Correctness Prediction on GSM8k
74.04AccuracyKMEANS
Evaluation Results
| Method | Links | |
|---|---|---|
| KMEANSTrain samples=10242026.01 | 74.04 | |
| kNNTrain samples=10242026.01 | 74 | |
| kNNTrain samples=5122026.01 | 73.92 | |
| KMEANSTrain samples=5122026.01 | 73.71 | |
| LOCUSTrain samples=10242026.01 | 72.85 | |
| LOCUSTrain samples=5122026.01 | 71.75 | |
| EMBEDLLM+Train samples=10242026.01 | 70.94 | |
| IRT-NETTrain samples=10242026.01 | 70.13 | |
| EMBEDLLMTrain samples=10242026.01 | 70.07 | |
| IRT-NETTrain samples=5122026.01 | 68.87 | |
| EMBEDLLM+Train samples=5122026.01 | 68.53 | |
| LOCUSTrain samples=2562026.01 | 66.18 | |
| EMBEDLLM+Train samples=2562026.01 | 65.95 | |
| EMBEDLLMTrain samples=5122026.01 | 65.51 | |
| IRT-NETTrain samples=2562026.01 | 64.23 | |
| kNNTrain samples=2562026.01 | 62.65 | |
| EMBEDLLMTrain samples=2562026.01 | 62.32 | |
| KMEANSTrain samples=2562026.01 | 58.45 |