BBC
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Classification | bbc | Accuracy99.72 | 61 | |
| Next Token Prediction | BBC | Next Token Accuracy40.05 | 32 | |
| Reference-grounded News Verification | BBC | Classification Accuracy (ACCcls)97.09 | 20 | |
| Topic Modeling | BBC | NPMI0.38 | 17 | |
| Cluster count selection | Bbc | Selected Cluster Count9 | 16 | |
| Multi-view Classification | BBC | Accuracy97.23 | 16 | |
| Topic Modeling | BBC | IRBO1 | 13 | |
| Document Clustering | BBC (test) | NMI0.729 | 13 | |
| Multi-view Clustering | BBC | NMI70.55 | 12 | |
| Dataset Addition | bbc-embedding | DA Score81 | 12 | |
| Dataset Removal | bbc embedding | DR0.9 | 12 | |
| Noisy label detection | bbc-embedding | NLD Score0.11 | 12 | |
| Word Intrusion Detection | BBC | Accuracy63.15 | 10 | |
| Document Classification | BBC | Accuracy100 | 10 | |
| Synthetic Text Generation | BBC | Mean Embedding Similarity0.43 | 10 | |
| Node Classification | BBC rich-text graph (test) | Accuracy98.4 | 10 | |
| Node Classification | BBC (test) | NMI0.949 | 10 | |
| Clustering | Bbc | SIL0.188 | 5 | |
| Clustering | Bbc | AMI83.9 | 5 | |
| Next Token Prediction | BBC | Accuracy (ϵ=∞)25.75 | 5 | |
| Dataset Addition | BBC | Accuracy (5% Threshold)68 | 5 | |
| Dataset Removal | BBC | Accuracy (5%)90 | 5 | |
| Noisy Label Detection | BBC | F1 (5%)19 | 5 | |
| Scene Detection | BBC | AP0.4364 | 5 | |
| Shot Boundary Detection | BBC | F1 Score97.1 | 5 |
Showing 25 of 30 rows