Multi-domain Science Q&A on SciKnowEval Chem-Mat (test)
71.3Chemistry AccuracyOPCoD
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OPCoDBase Student=Student 1, Domain Strength=Chem-stronger2026.06 | 71.3 | 69.8 | 70.6 | |
| SDPOBase Student=Student 1, Domain Strength=Chem-stronger2026.06 | 70.9 | 65.8 | 68.4 | |
| GRPOBase Student=Student 1, Domain Strength=Chem-stronger2026.06 | 62 | 65.6 | 63.8 | |
| OPCoDBase Student=Student 2, Domain Strength=Mat-stronger2026.06 | 57.5 | 66.4 | 62 | |
| GRPOBase Student=Student 2, Domain Strength=Mat-stronger2026.06 | 57.3 | 65.2 | 61.2 | |
| Student 1Domain Strength=Chem-stronger2026.06 | 56.3 | 56.1 | 56.2 | |
| SDPOBase Student=Student 2, Domain Strength=Mat-stronger2026.06 | 55.4 | 60 | 57.7 | |
| Student 2Domain Strength=Mat-stronger2026.06 | 37.6 | 65.1 | 51.4 |