| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| 14 vision tasks | Average Absolute Accuracy94.3 | 42 | 1mo ago | ||
| 20 vision tasks | Average Absolute Accuracy94.7 | 40 | 1mo ago | ||
| Multi-task Category-level Evaluation Suite (Instruction Following, Math, Multilingual, Safety) | METIS | Average Score93.5 | 9 | 1mo ago | |
| MMLU, SciQA, and GSM8K (test) | NeuroLoRA | Average (Individual)74.3 | 4 | 4mo ago |