Hugging Face's logo

Spaces:
MTEB-BR
/
leaderboard
Running

App Files Community
tardellirs commited on
Commit
728e2e8
·
verified ·
1 Parent(s): b98ba67

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +85 -56
README.md CHANGED
@@ -8,64 +8,93 @@ pinned: true
8
  license: apache-2.0
9
  short_description: Massive Text Embedding Benchmark for Brazilian Portuguese
10
  tags:
11
- - leaderboard
12
- - benchmark
13
- - embeddings
14
- - portuguese
15
- - brazilian-portuguese
16
- - mteb
17
- - retrieval
18
- - sentence-transformers
19
  datasets:
20
- - MTEB-BR/mteb-pt-results
21
  models:
22
- - Qwen/Qwen3-Embedding-8B
23
- - Octen/Octen-Embedding-8B
24
- - google/embeddinggemma-300m
25
- - microsoft/harrier-oss-v1-27b
26
- - Qwen/Qwen3-Embedding-4B
27
- - tencent/KaLM-Embedding-Gemma3-12B-2511
28
- - codefuse-ai/F2LLM-v2-8B
29
- - microsoft/harrier-oss-v1-0.6b
30
- - codefuse-ai/F2LLM-v2-14B
31
- - intfloat/multilingual-e5-large-instruct
32
- - SamilPwC-AXNode-GenAI/PwC-Embedding_expr
33
- - BAAI/bge-m3
34
- - Qwen/Qwen3-Embedding-0.6B
35
- - telepix/PIXIE-Rune-v1.0
36
- - ufca-llms/jua-4B-mixed
37
- - Octen/Octen-Embedding-0.6B
38
- - jinaai/jina-embeddings-v5-text-small
39
- - intfloat/multilingual-e5-large
40
- - Snowflake/snowflake-arctic-embed-l-v2.0
41
- - ibm-granite/granite-embedding-311m-multilingual-r2
42
- - intfloat/multilingual-e5-base
43
- - PORTULAN/serafim-335m-portuguese-pt-sentence-encoder-ir
44
- - PORTULAN/serafim-100m-portuguese-pt-sentence-encoder-ir
45
- - PORTULAN/serafim-900m-portuguese-pt-sentence-encoder-ir
46
- - microsoft/harrier-oss-v1-270m
47
- - jinaai/jina-embeddings-v5-text-nano
48
- - intfloat/multilingual-e5-small
49
- - ibm-granite/granite-embedding-107m-multilingual
50
- - codefuse-ai/F2LLM-v2-160M
51
- - rufimelo/Legal-BERTimbau-sts-large
52
- - ibm-granite/granite-embedding-97m-multilingual-r2
53
- - Alibaba-NLP/gte-Qwen2-1.5B-instruct
54
- - sentence-transformers/paraphrase-multilingual-mpnet-base-v2
55
- - stjiris/bert-large-portuguese-cased-legal-mlm-sts-v1.0
56
- - sentence-transformers/LaBSE
57
- - rufimelo/Legal-BERTimbau-sts-large-ma-v3
58
- - neuralmind/bert-base-portuguese-cased
59
- - neuralmind/bert-large-portuguese-cased
60
- - mixedbread-ai/mxbai-embed-large-v1
61
- - PORTULAN/albertina-900m-portuguese-ptbr-encoder
62
- - sentence-transformers/all-MiniLM-L12-v2
63
- - nvidia/llama-embed-nemotron-8b
64
- - PORTULAN/albertina-100m-portuguese-ptbr-encoder
65
- - sentence-transformers/all-mpnet-base-v2
66
- - sentence-transformers/all-MiniLM-L6-v2
67
- - BidirLM/BidirLM-1.7B-Embedding
68
- - sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  ---
70
 
