Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Retrieval on Overall (Musique, HotpotQA, NarrativeQA, DetectiveQA)
Loading...
56.64
Avg Recall@3
QRRanker-4B
39.9168
44.2584
48.6
52.9416
Feb 12, 2026
Avg Recall@3
Avg Recall@5
Avg Recall@10
Updated 3mo ago
Evaluation Results
Method
Method
Links
Avg Recall@3
Avg Recall@5
Avg Recall@10
QRRanker-4B
method_category=Rerank...
2026.02
56.64
63.62
72.13
Qwen-Reranker-4B (trained)
method_category=Rerank...
2026.02
51.61
59.41
68.82
QRHeads-4B (out-of-box)
method_category=Rerank...
2026.02
50.33
58.09
67.59
Qwen-Reranker-4B (out-of-box)
method_category=Rerank...
2026.02
47.91
54.82
63.77
GroupRank-32B*
method_category=Rerank...
2026.02
47.82
57.16
66.95
SFT-Embedding-8B
method_category=Embedd...
2026.02
42.16
49.73
59.85
Qwen3-Embedding-8B
method_category=Embedd...
2026.02
41.25
48.13
57.8
Qwen3-Embedding-4B
method_category=Embedd...
2026.02
40.56
47.62
56.83
Feedback
Search any
task
Search any
task