MTEB · English — Reranking task-type split

MTEB · English — Reranking task-type split is run by MTEB / embeddings-benchmark. It has ranked 238 models, of which the catalogue holds 22, scoring from 0.4859 to 0.5327 on scoresByTaskType.Reranking (0-1).

measured by MTEB / embeddings-benchmark · the board itself

Place	Model	Metric	Score
1stof 238	Yuan-embedding-2.0-en	scoresByTaskType.Reranking (0-1)	0.5327
1stof 238	ingot-8b-r3	scoresByTaskType.Reranking (0-1)	0.5093
2ndof 238	QZhou-Embedding	scoresByTaskType.Reranking (0-1)	0.5177
2ndof 238	Jasper-Token-Compression-600M	scoresByTaskType.Reranking (0-1)	0.506
3rdof 238	Qwen3 8B (embeddings)	scoresByTaskType.Reranking (0-1)	0.5156
5thof 238	Qwen3-Embedding-4B	scoresByTaskType.Reranking (0-1)	0.5076
5thof 238	Seed1.5-Embedding	scoresByTaskType.Reranking (0-1)	0.5067
6thof 238	LGAI-Embedding-Preview	scoresByTaskType.Reranking (0-1)	0.4913
8thof 238	gte-Qwen2-7B-instruct	scoresByTaskType.Reranking (0-1)	0.5047
8thof 238	Seed1.6-embedding	scoresByTaskType.Reranking (0-1)	0.5028
9thof 238	F2LLM-v2-14B	scoresByTaskType.Reranking (0-1)	0.5032
9thof 238	Gemini Embedding	scoresByTaskType.Reranking (0-1)	0.4859
10thof 238	speed-embedding-7b-instruct	scoresByTaskType.Reranking (0-1)	0.5029
10thof 238	F2LLM-v2-8B	scoresByTaskType.Reranking (0-1)	0.5021
13thof 238	stella_en_1.5B_v5	scoresByTaskType.Reranking (0-1)	0.5019
14thof 238	SFR-Embedding-Mistral	scoresByTaskType.Reranking (0-1)	0.5015
15thof 238	voyage-large-2-instruct	scoresByTaskType.Reranking (0-1)	0.5009
16thof 238	F2LLM-v2-4B	scoresByTaskType.Reranking (0-1)	0.5007
17thof 238	F2LLM-4B	scoresByTaskType.Reranking (0-1)	0.5005
18thof 238	jasper_en_vision_language_v1	scoresByTaskType.Reranking (0-1)	0.5
19thof 238	F2LLM-1.7B	scoresByTaskType.Reranking (0-1)	0.4984
20thof 238	e5-mistral-7b-instruct	scoresByTaskType.Reranking (0-1)	0.4978

Place

Model

Metric

Score

1stof 238

Yuan-embedding-2.0-en

scoresByTaskType.Reranking (0-1)

0.5327

1stof 238

ingot-8b-r3

scoresByTaskType.Reranking (0-1)

0.5093