Correctness Prediction on MedQA
61.29AccuracyKMEANS
Evaluation Results
| Method | Links | |
|---|---|---|
| KMEANSTrain samples=5122026.01 | 61.29 | |
| KMEANSTrain samples=10242026.01 | 61.2 | |
| IRT-NETTrain samples=10242026.01 | 61.06 | |
| LOCUSTrain samples=10242026.01 | 60.89 | |
| IRT-NETTrain samples=2562026.01 | 60.57 | |
| kNNTrain samples=10242026.01 | 60.55 | |
| EMBEDLLMTrain samples=10242026.01 | 60.45 | |
| EMBEDLLMTrain samples=2562026.01 | 60.39 | |
| EMBEDLLM+Train samples=10242026.01 | 60.19 | |
| kNNTrain samples=5122026.01 | 60.1 | |
| LOCUSTrain samples=5122026.01 | 60.03 | |
| kNNTrain samples=2562026.01 | 59.73 | |
| IRT-NETTrain samples=5122026.01 | 59.69 | |
| KMEANSTrain samples=2562026.01 | 59.39 | |
| LOCUSTrain samples=2562026.01 | 59.36 | |
| EMBEDLLM+Train samples=5122026.01 | 58.89 | |
| EMBEDLLM+Train samples=2562026.01 | 58.83 | |
| EMBEDLLMTrain samples=5122026.01 | 58.78 |