LES Leaderboard – Slovene Embedding Benchmark

Lestvica embeddingov za slovenščino

Comparing embedding models on Slovene NLP tasks

Rank	Model	Score	Classification	Clustering	Retrieval
🥇	Qwen/Qwen3-Embedding-8B🤗	55.72	53.33	23.53	90.30
🥈	Snowflake/snowflake-arctic-embed-l-v2.0🤗	55.63	52.35	23.94	90.59
🥉	openai/text-embedding-3-large	55.58	55.71	24.37	86.66
4	BAAI/bge-m3🤗	55.08	52.45	22.65	90.15
5	Qwen/Qwen3-Embedding-4B🤗	55.05	51.96	24.48	88.73
6	intfloat/multilingual-e5-large-instruct🤗	54.08	52.76	23.93	85.55
7	openai/text-embedding-3-small	53.37	52.07	23.80	84.24
8	Lajavaness/bilingual-embedding-small🤗	50.95	48.49	23.08	81.26
9	intfloat/multilingual-e5-small🤗	50.41	47.64	20.85	82.72
10	Qwen/Qwen3-Embedding-0.6B🤗	50.11	46.61	21.16	82.55
11	sentence-transformers/paraphrase-multilingual-mpnet-base-v2🤗	46.27	51.15	21.28	66.40
12	sentence-transformers/LaBSE🤗	44.71	48.85	19.86	65.43
13	cjvt/GaMS-1B🤗	43.30	55.29	27.83	46.78
14	intfloat/e5-large-v2🤗	39.79	39.85	15.49	64.03
15	Snowflake/snowflake-arctic-embed-l🤗	37.55	38.25	13.62	60.77
16	NovaSearch/stella/en/400M/v5🤗	35.43	41.60	17.92	46.78
17	intfloat/e5-small-v2🤗	33.93	35.95	14.15	51.70
18	cjvt/GaMS-2B🤗	29.87	50.13	21.39	18.08
19	EMBEDDIA/sloberta🤗	28.29	49.81	18.55	16.52
20	sentence-transformers/all-MiniLM-L6-v2🤗	25.67	32.66	14.60	29.76

🥇 1st🥈 2nd🥉 3rdBold = best in column

Scores are shown as percentages

About the Overall score

The overall score is the mean of the main Classification, Retrieval, and Clustering scores.