71
  # MTEB(por) — Brazilian Portuguese Massive Text Embedding Benchmark
 
8
  license: apache-2.0
9
  short_description: Massive Text Embedding Benchmark for Brazilian Portuguese
10
  tags:
11
+ - leaderboard
12
+ - benchmark
13
+ - embeddings
14
+ - portuguese
15
+ - brazilian-portuguese
16
+ - mteb
17
+ - retrieval
18
+ - sentence-transformers
19
  datasets:
20
+ - MTEB-BR/mteb-pt-results
21
  models:
22
+ - Alibaba-NLP/gte-Qwen2-1.5B-instruct
23
+ - Alibaba-NLP/gte-Qwen2-7B-instruct
24
+ - BAAI/bge-m3
25
+ - BAAI/bge-small-en-v1.5
26
+ - BidirLM/BidirLM-0.6B-Embedding
27
+ - BidirLM/BidirLM-1.7B-Embedding
28
+ - BidirLM/BidirLM-1B-Embedding
29
+ - ICT-TIME-and-Querit/BOOM_4B_v1
30
+ - Linq-AI-Research/Linq-Embed-Mistral
31
+ - MTEB-BR/baseline-random-encoder
32
+ - Mihaiii/Ivysaur
33
+ - Octen/Octen-Embedding-0.6B
34
+ - Octen/Octen-Embedding-8B
35
+ - PORTULAN/albertina-900m-portuguese-ptbr-encoder
36
+ - PORTULAN/serafim-100m-portuguese-pt-sentence-encoder
37
+ - PORTULAN/serafim-100m-portuguese-pt-sentence-encoder-ir
38
+ - PORTULAN/serafim-335m-portuguese-pt-sentence-encoder
39
+ - PORTULAN/serafim-335m-portuguese-pt-sentence-encoder-ir
40
+ - PORTULAN/serafim-900m-portuguese-pt-sentence-encoder
41
+ - PORTULAN/serafim-900m-portuguese-pt-sentence-encoder-ir
42
+ - Qwen/Qwen3-Embedding-0.6B
43
+ - Qwen/Qwen3-Embedding-4B
44
+ - Qwen/Qwen3-Embedding-8B
45
+ - Salesforce/SFR-Embedding-2_R
46
+ - Salesforce/SFR-Embedding-Mistral
47
+ - SamilPwC-AXNode-GenAI/PwC-Embedding_expr
48
+ - Snowflake/snowflake-arctic-embed-l-v2.0
49
+ - avsolatorio/GIST-all-MiniLM-L6-v2
50
+ - avsolatorio/NoInstruct-small-Embedding-v0
51
+ - codefuse-ai/F2LLM-0.6B
52
+ - codefuse-ai/F2LLM-v2-0.6B
53
+ - codefuse-ai/F2LLM-v2-1.7B
54
+ - codefuse-ai/F2LLM-v2-14B
55
+ - codefuse-ai/F2LLM-v2-160M
56
+ - codefuse-ai/F2LLM-v2-330M
57
+ - codefuse-ai/F2LLM-v2-4B
58
+ - codefuse-ai/F2LLM-v2-80M
59
+ - codefuse-ai/F2LLM-v2-8B
60
+ - google/embeddinggemma-300m
61
+ - ibm-granite/granite-embedding-107m-multilingual
62
+ - ibm-granite/granite-embedding-311m-multilingual-r2
63
+ - ibm-granite/granite-embedding-97m-multilingual-r2
64
+ - intfloat/e5-mistral-7b-instruct
65
+ - intfloat/e5-small-v2
66
+ - intfloat/multilingual-e5-base
67
+ - intfloat/multilingual-e5-large
68
+ - intfloat/multilingual-e5-large-instruct
69
+ - intfloat/multilingual-e5-small
70
+ - jinaai/jina-embeddings-v5-text-small
71
+ - lfcc/medlink-bi-encoder
72
+ - microsoft/harrier-oss-v1-0.6b
73
+ - microsoft/harrier-oss-v1-270m
74
+ - microsoft/harrier-oss-v1-27b
75
+ - mixedbread-ai/mxbai-embed-large-v1
76
+ - neuralmind/bert-base-portuguese-cased
77
+ - neuralmind/bert-large-portuguese-cased
78
+ - nvidia/llama-embed-nemotron-8b
79
+ - rufimelo/Legal-BERTimbau-sts-large
80
+ - rufimelo/Legal-BERTimbau-sts-large-ma-v3
81
+ - sentence-transformers/LaBSE
82
+ - sentence-transformers/all-MiniLM-L12-v2
83
+ - sentence-transformers/all-MiniLM-L6-v2
84
+ - sentence-transformers/all-mpnet-base-v2
85
+ - sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
86
+ - sentence-transformers/paraphrase-multilingual-mpnet-base-v2
87
+ - stjiris/bert-large-portuguese-cased-legal-mlm-mkd-nli-sts-v1
88
+ - stjiris/bert-large-portuguese-cased-legal-mlm-sts-v1.0
89
+ - stjiris/bert-large-portuguese-cased-legal-tsdae-gpl-nli-sts-MetaKD-v0
90
+ - tardellirs/brazembed-pt-br
91
+ - telepix/PIXIE-Rune-v1.0
92
+ - tencent/KaLM-Embedding-Gemma3-12B-2511
93
+ - thenlper/gte-small
94
+ - ufca-llms/Qwen3-Embedding-0.6B-jua-V2
95
+ - ufca-llms/jua-4B-legal-only
96
+ - ufca-llms/jua-4B-mixed
97
+ - ulysses-camara/legal-bert-pt-br
98
  ---
99
 
100
  # MTEB(por) — Brazilian Portuguese Massive Text Embedding Benchmark