MTEB Leaderboard

Massive Text Embedding Benchmark (MTEB) Leaderboard - Compare embedding models across multiple tasks

Rank	Model	Model Size (M)	Memory (GB)	Dimensions	Max Tokens	Average (56)	Classification (12)	Clustering (11)	Pair Class. (3)	Reranking (4)	Retrieval (15)	STS (10)	Summary (1)
1	NV-Embed-v2	7,851	29.25	4,096	32,768	72.31	90.37	58.46	88.67	60.65	62.65	84.31	30.70
2	jasper_en_vision_language_v1	N/A	N/A	N/A	N/A	72.02	88.49	58.04	88.07	60.91	63.12	84.67	31.42
4	bge-en-icl	7,111	26.49	4,096	32,768	71.67	88.95	57.89	88.14	59.86	62.16	84.24	30.77
3	bge-en-icl	7,111	26.49	4,096	32,768	71.67	88.95	57.89	88.14	59.86	62.16	84.24	30.77
5	stella_en_1.5B_v5	1,543	5.75	8,192	131,072	71.19	87.63	57.69	88.07	61.21	61.01	84.51	31.49
6	SFR-Embedding-2_R	7,111	26.49	4,096	32,768	70.31	89.05	56.17	88.07	60.14	60.18	81.26	30.71
11	gte-Qwen2-7B-instruct-Q4-mlx	1,190	4.43	3,584	131,072	70.24	86.58	56.92	85.79	61.42	60.25	83.04	31.35
10	gte-Qwen2-7B-instruct	7,613	28.36	3,584	131,072	70.24	86.58	56.92	85.79	61.42	60.25	83.04	31.35
9	gte-Qwen2-7B-instruct-fp16	7,069	26.33	3,584	131,072	70.24	86.58	56.92	85.79	61.42	60.25	83.04	31.35
8	gte-Qwen2-7B-instruct-Q4_K_M-GGUF	N/A	N/A	N/A	N/A	70.24	86.58	56.92	85.79	61.42	60.25	83.04	31.35
7	gte-Qwen2-7B-instruct	7,613	28.36	3,584	131,072	70.24	86.58	56.92	85.79	61.42	60.25	83.04	31.35
12	stella_en_400M_v5	435	1.62	8,192	8,192	70.11	86.67	56.70	87.74	60.16	58.97	84.22	31.66
13	bge-multilingual-gemma2	9,242	34.43	3,584	8,192	69.88	88.08	54.65	85.84	59.72	59.24	83.88	31.20
14	NV-Embed-v1	7,851	29.25	4,096	32,768	69.32	87.35	52.80	86.91	60.54	59.36	82.84	31.20
15	voyage-large-2-instruct	N/A	N/A	1,024	16,000	68.23	81.49	53.35	89.25	60.09	58.28	84.31	30.84
16	Linq-Embed-Mistral	7,111	26.49	4,096	32,768	68.17	80.20	51.42	88.35	60.29	60.19	84.97	30.98
17	hui-embedding	N/A	N/A	N/A	N/A	68.02	85.71	54.36	87.28	60.25	54.14	83.74	30.17
18	KaLM-embedding-multilingual-max-instruct-v1	N/A	N/A	N/A	N/A	67.60	88.46	50.71	86.37	57.87	54.62	82.86	27.86
19	SFR-Embedding-Mistral	7,111	26.49	4,096	32,768	67.56	78.33	51.67	88.54	60.64	59.00	85.05	31.16
20	Zeta-Alpha-E5-Mistral	7,111	26.49	4,096	32,768	67.55	78.77	51.89	88.19	59.02	59.50	84.24	31.42
21	gte-Qwen1.5-7B-instruct	7,099	26.45	4,096	32,768	67.35	79.60	55.83	87.41	60.13	56.24	82.42	31.46
23	gte-Qwen2-1.5B-instruct	1,776	6.62	1,536	131,072	67.16	82.47	48.75	87.51	59.98	58.29	82.73	31.17
