Question Answering on TriviaQA (Exact Match AUC)
81.3Exact Match AUCCOCOA
Evaluation Results
| Method | Links | |
|---|---|---|
| COCOAModel=Gemma-3-12B2026.01 | 81.3 | |
| COCOAModel=Qwen3-30B-A3B2026.01 | 81.1 | |
| MSPModel=Gemma-3-12B2026.01 | 80.3 | |
| MSPModel=Qwen3-30B-A3B2026.01 | 80.3 | |
| RBayesModel=Gemma-3-4B2026.01 | 78.5 | |
| COCOAModel=Gemma-3-4B2026.01 | 78.4 | |
| SEModel=Gemma-3-4B2026.01 | 78 | |
| KLEModel=Gemma-3-4B2026.01 | 77.5 | |
| SARModel=Gemma-3-12B2026.01 | 77.4 | |
| COCOAModel=Qwen3-4B2026.01 | 77.2 | |
| KLEModel=Gemma-3-12B2026.01 | 76.9 | |
| MSPModel=Qwen3-4B2026.01 | 76.9 | |
| MSPModel=Gemma-3-4B2026.01 | 76.8 | |
| RBayesModel=Gemma-3-12B2026.01 | 76.4 | |
| SEModel=Gemma-3-12B2026.01 | 76.1 | |
| SARModel=Gemma-3-4B2026.01 | 74.3 | |
| SARModel=Qwen3-30B-A3B2026.01 | 74.1 | |
| KLEModel=Qwen3-30B-A3B2026.01 | 73.8 | |
| KLEModel=Qwen3-4B2026.01 | 73.6 | |
| RBayesModel=Qwen3-4B2026.01 | 73.6 | |
| RBayesModel=Qwen3-30B-A3B2026.01 | 73.6 | |
| SARModel=Qwen3-4B2026.01 | 73 | |
| SEModel=Qwen3-30B-A3B2026.01 | 73 | |
| SEModel=Qwen3-4B2026.01 | 71.3 | |
| P(True)Model=Gemma-3-12B2026.01 | 64.4 | |
| P(True)Model=Qwen3-4B2026.01 | 64.1 | |
| P(True)Model=Qwen3-30B-A3B2026.01 | 62.2 | |
| P(True)Model=Gemma-3-4B2026.01 | 60.9 |