Fact-checking on AVeriTeC (test)
0.48Hu-METEOR (Q only)HerO
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| HerO2024.10 | 0.48 | 0.35 | 0.57 | |
| Llama 3.1 70BPipeline configuration=full-featured2024.10 | 0.47 | 0.29 | 0.42 | |
| GPT-4oPipeline configuration=full-featured2024.10 | 0.46 | 0.32 | 0.5 | |
| CTU AIC2024.10 | 0.46 | 0.32 | 0.5 | |
| GPT-4oPipeline configuration=simplified2024.10 | 0.45 | 0.3 | 0.47 | |
| TUDA_MAI_02024.10 | 0.45 | 0.34 | 0.63 | |
| Claude-3.5-SonnetPipeline configuration=full-featured2024.10 | 0.42 | 0.3 | 0.46 | |
| AVeriTeC baseline2024.10 | 0.24 | 0.2 | 0.11 | |
| Baseline2024.10 | 0.24 | 0.2 | 0.11 |