Scientific claim-citation verification on SCITANCE 2-class (test)
93.2Micro-F1Claude Sonnet 4.6
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Claude Sonnet 4.6Evidence=Abstract2026.05 | 93.2 | 93.2 | |
| GPT-4Evidence=Abstract2026.05 | 91.9 | 91.9 | |
| GPT-5.4Evidence=Abstract2026.05 | 87.8 | 87.8 | |
| Gemini 2.5 FlashEvidence=Abstract2026.05 | 86.5 | 86.4 |