Question Answering on OpenBook-QA (Accuracy and Performance Gain)
91.6AccuracyMistral Small 24B Inst 2501
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Mistral Small 24B Inst 2501Classifier=Self-labeled2026.01 | 91.6 | -0.2 | |
| Mistral Small 24B Inst 2501Classifier=Majority-labeled2026.01 | 91.2 | -0.6 | |
| Mistral Small 24B Base 2501Classifier=Self-labeled2026.01 | 85.6 | 0.4 | |
| Mistral Small 24B Base 2501Classifier=Majority-labeled2026.01 | 85.6 | 0.4 | |
| Llama 3.1 8B InstClassifier=Self-labeled2026.01 | 82.4 | 1.4 | |
| Llama 3.1 8B InstClassifier=Majority-labeled2026.01 | 81.8 | 0.8 | |
| Llama 3.1 8BClassifier=Self-labeled2026.01 | 76.6 | 1 | |
| Llama 3.1 8BClassifier=Majority-labeled2026.01 | 76.6 | 1 | |
| Llama 3.2 3B InstClassifier=Majority-labeled2026.01 | 76.4 | 0.2 | |
| Llama 3.2 3B InstClassifier=Self-labeled2026.01 | 76.2 | 0 | |
| Mistral 7B Inst v0.3Classifier=Self-labeled2026.01 | 74.8 | 1.2 | |
| Mistral 7B Inst v0.3Classifier=Majority-labeled2026.01 | 74.2 | 0.6 | |
| Mistral Nemo Base 2407Classifier=Majority-labeled2026.01 | 73.4 | 0.2 | |
| Mistral Nemo Base 2407Classifier=Self-labeled2026.01 | 73 | -0.2 | |
| Mistral Nemo Inst 2407Classifier=Self-labeled2026.01 | 70 | 4.2 | |
| Mistral 7B v0.3Classifier=Self-labeled2026.01 | 68.8 | 0.6 | |
| Mistral 7B v0.3Classifier=Majority-labeled2026.01 | 68.4 | 0.2 | |
| Mistral Nemo Inst 2407Classifier=Majority-labeled2026.01 | 66.2 | 0.4 | |
| Llama 3.2 3BClassifier=Self-labeled2026.01 | 65.4 | 0.6 | |
| Llama 3.2 3BClassifier=Majority-labeled2026.01 | 64.8 | 0 | |
| Llama 3.2 1B InstClassifier=Self-labeled2026.01 | 59.8 | 0 | |
| Llama 3.2 1B InstClassifier=Majority-labeled2026.01 | 59.6 | -0.2 | |
| Llama 3.2 1BClassifier=Self-labeled2026.01 | 47.4 | 3.8 | |
| Llama 3.2 1BClassifier=Majority-labeled2026.01 | 44 | 0.4 |