Hybrid Retrieval Benchmark — scifact
100 sampled queries, seed 42, warmup 10, concurrency 8. Dense: all-MiniLM-L6-v2.
Sparse: Qdrant/bm25. Colbert: answerai-colbert-small-v1. Cross-encoder: local fastembed
rerank (Xenova/ms-marco-MiniLM-L-6-v2). Dataset: BeIR/scifact-generated-queries,
15.4K passages, one generated query per passage.
recall@20 by quantization config × rescorer (hybrid prefetch, prefetch_limit=100)
| config | colbert | cross-encoder | rrf |
| no-quant (f32) | 93.0 | 92.0 | 89.0 |
| no-quant (f16) | 93.0 | 92.0 | 89.0 |
| no-quant (turbo4) | 92.0 | 91.0 | 90.0 |
| scalar int8 | 93.0 | 92.0 | 89.0 |
| product x16 | 92.0 | 93.0 | 88.0 |
| binary (f32) | 92.0 | 93.0 | 88.0 |
| binary (f16) | 92.0 | 94.0 | 89.0 |
| turbo4 tq1 | 93.0 | 92.0 | 89.0 |
recall / mrr / ndcg by rescorer
recall@20
mrr@20
ndcg@20
(opacity = metric; hue = rescorer)
throughput by rescorer
recall@20 vs prefetch_limit, by rescorer (hybrid, k=20)
colbert · recall@20
cross-encoder · recall@20
rrf · recall@20
throughput vs prefetch_limit, by rescorer (hybrid, k=20)
colbert · qps (log)
cross-encoder · qps (log)
rrf · qps (log)
colbert & cross-encoder, hybrid vs sparse-only prefetch (k=20, prefetch_limit=100)
recall@20
mrr@20
ndcg@20
(opacity = metric; hue = rescorer)
hybrid prefetch
colbertmrr 0.470ndcg 0.581
cross-encodermrr 0.471ndcg 0.580
sparse-only prefetch
colbertmrr 0.478ndcg 0.582
cross-encodermrr 0.469ndcg 0.575
recall@20 vs prefetch_limit, colbert & cross-encoder (sparse-only, k=20)
colbert · recall@20
cross-encoder · recall@20
throughput vs prefetch_limit, colbert & cross-encoder (sparse-only, k=20)
colbert · qps (log)
cross-encoder · qps (log)
mrr@20 by config, colbert rescorer (bold outline = turbo4 datatype)
hybridsparse-only
ndcg@20 by config, colbert rescorer (bold outline = turbo4 datatype)
hybridsparse-only
exact values, colbert rescorer, k=20 prefetch_limit=100
| config | hybrid mrr | hybrid ndcg | sparse-only mrr | sparse-only ndcg |
| no-quant (f32) | 0.4126 | 0.5387 | 0.4711 | 0.5764 |
| no-quant (f16) | 0.5227 | 0.6215 | 0.4851 | 0.5873 |
| no-quant (turbo4) | 0.4876 | 0.5923 | 0.4753 | 0.5785 |
| scalar int8 | 0.4860 | 0.5948 | 0.4815 | 0.5839 |
| product x16 | 0.4336 | 0.5514 | 0.4538 | 0.5633 |
| binary (f32) | 0.4558 | 0.5687 | 0.4844 | 0.5866 |
| binary (f16) | 0.5013 | 0.6030 | 0.4913 | 0.5894 |
| turbo4 tq1 | 0.4627 | 0.5765 | 0.4859 | 0.5869 |