Text Retrieval On Mteb

nDCG@10

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	nDCG@10	Paper Title
BERT	10.59	MTEB: Massive Text Embedding Benchmark
ST5-XL	38.47	MTEB: Massive Text Embedding Benchmark
MPNet-multilingual	35.34	MTEB: Massive Text Embedding Benchmark
SPECTER	15.88	MTEB: Massive Text Embedding Benchmark
MiniLM-L12	42.69	MTEB: Massive Text Embedding Benchmark
GTR-Large	47.42	MTEB: Massive Text Embedding Benchmark
coCondenser-msmarco	32.96	MTEB: Massive Text Embedding Benchmark
ST5-Large	36.71	MTEB: Massive Text Embedding Benchmark
Glove	21.62	MTEB: Massive Text Embedding Benchmark
LaBSE	18.99	MTEB: Massive Text Embedding Benchmark
MiniLM-L6	41.95	MTEB: Massive Text Embedding Benchmark
SGPT-5.8B-nli	32.34	MTEB: Massive Text Embedding Benchmark
MPNet	43.81	MTEB: Massive Text Embedding Benchmark
GTR-Base	44.67	MTEB: Massive Text Embedding Benchmark
GTR-XXL	48.48	MTEB: Massive Text Embedding Benchmark
LASER2	7.93	MTEB: Massive Text Embedding Benchmark
ST5-XXL	42.24	MTEB: Massive Text Embedding Benchmark
SGPT-BLOOM-7.1B-msmarco	48.21	MTEB: Massive Text Embedding Benchmark
SGPT-1.3B-msmarco	44.49	MTEB: Massive Text Embedding Benchmark
GTR-XL	47.96	MTEB: Massive Text Embedding Benchmark

0 of 30 row(s) selected.