Abductive Natural Language Inference on AlphaNLI n=300 per condition (test)
95Accuracy
Flat
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.06 | 95 | 0 | 98 | 28.6 | - | |
2026.06 | 93 | 0 | 100 | 0 | - | |
2026.06 | 93 | 0 | 100 | 0 | - | |
2026.06 | 92.7 | 6.3 | 99 | 4.8 | - | |
2026.06 | 92.3 | 0 | 100 | 0 | - | |
2026.06 | 92.3 | 0 | 100 | 0 | - | |
2026.06 | 92.3 | 16.7 | 98 | 13 | - | |
2026.06 | 92 | 0 | 97.7 | 13 | - | |
2026.06 | 92 | 0 | 99 | 0 | - | |
2026.06 | 92 | 6.3 | 99 | 0 | - | |
2026.06 | 91.7 | 10 | 97.3 | 8.7 | - | |
2026.06 | 91.7 | 27.3 | 98 | 4.8 | - | |
2026.06 | 90.3 | 0 | 96.3 | 8.7 | - | |
2026.06 | 90.3 | 10 | 96.3 | 8.7 | - | |
2026.06 | 89.3 | 34 | 95.3 | 27.5 | - | |
2026.06 | 88 | 0 | 95.3 | 22.5 | - | |
2026.06 | 88 | 15.3 | 96 | 20 | - | |
2026.06 | 87.3 | 0 | 96 | 17.5 | - | |
2026.06 | 87.3 | 15.3 | 95.3 | 20 | - | |
2026.06 | 86.7 | 0 | 100 | 0 | - | |
2026.06 | 86.7 | 0 | 100 | 0 | - | |
2026.06 | - | - | - | - | 92 | |
2026.06 | - | - | - | - | 90.3 | |
2026.06 | - | - | - | - | 92.3 | |
2026.06 | - | - | - | - | 92.3 | |
2026.06 | - | - | - | - | 90.3 | |
2026.06 | - | - | - | - | 91.7 | |
2026.06 | - | - | - | - | 92.3 | |
2026.06 | - | - | - | - | 87.3 | |
2026.06 | - | - | - | - | 88 | |
2026.06 | - | - | - | - | 86.7 | |
2026.06 | - | - | - | - | 86.7 | |
2026.06 | - | - | - | - | 87.3 | |
2026.06 | - | - | - | - | 88 | |
2026.06 | - | - | - | - | 89.3 | |
2026.06 | - | - | - | - | 95 | |
2026.06 | - | - | - | - | 92 | |
2026.06 | - | - | - | - | 93 | |
2026.06 | - | - | - | - | 93 | |
2026.06 | - | - | - | - | 92.7 | |
2026.06 | - | - | - | - | 92 | |
2026.06 | - | - | - | - | 91.7 |