Claim Verification on PrimeFacts Two Class
81Macro F1Llama-3.3-70B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Llama-3.3-70BExtraction Mode=C (open)2026.05 | 81 | 86 | |
| Qwen3-235BExtraction Mode=C (open)2026.05 | 81 | 81 | |
| Qwen3-32BExtraction Mode=C (open)2026.05 | 76 | 75 | |
| Llama-4-ScoutExtraction Mode=C (open)2026.05 | 76 | 79 | |
| Llama-3.3-70BExtraction Mode=B (decontext.)2026.05 | 74 | 78 | |
| Qwen3-8BExtraction Mode=C (open)2026.05 | 73 | 72 | |
| Qwen3-14BExtraction Mode=C (open)2026.05 | 72 | 77 | |
| Llama-4-ScoutExtraction Mode=B (decontext.)2026.05 | 70 | 65 | |
| Qwen3-235BExtraction Mode=B (decontext.)2026.05 | 69 | 70 | |
| Llama-3.3-70BExtraction Mode=A (linked)2026.05 | 68 | 93 | |
| Qwen3-32BExtraction Mode=B (decontext.)2026.05 | 66 | 64 | |
| Llama-4-ScoutExtraction Mode=A (linked)2026.05 | 65 | 74 | |
| Qwen3-8BExtraction Mode=B (decontext.)2026.05 | 63 | 64 | |
| Qwen3-235BExtraction Mode=A (linked)2026.05 | 62 | 82 | |
| Qwen3-14BExtraction Mode=B (decontext.)2026.05 | 61 | 65 | |
| Qwen3-32BExtraction Mode=A (linked)2026.05 | 59 | 71 | |
| Qwen3-8BExtraction Mode=A (linked)2026.05 | 58 | 82 | |
| Qwen3-14BExtraction Mode=A (linked)2026.05 | 57 | 78 | |
| Baseline2026.05 | 39 | — |