22	gte-Qwen2-1.5B-instruct-Q4_K_M-GGUF	N/A	N/A	N/A	N/A	67.16	82.47	48.75	87.51	59.98	58.29	82.73	31.17
24	voyage-lite-02-instruct	1,220	4.54	1,024	4,000	67.13	79.25	52.42	86.87	58.24	56.60	85.79	31.01
25	GritLM-7B-vllm	7,242	26.98	4,096	32,768	66.76	79.46	50.61	87.16	60.49	57.41	83.35	30.37
26	e5-mistral-7b-instruct	7,111	26.49	4,096	32,768	66.63	78.47	50.26	88.34	60.21	56.89	84.63	31.40
27	GritLM-7B	7,240	26.97	4,096	N/A	66.58	78.65	50.61	87.29	60.48	57.36	83.35	30.39
28	speed-embedding-7b-instruct	7,111	26.49	4,096	32,768	66.51	78.44	49.28	88.19	60.76	56.50	85.48	31.06
29	e5-mistral-7b-instruct	7,111	26.49	4,096	32,768	66.40	77.37	50.26	88.42	60.21	56.87	84.62	31.53
30	text-embedding-004	1,200	4.47	768	2,048	66.31	81.17	47.48	87.61	58.90	55.70	85.07	32.63
31	TDTE	N/A	N/A	N/A	N/A	65.96	77.17	47.86	88.27	60.46	57.05	84.82	30.83
32	BinGSE-Meta-Llama-3-8B-Instruct	N/A	N/A	N/A	N/A	65.72	76.05	47.18	88.84	59.28	57.38	85.31	31.19
33	GritLM-8x7B	46,703	173.98	4,096	32,768	65.66	78.53	50.14	84.97	59.80	55.09	83.26	29.82
34	jina-embeddings-v3	572	2.13	1,024	8,194	65.51	82.58	45.21	84.01	58.13	53.88	85.81	29.71
36	learning2_model	434	1.62	1,024	8,192	65.39	77.75	47.96	84.53	58.50	57.91	81.43	30.91
35	gte-large-en-v1.5	434	1.62	1,024	8,192	65.39	77.75	47.96	84.53	58.50	57.91	81.43	30.91
37	LLM2Vec-Meta-Llama-3-supervised	7,505	27.96	4,096	8,192	65.01	75.92	46.45	87.79	59.68	56.63	83.58	30.94
38	cde-small-v1	143	0.53	768	512	65.00	81.71	48.32	84.69	56.75	53.27	81.63	31.23
39	KaLM-embedding-multilingual-mini-instruct-v1.5	494	1.84	896	131,072	64.94	84.74	47.82	83.26	55.41	51.65	82.24	25.23
40	LLM2Vec-Mistral-supervised	7,111	26.49	4,096	32,768	64.80	76.63	45.54	87.99	58.42	55.99	84.09	29.96
41	KaLM-embedding-multilingual-mini-instruct-v1	494	1.84	896	131,072	64.74	85.10	45.46	83.92	55.58	51.88	82.40	27.88
43	mxbai-embed-large-v1	335	1.25	1,024	512	64.68	75.64	46.71	87.20	60.11	54.39	85.00	32.71
42	echo-mistral-7b-instruct-lasttoken	7,111	26.49	4,096	32,768	64.68	77.43	46.32	87.34	58.14	55.52	82.56	30.73
44	UAE-Large-V1	335	1.25	1,024	512	64.64	75.58	46.73	87.25	59.88	54.66	84.54	32.03
45	text-embedding-3-large	N/A	N/A	3,072	8,191	64.59	75.45	49.01	85.72	59.16	55.44	81.73	29.92
46	voyage-lite-01-instruct	N/A	N/A	1,024	4,000	64.49	74.79	47.40	86.57	59.74	55.58	82.93	30.97
47	Cohere-embed-english-v3.0	N/A	N/A	N/A	N/A	64.47	76.49	47.43	85.84	58.01	55.00	82.62	30.18
48	text-embedding-004-256	1,200	4.47	256	2,048	64.37	79.00	45.07	87.29	57.78	52.44	84.93	32.36
