| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Question Answering | ARC Challenge | Accuracy96.3 | 906 | |
| Question Answering | ARC Challenge | Accuracy (ARC)87.3 | 631 | |
| Question Answering | ARC Easy | Accuracy98.2 | 597 | |
| Question Answering | ARC-E | Accuracy95.23 | 544 | |
| Question Answering | ARC Easy | Normalized Acc96.4 | 420 | |
| Science Question Answering | ARC Challenge | Accuracy96 | 354 | |
| Question Answering | ARC-C | Accuracy94.1 | 283 | |
| Multiple Choice Question Answering | ARC Easy | Accuracy99.7 | 269 | |
| Reasoning | ARC | Accuracy94.5 | 269 | |
| Science Question Answering | ARC-C | Accuracy96.3 | 268 | |
| Commonsense Reasoning | ARC Challenge | Accuracy97.35 | 259 | |
| Commonsense Reasoning | ARC-E | Accuracy96.56 | 249 | |
| Question Answering | ARC Easy | Accuracy90.48 | 246 | |
| Reasoning | ARC Easy | Accuracy96.63 | 242 | |
| Science Question Answering | ARC-E | Accuracy97.53 | 240 | |
| Question Answering | ARC | Accuracy94.6 | 230 | |
| Commonsense Reasoning | ARC-C | Accuracy96.3 | 225 | |
| Science Question Answering | ARC Easy | Accuracy98 | 162 | |
| Question Answering | ARC (test) | Accuracy90.5 | 153 | |
| Common-sense reasoning | ARC easy | ARC (easy) Accuracy93.27 | 149 | |
| Multiple-choice Question Answering | ARC Challenge | Acc74.7 | 133 | |
| Scientific Reasoning | ARC Challenge | Accuracy92.5 | 121 | |
| Question Answering | ARC-C | Accuracy0.71 | 116 | |
| Reasoning | ARC-c | Accuracy (ARC-c)96.3 | 113 | |
| Science Question Answering | ARC Challenge | Accuracy93 | 111 |