Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Information Retrieval on LongMemEval-S (challenge subset n=150)
Loading...
59.4
Recall@1
RRF(BM25, late)
54.304
55.627
56.95
58.273
Jun 2, 2026
Recall@1
Recall@5
NDCG@5
Updated 1mo ago
Evaluation Results
Method
Method
Links
Recall@1
Recall@5
NDCG@5
RRF(BM25, late)
Encoder=all-MiniLM-L6-...
2026.06
59.4
95.6
93.2
BM25 ⊕ late
Encoder=all-MiniLM-L6-...
2026.06
59.4
95.9
93
BM25
Encoder=all-MiniLM-L6-v2
2026.06
58.9
94.8
91.6
Dense, late (top-3)
Encoder=all-MiniLM-L6-...
2026.06
56.9
95.1
90.8
Dense, late (max-sim)
Encoder=all-MiniLM-L6-...
2026.06
56.8
95.3
90.6
Dense, early (mean)
Encoder=all-MiniLM-L6-...
2026.06
54.5
92
87.6
Feedback
Search any
task
Search any
task