Add the benchmark datasets section to the org card

README.md

@@ -11,7 +11,7 @@ pinned: false
 
 # Aurigene AI
 
-We are the AI and computational discovery group at **Aurigene Pharmaceutical Services Limited**. This organization is our public home for open models and browser-based tools that support **AI-driven drug discovery** — from picking a target, through generating and triaging chemical matter, to planning the synthesis and reading the literature that justifies all of it.
+We are the AI and computational discovery group at **Aurigene Pharmaceutical Services Limited**. This organization is our public home for open models, benchmark datasets and browser-based tools that support **AI-driven drug discovery** — from picking a target, through generating and triaging chemical matter, to planning the synthesis and reading the literature that justifies all of it.
 
 Everything here is open, permissively licensed, and mirrored from the original authors with full attribution.
 
@@ -87,6 +87,40 @@ Mine the papers that justify the programme.
 
 ---
 
+## 📊 Benchmark datasets
+
+Standard evaluation sets, mirrored so every model above has data to train and benchmark against. Row counts on each card are computed from the files themselves.
+
+**Lead optimization — MoleculeNet ADMET & toxicity**
+
+| Dataset | Task | Rows |
+| :-- | :-- | --: |
+| [MoleculeNet_BBBP](https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_BBBP) | Blood-brain barrier penetration | 2,039 |
+| [MoleculeNet_BACE](https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_BACE) | BACE-1 inhibition, an Alzheimer's target | 1,513 |
+| [MoleculeNet_ClinTox](https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_ClinTox) | Clinical toxicity & FDA approval | 1,477 |
+| [MoleculeNet_Tox21](https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_Tox21) | 12 toxicity assays | 7,831 |
+| [MoleculeNet_SIDER](https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_SIDER) | Marketed-drug side effects | 1,427 |
+| [MoleculeNet_ESOL](https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_ESOL) | Aqueous solubility | 1,128 |
+| [MoleculeNet_FreeSolv](https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_FreeSolv) | Hydration free energy | 642 |
+| [MoleculeNet_Lipophilicity](https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_Lipophilicity) | logD at pH 7.4 | 4,200 |
+
+**Hit generation — virtual screening**
+
+| Dataset | Task | Rows |
+| :-- | :-- | --: |
+| [MoleculeNet_HIV](https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_HIV) | HIV replication inhibition | 41,127 |
+
+**Evidence & literature — medical QA**
+
+| Dataset | Task | Rows |
+| :-- | :-- | --: |
+| [MedQA-USMLE-4-options](https://huggingface.co/datasets/Aurigene-AI/MedQA-USMLE-4-options) | US licensing exam, 4-option MCQ | 11,451 |
+| [MedMCQA](https://huggingface.co/datasets/Aurigene-AI/MedMCQA) | Medical entrance exam questions | 193,155 |
+
+All eleven are in the [Benchmark Datasets collection](https://huggingface.co/collections/Aurigene-AI/benchmark-datasets-6aa235046a491fa5b8a87fe0).
+
+---
+
 ## ⚡ Quick start
 
 ```python
@@ -103,7 +137,7 @@ print(embeddings.shape)   # torch.Size([2, 768])
 
 ## 📚 Collections
 
-Browse the catalogue as curated collections: [molecular representation & property prediction](https://huggingface.co/collections/Aurigene-AI/molecular-representation-and-property-prediction-6aa2203a94123133168b49e2), [generative chemistry & synthesis planning](https://huggingface.co/collections/Aurigene-AI/generative-chemistry-and-synthesis-planning-6aa2203c3d5b3527359ee444), [protein & target modeling](https://huggingface.co/collections/Aurigene-AI/protein-and-target-modeling-6aa2203e4e5bdf1f106c7d55), [biomedical language models](https://huggingface.co/collections/Aurigene-AI/biomedical-language-models-6aa2203f4469f54b61382c40), [interactive tools](https://huggingface.co/collections/Aurigene-AI/interactive-drug-discovery-tools-6aa220414e5bdf1f106c7dc0).
+Browse the catalogue as curated collections: [molecular representation & property prediction](https://huggingface.co/collections/Aurigene-AI/molecular-representation-and-property-prediction-6aa2203a94123133168b49e2), [generative chemistry & synthesis planning](https://huggingface.co/collections/Aurigene-AI/generative-chemistry-and-synthesis-planning-6aa2203c3d5b3527359ee444), [protein & target modeling](https://huggingface.co/collections/Aurigene-AI/protein-and-target-modeling-6aa2203e4e5bdf1f106c7d55), [biomedical language models](https://huggingface.co/collections/Aurigene-AI/biomedical-language-models-6aa2203f4469f54b61382c40), [interactive tools](https://huggingface.co/collections/Aurigene-AI/interactive-drug-discovery-tools-6aa220414e5bdf1f106c7dc0), [benchmark datasets](https://huggingface.co/collections/Aurigene-AI/benchmark-datasets-6aa235046a491fa5b8a87fe0).
 
 ## 📄 Attribution & licensing