Temporal Question Answering on TempReason OBQA-L2
48EM
DeepSeek-V3-AdapTime
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 48 | 52.1 | |
2026.04 | 45.8 | 50.8 | |
2026.04 | 45.4 | 52.5 | |
2026.04 | 45.1 | 50.8 | |
2026.04 | 44.8 | 49.1 | |
2026.04 | 44.3 | 47.2 | |
2026.04 | 42.4 | 52.2 | |
2026.04 | 37.4 | 54.9 | |
2026.04 | 33.6 | 51.6 | |
2026.04 | 32.7 | 50.9 | |
2026.04 | 29.1 | 37.9 | |
2026.04 | 26 | 45 | |
2026.04 | 23.9 | 33.9 | |
2026.04 | 22.6 | 30.6 | |
2026.04 | 18.7 | 26.8 | |
2026.04 | 18.5 | 26.1 | |
2026.04 | 3.8 | 10 |