Seed1.5-Embedding

Introduction

We introduce Seed1.5-Embedding, a powerful embedding model built on top of our pretrained LLM. It stands out with the following key features:

• Generalist: Excels in general-purpose embedding tasks, achieving state-of-the-art performance on MTEB benchmark in both Chinese and English.

• Reasoning Expertise: Demonstrates strong capability in complex query understanding and reasoning, delivering state-of-the-art results on BRIGHT benchmark.

• Flexibility: Supports multiple embedding dimensions — [2048, 1024, 512, 256] — with minimal performance degradation at lower dimensions.

This is a temporary model card. The model's API will be publicly available soon. Please stay tuned! :)

Performance

MTEB_v2 (English)

Model	AVG	Classification	Clustering	Pair Classification	Reranking	Retrieval	STS	Summarization
Linq-Embed-Mistral	69.80	83.00	54.07	88.44	49.44	60.14	84.69	37.26
NV-Embed-v2	69.81	87.19	47.66	88.69	49.61	62.84	83.82	35.21
jasper-en-vision-language-v1	71.41	90.27	60.52	88.14	50.00	56.05	84.37	37.19
gemini-embedding-exp-03-07	73.30	90.05	59.39	87.70	48.59	64.35	85.29	38.28
RELLE	73.59	90.06	58.20	88.74	49.46	67.15	84.04	38.02
Seed1.5-Embedding	74.76	89.88	60.83	87.39	50.67	67.45	87.23	36.44

C-MTEB (Chinese)

Model	AVG	Classification	Clustering	Pair Classification	Reranking	Retrieval	STS
bge-multilingual-gemma2	67.64	75.31	59.30	86.67	68.28	73.73	55.19
gte-Qwen2-7B-instruct	71.62	75.77	66.06	87.48	68.92	75.71	65.20
xiaobu-embedding-v2	72.36	76.53	65.17	91.87	72.58	76.50	64.18
Conan-embedding-v1	72.50	76.77	66.33	91.66	72.76	76.67	63.67
Conan-embedding-v2	74.24	76.47	68.84	92.44	74.41	78.31	65.48
Seed1.5-Embedding	74.87	79.37	71.11	89.57	70.14	79.33	66.56

BRIGHT

Model	BRIGHT AVG
SFR-Embedding-Mistral	18.3
text-embedding-004	20.0
GritLM-7B	21.0
gte-Qwen2-7B-instruct	22.5
ReasonIR-8B	24.4
Seed1.5-Embedding	27.2