Factuality Evaluation on Evidence Inference Dataset 2.0
2.0778Rank 1 ScoreCERA
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| CERAJudge=GPT5.42026.05 | 2.0778 | 1.9671 | 1.8737 | |
| CERAJudge=Jury2026.05 | 1.9015 | 1.7453 | 1.6152 | |
| CERAJudge=Mistral Large 32026.05 | 1.8544 | 1.6628 | 1.5016 | |
| CERAJudge=Qwen3-Max2026.05 | 1.7724 | 1.6059 | 1.4703 | |
| ContrieverJudge=GPT5.42026.05 | 1.4379 | 1.4489 | 1.4207 | |
| ContrieverJudge=Qwen3-Max2026.05 | 1.1957 | 1.2114 | 1.1696 | |
| ContrieverJudge=Jury2026.05 | 1.1881 | 1.1839 | 1.1367 | |
| ContrieverJudge=Mistral Large 32026.05 | 0.9306 | 0.8914 | 0.8199 |