| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| CreaCOF | SCDiff | Votes165 | 20 | 2mo ago | |
| GraphRAG-Bench Medical Dataset | HyperSU | Accuracy69.92 | 9 | 25d ago | |
| GraphRAG-Bench | HyperSU | ACC56.94 | 9 | 25d ago | |
| GraphRAG-Bench Medical | HyperSU | Recall93.56 | 9 | 25d ago | |
| GraphRAG-Bench | HyperSU | Recall (Rec)78.52 | 9 | 25d ago | |
| CreativeBench Explore | GEPA | Pass@127.88 | 9 | 4mo ago | |
| CreativeBench Combo | AlphaEvolve | Pass@139.01 | 9 | 4mo ago | |
| Creative Generation Benchmarks (test) | DICAI | Novelty0.1351 | 8 | 26d ago | |
| Retrieval Quality Evaluation (test) | FlowRAG | Recall94.81 | 8 | 1mo ago | |
| Nature Mixture | CAT | VLM Judge Score8.82 | 4 | 4mo ago | |
| Furniture Design | CAT | VLM-as-a-Judge Score8.2 | 3 | 4mo ago | |
| Architecture Design | CAT | VLM Judge Score8.44 | 3 | 4mo ago |