Claim Verification on ChartCheck
0.643Macro F1MEVER
Evaluation Results
| Method | Links | |
|---|---|---|
| MEVEREvidence Setting=Gold2026.02 | 0.643 | |
| MEVEREvidence Setting=Retrieved2026.02 | 0.641 | |
| ChartGemmaEvidence Setting=Retrieved2026.02 | 0.639 | |
| ChartGemmaEvidence Setting=Gold2026.02 | 0.633 | |
| TransformerXH++Evidence Setting=Gold2026.02 | 0.632 | |
| TransformerXHEvidence Setting=Gold2026.02 | 0.629 | |
| MR2RetrievedEvidence Setting=Gold2026.02 | 0.627 | |
| TransformerXH++Evidence Setting=Retrieved2026.02 | 0.626 | |
| CCNEvidence Setting=Gold2026.02 | 0.626 | |
| CCNEvidence Setting=Retrieved2026.02 | 0.626 | |
| UniChartEvidence Setting=Gold2026.02 | 0.626 | |
| KGATEvidence Setting=Gold2026.02 | 0.624 | |
| CORRECTEvidence Setting=Gold2026.02 | 0.623 | |
| MR2RetrievedEvidence Setting=Retrieved2026.02 | 0.623 | |
| UniChartEvidence Setting=Retrieved2026.02 | 0.623 | |
| JustiLMEvidence Setting=Retrieved2026.02 | 0.623 | |
| TransformerXHEvidence Setting=Retrieved2026.02 | 0.62 | |
| MEVER w/o imagesEvidence Setting=Retrieved2026.02 | 0.619 | |
| RAVEvidence Setting=Gold2026.02 | 0.618 | |
| MEVER w/o imagesEvidence Setting=Gold2026.02 | 0.616 | |
| CORRECTEvidence Setting=Retrieved2026.02 | 0.615 | |
| CausalWalkEvidence Setting=Retrieved2026.02 | 0.613 | |
| ESCNetEvidence Setting=Retrieved2026.02 | 0.613 | |
| ECENetEvidence Setting=Retrieved2026.02 | 0.613 | |
| JustiLMEvidence Setting=Gold2026.02 | 0.613 | |
| ECENetEvidence Setting=Gold2026.02 | 0.609 | |
| ESCNetEvidence Setting=Gold2026.02 | 0.607 | |
| MultiKE-GATEvidence Setting=Retrieved2026.02 | 0.606 | |
| MultiKE-GATEvidence Setting=Gold2026.02 | 0.605 | |
| KGATEvidence Setting=Retrieved2026.02 | 0.604 | |
| CausalWalkEvidence Setting=Gold2026.02 | 0.604 | |
| RAVEvidence Setting=Retrieved2026.02 | 0.603 | |
| MochegModelEvidence Setting=Retrieved2026.02 | 0.578 | |
| MochegModelEvidence Setting=Gold2026.02 | 0.567 | |
| ChartBERTEvidence Setting=Gold2026.02 | 0.557 | |
| GPT-4oEvidence Setting=Retrieved2026.02 | 0.498 | |
| GPT-4oEvidence Setting=Gold2026.02 | 0.439 | |
| ChartBERTEvidence Setting=Retrieved2026.02 | 0.409 |