MTEB · Multilingual (MTEB(Multilingual, v2))

MTEB · Multilingual (MTEB(Multilingual, v2)) is run by MTEB / embeddings-benchmark. It has ranked 86 models, of which the catalogue holds 31, scoring from 0.5523 to 0.7427 on meanTask (mean score, 0-1).

measured by MTEB / embeddings-benchmark · the board itself

Place	Model	Metric	Score
1stof 86	harrier-oss-v1-27b	meanTask (mean score, 0-1)	0.7427
2ndof 86	KaLM-Embedding-Gemma3-12B-2511	meanTask (mean score, 0-1)	0.7232
3rdof 86	Qwen3 8B (embeddings)	meanTask (mean score, 0-1)	0.7058
3rdof 86	llama-embed-nemotron-8b	meanTask (mean score, 0-1)	0.6946
4thof 86	Seed1.6-embedding-1215	meanTask (mean score, 0-1)	0.7026
6thof 86	Qwen3-Embedding-4B	meanTask (mean score, 0-1)	0.6945
7thof 86	harrier-oss-v1-0.6b	meanTask (mean score, 0-1)	0.6901
8thof 86	F2LLM-v2-14B	meanTask (mean score, 0-1)	0.6874
9thof 86	Gemini Embedding	meanTask (mean score, 0-1)	0.6837
10thof 86	F2LLM-v2-8B	meanTask (mean score, 0-1)	0.6809
11thof 86	Octen-Embedding-8B	meanTask (mean score, 0-1)	0.6784
12thof 86	F2LLM-v2-4B	meanTask (mean score, 0-1)	0.6706
13thof 86	jina-embeddings-v5-text-small	meanTask (mean score, 0-1)	0.67
14thof 86	jina-embeddings-v5-omni-small	meanTask (mean score, 0-1)	0.67
15thof 86	harrier-oss-v1-270m	meanTask (mean score, 0-1)	0.6655
16thof 86	jina-embeddings-v5-text-nano	meanTask (mean score, 0-1)	0.6552
17thof 86	jina-embeddings-v5-omni-nano	meanTask (mean score, 0-1)	0.6552
18thof 86	F2LLM-v2-1.7B	meanTask (mean score, 0-1)	0.6521
19thof 86	Qwen3-Embedding-0.6B	meanTask (mean score, 0-1)	0.6434
20thof 86	ICT-TIME-and-Querit-embedding-v1	meanTask (mean score, 0-1)	0.6378
21stof 86	BidirLM-1.7B-Embedding	meanTask (mean score, 0-1)	0.6354
22ndof 86	BOOM_4B_v1	meanTask (mean score, 0-1)	0.6352
23rdof 86	BidirLM-Omni-2.5B-Embedding	meanTask (mean score, 0-1)	0.635
24thof 86	Multilingual-e5-large-instruct	meanTask (mean score, 0-1)	0.6322
25thof 86	BidirLM-1B-Embedding	meanTask (mean score, 0-1)	0.6321
26thof 86	F2LLM-v2-0.6B	meanTask (mean score, 0-1)	0.6274
27thof 86	gte-Qwen2-7B-instruct	meanTask (mean score, 0-1)	0.6251
28thof 86	Text Multilingual Embedding 002	meanTask (mean score, 0-1)	0.6216
29thof 86	embeddinggemma-300m	meanTask (mean score, 0-1)	0.6115
30thof 86	GritLM-7B	meanTask (mean score, 0-1)	0.6092
72ndof 86	F2LLM-v2-80M	meanTask (mean score, 0-1)	0.5523

Place

Model

Metric

Score

1stof 86

harrier-oss-v1-27b

meanTask (mean score, 0-1)

0.7427

2ndof 86

KaLM-Embedding-Gemma3-12B-2511

meanTask (mean score, 0-1)

0.7232