Multi-task Category-level Evaluation Suite
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-task Model Merging | Multi-task Category-level Evaluation Suite (Instruction Following, Math, Multilingual, Safety) | Average Score93.5 | 9 | |
| Multi-task Model Merging Evaluation | Multi-task Category-level Evaluation Suite Qwen-3-4B | Average Score1.18 | 9 |
Showing 2 of 2 rows