49	GIST-large-Embedding-v0	335	1.25	1,024	512	64.34	76.01	46.55	86.70	60.05	53.44	84.59	30.96
50	bge-large-en-v1.5	335	1.25	1,024	512	64.23	75.97	46.08	87.12	60.03	54.29	83.11	31.61
51	b1ade-embed	335	1.25	1,024	512	64.21	75.16	46.46	87.07	60.00	53.30	85.04	31.93
52	MUG-B-1.6	335	1.25	1,024	512	64.20	74.50	46.93	87.14	59.97	53.46	84.99	32.12
53	LLM2Vec-Llama-2-7b-chat-hf-mntp-supervised	6,607	24.61	4,096	4,096	64.14	76.33	45.24	88.03	57.38	54.60	83.73	28.49
54	gte-base-en-v1.5	137	0.51	768	8,192	64.11	77.17	46.82	85.33	57.66	54.09	81.97	31.17
55	Cohere-embed-multilingual-v3.0	N/A	N/A	1,024	512	64.01	76.01	46.60	86.15	57.86	53.84	83.15	30.99
56	GIST-Embedding-v0	109	0.41	768	512	63.71	76.03	46.21	86.32	59.37	52.31	83.51	30.87
57	multilingual-e5-large-instruct	560	2.09	1,024	514	63.61	73.32	47.07	86.24	58.92	52.64	85.03	30.46
58	bge-base-en-v1.5	109	0.41	768	512	63.56	75.53	45.81	86.55	58.86	53.25	82.40	31.07
59	ember-v1	335	1.25	1,024	512	63.54	75.99	45.58	87.37	60.04	51.92	83.34	30.82
60	sf_model_e5	335	1.25	1,024	512	63.34	73.96	46.61	86.85	59.86	51.80	83.85	31.61
61	mxbai-embed-2d-large-v1	335	1.25	1,024	512	63.25	74.14	46.07	85.89	58.94	51.42	84.90	31.55
62	gte-large	335	1.25	1,024	512	63.13	73.33	46.84	85.00	59.13	52.22	83.35	31.66
63	NoInstruct-small-Embedding-v0	33	0.12	384	512	63.12	75.97	44.95	84.99	58.30	51.99	83.00	30.60
64	GIST-small-Embedding-v0	33	0.12	384	512	62.72	76.11	44.82	84.68	58.56	50.43	83.03	31.14
65	stella-base-en-v2	55	0.20	768	512	62.61	75.28	44.90	86.45	58.78	50.10	83.02	32.52
67	nomic-embed-text-v1	137	0.51	768	8,192	62.39	74.12	43.91	85.15	55.69	52.81	82.06	30.08
66	gte-base	109	0.41	768	512	62.39	73.01	46.20	84.57	58.61	51.14	82.30	31.17
68	nomic-embed-text-v1.5	137	0.51	768	8,192	62.28	73.55	43.93	84.61	55.78	53.01	81.94	30.40
69	text-embedding-3-small	N/A	N/A	1,536	8,191	62.26	73.21	46.65	85.04	56.72	51.08	81.58	31.12
70	e5-large-v2	335	1.25	1,024	512	62.20	75.24	44.26	86.03	56.61	50.56	82.05	30.19
71	concat-e5-small-bge-small-01	N/A	N/A	N/A	N/A	62.18	73.33	44.36	86.09	58.14	51.40	82.24	30.07
73	bge-small-en-v1.5	33	0.12	384	512	62.17	74.14	43.82	84.92	58.36	51.68	81.59	30.12
72	bge-small-retail-finetuned	33	0.12	384	512	62.17	74.14	43.82	84.92	58.36	51.68	81.59	30.12
74	bge-small-en	N/A	N/A	N/A	N/A	62.11	74.37	44.31	83.78	57.97	51.82	80.72	30.53
75	Cohere-embed-english-light-v3.0	N/A	N/A	N/A	N/A	62.01	74.31	44.64	85.05	56.09	51.34	80.92	31.29
