Fact-checking on CheckCOVID
60AccuracyToE
Evaluation Results
| Method | Links | |
|---|---|---|
| ToEBackbone=DeepSeek-V3.22026.06 | 60 | |
| TELLERBackbone=DeepSeek-V3.22026.06 | 56 | |
| ZCoTBackbone=DeepSeek-V3.22026.06 | 52 | |
| TELLERBackbone=GPT-OSS-20B2026.06 | 52 | |
| ToEBackbone=GPT-OSS-20B2026.06 | 48 | |
| STEELBackbone=GPT-OSS-20B2026.06 | 46 | |
| ZCoTBackbone=GPT-OSS-20B2026.06 | 44 | |
| DefGenBackbone=GPT-OSS-20B2026.06 | 40 | |
| STEELBackbone=DeepSeek-V3.22026.06 | 40 | |
| AFacTABackbone=DeepSeek-V3.22026.06 | 36 | |
| DefGenBackbone=DeepSeek-V3.22026.06 | 36 | |
| AdsentBackbone=DeepSeek-V3.22026.06 | 36 | |
| AFacTABackbone=GPT-OSS-20B2026.06 | 32 | |
| DirectBackbone=DeepSeek-V3.22026.06 | 28 | |
| DirectBackbone=GPT-OSS-20B2026.06 | 26 | |
| AdsentBackbone=GPT-OSS-20B2026.06 | 22 |