| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Scientific Reasoning | SciBench | Accuracy44.3 | 33 | |
| Chemistry | SciBench | Accuracy66.4 | 32 | |
| Physics problem solving | Scibench fund | Accuracy74.6 | 24 | |
| Scientific Problem Solving | SciBench-107 | Atkins Score62.5 | 24 | |
| Scientific Reasoning | SciBench Physics | Accuracy82.4 | 20 | |
| Scientific Reasoning | SciBench Chemistry | Accuracy73.2 | 20 | |
| General and STEM reasoning | SciBench | Pass@171.39 | 20 | |
| Uncertainty Calibration | SciBench | AUROC78.7 | 18 | |
| Scientific Problem Solving | SciBench | Pass@2077.46 | 17 | |
| College-level Science Problem Solving | SciBench | Accuracy72.1 | 12 | |
| Scientific Problem Solving | SciBench | Accuracy4 | 12 | |
| Scientific Reasoning | SciBench | Pass@129.64 | 12 | |
| Scientific Reasoning | SciBench | Accuracy7.4 | 10 | |
| Scientific Problem Solving | SciBench | Diff Accuracy65.47 | 6 | |
| Scientific Reasoning | SciBench | Pass@1072.23 | 6 | |
| Science | SciBench chemistry | Score90.61 | 3 |