Quality Estimation on GSM8k
0.642BCESigmoid Head
Evaluation Results
| Method | Links | |
|---|---|---|
| Sigmoid HeadModel=Olmo2026.01 | 0.642 | |
| Monte Carlo Seq. Entropy SigmoidModel=Olmo2026.01 | 0.798 | |
| Monte Carlo Seq. Entropy SoftmaxModel=Olmo2026.01 | 15.241 | |
| LLM Self JudgeModel=Olmo2026.01 | 16.408 |