| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Science Question Answering | ScienceQA | Accuracy98.5 | 502 | |
| Visual Question Answering | ScienceQA | Accuracy98.18 | 370 | |
| Science Question Answering | ScienceQA IMG | Accuracy98.2 | 294 | |
| Science Question Answering | ScienceQA (SQA) | Accuracy88.8 | 273 | |
| Science Question Answering | ScienceQA (test) | Average Accuracy98.3 | 245 | |
| Scientific Question Answering | ScienceQA image | Accuracy98 | 184 | |
| Science Question Answering | ScienceQA SQA-IMG | Accuracy92.8 | 139 | |
| Multimodal Science Question Answering | ScienceQA IMG | Accuracy95.78 | 131 | |
| Visual Question Answering | ScienceQA (test) | Accuracy98.2 | 113 | |
| Science Question Answering | ScienceQA SQA-I | Accuracy96.6 | 103 | |
| Question Answering | ScienceQA | Accuracy96 | 77 | |
| Science Question Answering | ScienceQA IMG (test) | Accuracy98.4 | 74 | |
| Multimodal Question Answering | ScienceQA (test) | Accuracy92.53 | 65 | |
| Science Question Answering | ScienceQA | IMG Score88.6 | 64 | |
| Scientific Question Answering | ScienceQA | Accuracy88.6 | 61 | |
| Visual Question Answering | ScienceQA img | Accuracy86.2 | 52 | |
| Science Question Answering | ScienceQA Image | Score74.2 | 51 | |
| Visual Question Answering | ScienceQA image | Accuracy75.1 | 51 | |
| Visual Question Answering | ScienceQA Image (test) | Accuracy96.2 | 45 | |
| Visual Question Answering | ScienceQA (SQA) | SQA Accuracy89.3 | 43 | |
| Multimodal Question Answering | ScienceQA | Accuracy97.8 | 41 | |
| Out-of-scope refusal | ScienceQA out-of-scope (test) | Refusal Rate0 | 40 | |
| Multimodal Science Question Answering | ScienceQA | Overall Average Score88.4 | 36 | |
| Multi-step Reasoning | ScienceQA | Accuracy92.72 | 35 | |
| Visual Question Answering | ScienceQA (SQAI) | Accuracy74.2 | 35 |