Multi-domain Science Q&A on SciKnowEval Phys-Chem (test)
58.8Accuracy (Physics)OPCoD
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OPCoDBase Student=Student 2, Domain Strength=Chem-stronger2026.06 | 58.8 | 70.2 | 64.5 | |
| SDPOBase Student=Student 2, Domain Strength=Chem-stronger2026.06 | 56.4 | 69.9 | 63.2 | |
| GRPOBase Student=Student 2, Domain Strength=Chem-stronger2026.06 | 54.3 | 62.8 | 58.6 | |
| OPCoDBase Student=Student 1, Domain Strength=Phys-stronger2026.06 | 54.1 | 58.9 | 56.5 | |
| GRPOBase Student=Student 1, Domain Strength=Phys-stronger2026.06 | 52.6 | 55.4 | 54 | |
| Student 1Domain Strength=Phys-stronger2026.06 | 51.6 | 37.3 | 44.5 | |
| SDPOBase Student=Student 1, Domain Strength=Phys-stronger2026.06 | 51.1 | 56.7 | 53.9 | |
| Student 2Domain Strength=Chem-stronger2026.06 | 48.6 | 56.3 | 52.5 |