Fact-Checking on FEVER (Balanced Accuracy)
91.9Balanced AccuracyWKGFC
Evaluation Results
| Method | Links | |
|---|---|---|
| WKGFCMethod Category=Specialized Methods, Evidence Retrieval Protocol=Self-retrieved2026.02 | 91.9 | |
| FIREMethod Category=Specialized Methods, Evidence Retrieval Protocol=Self-retrieved2026.02 | 90.6 | |
| HerOMethod Category=Specialized Methods, Evidence Retrieval Protocol=Self-retrieved2026.02 | 67.5 | |
| Qwen2.5 72BMethod Category=Small-scale LLMs, Evidence Retrieval Protocol=Self-retrieved2026.02 | 58.1 | |
| Llama3.3 70BMethod Category=Small-scale LLMs, Evidence Retrieval Protocol=Self-retrieved2026.02 | 57.4 | |
| Claude 3.5-SonnetMethod Category=Large-scale LLMs, Evidence Retrieval Protocol=Self-retrieved2026.02 | 57.1 | |
| GPT-4oMethod Category=Large-scale LLMs, Evidence Retrieval Protocol=Self-retrieved2026.02 | 55.3 | |
| Gemini-2.5-flashMethod Category=Large-scale LLMs, Evidence Retrieval Protocol=Self-retrieved2026.02 | 54.8 | |
| DeepSeek-V3 67BMethod Category=Large-scale LLMs, Evidence Retrieval Protocol=Self-retrieved2026.02 | 53.5 | |
| GPT-4Method Category=Large-scale LLMs, Evidence Retrieval Protocol=Self-retrieved2026.02 | 51.4 | |
| Qwen2.5 7BMethod Category=Small-scale LLMs, Evidence Retrieval Protocol=Self-retrieved2026.02 | 50.1 | |
| Llama3 8BMethod Category=Small-scale LLMs, Evidence Retrieval Protocol=Self-retrieved2026.02 | 48.2 |