Fact-Checking on Reveal
89.8Balanced AccuracyGraphEval
Evaluation Results
| Method | Links | |
|---|---|---|
| GraphEval2025.02 | 89.8 | |
| GraphCheck-Llama3.3 70BBackbone=Llama3.3 70B2025.02 | 89.7 | |
| MiniCheck2025.02 | 88.8 | |
| GraphCheck-Qwen2.5 72BBackbone=Qwen2.5 72B2025.02 | 88 | |
| Llama3.3 70BBackbone=Llama3.3 70B2025.02 | 86.8 | |
| Qwen2.5 72BBackbone=Qwen2.5 72B2025.02 | 85.9 | |
| AlignScore2025.02 | 85.3 |