| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| CommonGen (test) | ROUGE-L54.45 | 31 | 1mo ago | ||
| CommonGen Hard | Qwen3-235B-A22B | Accuracy87.12 | 9 | 1mo ago | |
| CommonGen (dev) | T5-3b + VAWI-SBS | BLEU-347.67 | 8 | 1mo ago | |
| DimonGen (test) | Quality4.7 | 4 | 1mo ago | ||
| Visual Commonsense Graphs (VCG) (val) | KM-BART | Before Score61.3 | 4 | 1mo ago | |
| Event2Mind (test) | EA-VQ-VAE | Accuracy50.72 | 3 | 1mo ago |