| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-task Language Model Evaluation | TÜLU Evaluation Suite (MMLU, TQA, PopQA, BBH, DROP, CHE, CHE+, GSM8K, MATH, IFEval) 2/3 | MMLU Accuracy62.1 | 24 | |
| Membership Inference Attack | TÜLU | N-Gram Coverage (Cov.)85 | 7 | |
| General Capability Evaluation | Tülu General Benchmarks 3 | MMLU45 | 6 | |
| Safety Evaluation | Tülu Safety Benchmarks 3 | DAN Score89 | 6 |