**: add the text label, radio-group identity, and — with v2 — the entered value and description for each detected field, on empty, filled, and handwritten forms | | [form-field-vlm](https://huggingface.co/nutrientdocs/form-field-vlm) · [form-field-vlm-v2](https://huggingface.co/nutrientdocs/form-field-vlm-v2) | [form-field-vlm-benchmark](https://huggingface.co/datasets/nutrientdocs/form-field-vlm-benchmark) (CC-BY-4.0) · [form-field-vlm-v2-benchmark](https://huggingface.co/datasets/nutrientdocs/form-field-vlm-v2-benchmark) (CC-BY-4.0) | [form-field-vlm-leaderboard](https://huggingface.co/spaces/nutrientdocs/form-field-vlm-leaderboard) · [form-field-vlm-v2-leaderboard](https://huggingface.co/spaces/nutrientdocs/form-field-vlm-v2-leaderboard) | [form-field-vlm-demo](https://huggingface.co/spaces/nutrientdocs/form-field-vlm-demo) · [form-field-vlm-v2-demo](https://huggingface.co/spaces/nutrientdocs/form-field-vlm-v2-demo) |
 | **Chart parsing**: read a chart image and return its title, chart type, data table, axes, series, and legend as one JSON object | | [chart-parsing-vlm](https://huggingface.co/nutrientdocs/chart-parsing-vlm) | [chart-parsing-benchmark](https://huggingface.co/datasets/nutrientdocs/chart-parsing-benchmark) (CC-BY-4.0) | [chart-parsing-leaderboard](https://huggingface.co/spaces/nutrientdocs/chart-parsing-leaderboard) | [chart-parsing-demo](https://huggingface.co/spaces/nutrientdocs/chart-parsing-demo) |
 | **PII detection and redaction**: context-aware redaction on full documents | | | [DocPII-redaction-benchmark](https://huggingface.co/datasets/nutrientdocs/DocPII-redaction-benchmark) (MIT) | [LLM-PII-Detection-Leaderboard](https://huggingface.co/spaces/nutrientdocs/LLM-PII-Detection-Leaderboard) | |
+| **Decision model**: one model across grounding, document splitting, and document classification — a general document-decision model (in the same vein as hosted System-One offerings), scored on the same public benchmarks as our single-task specialists above | | [nutrient-document-decision](https://huggingface.co/nutrientdocs/nutrient-document-decision) | [grounding-benchmark](https://huggingface.co/datasets/nutrientdocs/grounding-benchmark) · [document-classification-benchmark](https://huggingface.co/datasets/nutrientdocs/document-classification-benchmark) · [doc-openvocab-benchmark](https://huggingface.co/datasets/nutrientdocs/doc-openvocab-benchmark) · [doc-split-benchmark](https://huggingface.co/datasets/nutrientdocs/doc-split-benchmark) | [grounding-leaderboard](https://huggingface.co/spaces/nutrientdocs/grounding-leaderboard) · [document-classification-leaderboard](https://huggingface.co/spaces/nutrientdocs/document-classification-leaderboard) · [doc-openvocab-leaderboard](https://huggingface.co/spaces/nutrientdocs/doc-openvocab-leaderboard) · [doc-split-leaderboard](https://huggingface.co/spaces/nutrientdocs/doc-split-leaderboard) | [nutrient-document-decision-demo](https://huggingface.co/spaces/nutrientdocs/nutrient-document-decision-demo) |
 
 Every leaderboard is scored by the same open scorer we use ourselves. Current numbers, including the cases where a cloud model beats us, live on the leaderboards, not in this README. To add a model, run the scorer and open a pull request on the leaderboard space.