FRAMES
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Frames
70.5Score
7
FRAMES
55.8Evidence Coverage Rate
6
FRAMES
0.834NDCG
5
Frames
70.45Accuracy
5
Frames out-of-domain
0.413F1 Score
4
FRAMES In-Distribution (test)
77.9CPT (90%)
4
FRAMES OOD
68.74CPT 85%
4
FRAMES
88.84CPT (95%)
4
FRAMES
78.61CPT (90%)
4
FRAMES (ID)
60.92CPT (80%)
4
FRAMES (ID queries)
69.41CPT (85%) Score
4
FRAMES
0.887Hypervolume
4
FRAMES OOD
60.73CPT (80%)
4
FRAMES (test)
0.876Hypervolume
4
Frames
37.69F1 Score
4
FRAMES
89.3CPT (95%)
3
Frames (OOD)
57.1Avg@4
3
FRAMES
55.7Accuracy
2
FRAMES Small-scale (evaluation)
3.2Search Count
1