Error Detection on Bamboogle Full
100PrecisionIC-IDK
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| IC-IDKBase Model=Gemini Flash2026.02 | 100 | 5 | 10 | 53 | |
| IC-IDKBase Model=Gemini Pro2026.02 | 100 | 6 | 10 | 53 | |
| DBA-IBase Model=Qwen 2.5 72B2026.02 | 97 | 73 | 83 | 84 | |
| AYSBase Model=Mistral 7B2026.02 | 95 | 38 | 54 | 63 | |
| DBA-ABase Model=Qwen3-32B2026.02 | 95 | 89 | 92 | 84 | |
| DBA-ABase Model=Mistral 7B2026.02 | 94 | 43 | 59 | 64 | |
| IC-IDKBase Model=Qwen3-32B2026.02 | 94 | 15 | 26 | 55 | |
| DBA-IBase Model=Qwen3-32B2026.02 | 94 | 89 | 91 | 81 | |
| DBA-ABase Model=Qwen 2.5 72B2026.02 | 94 | 82 | 88 | 86 | |
| Ensemble-ABase Model=Mistral 7B2026.02 | 93 | 62 | 75 | 68 | |
| DBA-ABase Model=Llama 3.1 8B2026.02 | 93 | 83 | 88 | 80 | |
| DBA-IBase Model=Llama 3.1 8B2026.02 | 93 | 69 | 79 | 75 | |
| IC-IDKBase Model=Mistral 7B2026.02 | 92 | 22 | 36 | 56 | |
| Ensemble-IBase Model=Mistral 7B2026.02 | 92 | 57 | 70 | 65 | |
| AYSBase Model=Llama 3.1 8B2026.02 | 92 | 50 | 65 | 68 | |
| DBA-IBase Model=Mistral 7B2026.02 | 91 | 40 | 56 | 60 | |
| Ensemble-IBase Model=Llama 3.1 8B2026.02 | 91 | 84 | 88 | 77 | |
| AYSBase Model=Qwen3-32B2026.02 | 90 | 56 | 69 | 65 | |
| Ensemble-ABase Model=Qwen3-32B2026.02 | 90 | 90 | 90 | 73 | |
| Ensemble-IBase Model=Qwen3-32B2026.02 | 90 | 91 | 91 | 74 | |
| Ensemble-IBase Model=Qwen 2.5 72B2026.02 | 90 | 85 | 87 | 82 | |
| Ensemble-ABase Model=Llama 3.1 8B2026.02 | 89 | 89 | 89 | 76 | |
| AYSBase Model=Qwen 2.5 72B2026.02 | 87 | 63 | 73 | 71 | |
| Ensemble-ABase Model=Qwen 2.5 72B2026.02 | 87 | 90 | 89 | 81 | |
| IC-IDKBase Model=Llama 3.1 8B2026.02 | 83 | 5 | 10 | 51 | |
| IC-IDKBase Model=Qwen 2.5 72B2026.02 | 79 | 87 | 82 | 68 | |
| AYSBase Model=Gemini Pro2026.02 | 78 | 39 | 52 | 68 | |
| AYSBase Model=Gemini Flash2026.02 | 67 | 40 | 50 | 68 | |
| DBA-IBase Model=Gemini Pro2026.02 | 67 | 44 | 53 | 70 | |
| Ensemble-IBase Model=Gemini Pro2026.02 | 67 | 56 | 61 | 75 | |
| Ensemble-ABase Model=Gemini Pro2026.02 | 63 | 67 | 65 | 80 | |
| DBA-IBase Model=Gemini Flash2026.02 | 57 | 60 | 58 | 76 | |
| DBA-ABase Model=Gemini Pro2026.02 | 57 | 44 | 50 | 69 | |
| Ensemble-IBase Model=Gemini Flash2026.02 | 52 | 70 | 60 | 79 | |
| Ensemble-ABase Model=Gemini Flash2026.02 | 45 | 75 | 57 | 79 | |
| DBA-ABase Model=Gemini Flash2026.02 | 43 | 60 | 50 | 72 |