Abductive Reasoning on Disamb-QA
93AccuracyPACS
Evaluation Results
| Method | Links | |
|---|---|---|
| PACSBackbone=Llama 3.3 70B2026.05 | 93 | |
| SC-20Backbone=Llama 3.3 70B2026.05 | 92 | |
| COTBackbone=Llama 3.3 70B2026.05 | 89 | |
| PACSBackbone=Llama 3-Instruct 8B2026.05 | 88 | |
| If-BeamBackbone=Llama 3.3 70B2026.05 | 88 | |
| ARGOSBackbone=Llama 3.3 70B2026.05 | 83 | |
| SC-20Backbone=Llama 3-Instruct 8B2026.05 | 81 | |
| ARGOSBackbone=Llama 3-Instruct 8B2026.05 | 80 | |
| LoTBackbone=Llama 3.3 70B2026.05 | 78 | |
| COTBackbone=Llama 3-Instruct 8B2026.05 | 74 | |
| If-BeamBackbone=Llama 3-Instruct 8B2026.05 | 72 | |
| LoTBackbone=Llama 3-Instruct 8B2026.05 | 71 | |
| LLM-TreeBackbone=Llama 3-Instruct 8B2026.05 | 56 | |
| LLM-TreeBackbone=Llama 3.3 70B2026.05 | 56 |