76	text-embedding-3-large-256	N/A	N/A	256	8,191	62.00	71.97	46.23	84.22	57.99	51.66	81.04	29.92
77	nomic-embed-text-v1.5-512	138	0.51	512	8,192	61.96	73.24	43.71	84.59	55.65	52.40	81.70	30.47
78	KaLM-embedding-multilingual-mini-v1	494	1.84	896	131,072	61.87	72.88	45.37	84.09	55.86	50.81	82.42	29.15
79	LLM2Vec-Sheared-Llama-supervised	1,280	4.77	2,048	4,096	61.85	72.21	43.57	86.21	55.38	51.44	83.58	30.01
81	MedEmbed-small-v0.1	33	0.12	384	512	61.79	71.83	43.45	84.71	58.38	52.49	81.48	30.49
80	instructor-xl	1,241	4.62	768	512	61.79	73.12	44.74	86.62	57.29	49.26	83.06	32.32
82	instructor-large	335	1.25	768	512	61.59	73.86	45.29	85.89	57.54	47.57	83.15	31.84
83	BinGSE-Sheared-LLaMA	N/A	N/A	N/A	N/A	61.58	70.56	43.59	86.61	54.16	52.28	83.10	30.79
84	e5-base-v2	110	0.41	768	512	61.56	73.84	44.10	85.73	55.91	50.29	81.05	30.28
85	e5-base-4k	112	0.42	768	4,096	61.50	73.84	43.80	85.73	55.91	50.29	81.05	30.28
86	e5-large	335	1.25	1,024	512	61.42	73.14	43.33	85.94	56.53	49.99	82.06	30.97
88	gte-multilingual-base	305	1.14	768	8,192	61.40	70.89	44.31	84.24	57.47	51.08	82.11	30.58
87	onnx-gte-multilingual-base	N/A	N/A	N/A	N/A	61.40	70.89	44.31	84.24	57.47	51.08	82.11	30.58
90	gte-small	33	0.12	384	512	61.36	72.31	44.89	83.54	57.70	49.46	82.07	30.42
89	nomic-embed-text-v1-ablated	137	0.51	768	8,192	61.36	73.65	43.70	84.59	53.32	51.43	80.22	31.28
91	nomic-embed-text-v1.5-256	138	0.51	256	8,192	61.04	72.10	43.16	84.09	55.18	50.81	81.34	30.05
92	text-embedding-ada-002	N/A	N/A	1,536	8,191	60.99	70.93	45.90	84.89	56.32	49.25	80.97	30.80
93	multilingual-e5-large	560	2.09	1,024	514	60.89	71.77	41.23	84.75	55.96	51.40	81.62	29.64
94	udever-bloom-7b1	7,069	26.33	4,096	2,048	60.63	72.13	40.81	85.40	55.91	49.34	83.01	30.97
95	snowflake-arctic-embed-l-v2.0	568	2.12	1,024	8,194	60.50	67.18	41.65	83.00	55.78	55.65	78.62	30.51
96	e5-base	109	0.41	768	512	60.44	72.63	42.11	85.09	55.70	48.75	80.96	31.01
97	jina-embeddings-v2-base-en	137	0.51	768	8,192	60.38	73.45	41.73	85.38	56.98	47.87	80.70	31.60

About MTEB

The Massive Text Embedding Benchmark (MTEB) evaluates embedding models across 56 datasets covering various tasks like classification, clustering, retrieval, and more.

Dataset Categories

• Classification (12 datasets)
• Clustering (11 datasets)
• Pair Classification (3 datasets)
• Reranking (4 datasets)
• Retrieval (15 datasets)
• STS (10 datasets)
• Summarization (1 dataset)

GitHub Repository

HuggingFace Leaderboard