MMLU, ScienceQA, GSM8K, and HumanEval
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Continual instruction tuning | MMLU, ScienceQA, GSM8K, and HumanEval | Average Accuracy74.6 | 3 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Continual instruction tuning | MMLU, ScienceQA, GSM8K, and HumanEval | Average Accuracy74.6 | 3 |