lightonai/Reason-ModernColBERT
Reason-ModernColBERT is a late interaction model trained on the reasonir-hq dataset. It achieves extremely competitive performance on the BRIGHT benchmark aimed at evaluating reasoning-intensive retrieval performance, outperforming all existing models up to 7B (more than 45 times its size) and ev...
Benchmarks
CQADupstackPhysicsRetrieval
Duplicate question retrieval from StackExchange Physics
Corpus: 38,314 Queries: 1,039
Quality
ndcg at 10 0.4382
map at 10 0.3824
mrr at 10 0.4397
Performance L4 b1 c16
Corpus 29.6K tok/s
Corpus p50 61.0ms
Query 2.9K tok/s
Query p50 57.8ms
CosQA
Code search with natural language queries
Corpus: 6,267 Queries: 500
Quality
ndcg at 10 0.3443
map at 10 0.2641
mrr at 10 0.2620
Performance L4 b1 c16
Corpus 12.7K tok/s
Corpus p50 60.8ms
Query 1.6K tok/s
Query p50 59.1ms
FiQA2018
Financial opinion mining and question answering
Corpus: 57,599 Queries: 648
Quality
ndcg at 10 0.4081
map at 10 0.3315
mrr at 10 0.4936
Performance L4 b1 c16
Corpus 30.7K tok/s
Corpus p50 71.5ms
Query 3.0K tok/s
Query p50 59.6ms
LegalBenchConsumerContractsQA
Question answering on consumer contracts
Corpus: 153 Queries: 396
Quality
ndcg at 10 0.7777
map at 10 0.7287
mrr at 10 0.7307
Performance L4 b1 c16
Corpus 50.0K tok/s
Corpus p50 144.2ms
Query 4.2K tok/s
Query p50 60.7ms
NFCorpus
Biomedical literature search from NutritionFacts.org
Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3580
map at 10 0.1342
mrr at 10 0.5702
Performance L4 b1 c16
Corpus 44.6K tok/s
Corpus p50 89.2ms
Query 1.4K tok/s
Query p50 56.3ms
SCIDOCS
Citation prediction, document classification, and recommendation for scientific papers
Corpus: 25,656 Queries: 1,000
Quality
ndcg at 10 0.1710
map at 10 0.0986
mrr at 10 0.2991
Performance L4 b1 c16
Corpus 27.0K tok/s
Corpus p50 80.8ms
Query 2.8K tok/s
Query p50 60.8ms
SciFact
Scientific claim verification using research literature
Corpus: 5,183 Queries: 300
Quality
ndcg at 10 0.7380
map at 10 0.6953
mrr at 10 0.7076
Performance L4 b1 c16
Corpus 41.6K tok/s
Corpus p50 83.7ms
Query 4.1K tok/s
Query p50 60.4ms
StackOverflowQA
Programming question answering from Stack Overflow
Corpus: 19,931 Queries: 1,994
Quality
ndcg at 10 0.5934
map at 10 0.5591
mrr at 10 0.5591
Performance L4 b1 c16
Corpus 35.4K tok/s
Corpus p50 84.4ms
Query 62.1K tok/s
Query p50 75.3ms