Correctness Prediction on MathQA
66.15AccuracyKMEANS
Evaluation results
| Method | Links | |
|---|---|---|
| KMEANSTrain samples=2562026.01 | 66.15 | |
| KMEANSTrain samples=5122026.01 | 66.09 | |
| EMBEDLLMTrain samples=2562026.01 | 65.95 | |
| IRT-NETTrain samples=10242026.01 | 65.85 | |
| EMBEDLLMTrain samples=5122026.01 | 65.75 | |
| IRT-NETTrain samples=2562026.01 | 65.74 | |
| KMEANSTrain samples=10242026.01 | 65.59 | |
| EMBEDLLMTrain samples=10242026.01 | 65.5 | |
| LOCUSTrain samples=2562026.01 | 65.38 | |
| kNNTrain samples=2562026.01 | 65.25 | |
| LOCUSTrain samples=10242026.01 | 65.22 | |
| EMBEDLLM+Train samples=10242026.01 | 65.22 | |
| IRT-NETTrain samples=5122026.01 | 65.12 | |
| EMBEDLLM+Train samples=2562026.01 | 65.09 | |
| EMBEDLLM+Train samples=5122026.01 | 64.29 | |
| LOCUSTrain samples=5122026.01 | 64.09 | |
| kNNTrain samples=10242026.01 | 62.81 | |
| kNNTrain samples=5122026.01 | 60.47 |