Benchmark Almanac

Bank Question Corpus

Alibaba-NLP/gte-Qwen2-7B-instruct 0.81 tops its leaderboard Qwen3-Embedding-8B 0.76 leads the models we track
Not in model cards

Models determine whether two Chinese customer service questions ask for the same thing. The authors reserved 10,000 labeled pairs for testing.

The MTEB leaderboard reports test scores for 101 model names. Its score measures the rank correlation between predicted similarity and the binary intent labels.

Released
September 2018
Kind
Finance
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
Chinese
In and out
Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Last model added
June 2025
Scores refreshed
November 20th, 2026
101
Entries on its own leaderboard, 4 models we track

Alibaba-NLP/gte-Qwen2-7B-instruct tops the leaderboard with 0.81 Qwen3-Embedding-8B leads with 0.76 among models released by June 2025

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Qwen3-Embedding-8B, at 0.76. This view shows only models we track, each at its best.

The newest model with a score here came out in June 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

101 entries. Scroll sideways for the rest.

  1. 0.81 Alibaba-NLP/gte-Qwen2-7B-instruct
  2. 0.81 Kingsoft-LLM/QZhou-Embedding-Zh
  3. 0.79 Alibaba-NLP/gme-Qwen2-VL-7B-Instruct
  4. 0.79 TencentBAC/Conan-embedding-v2
  5. 0.78 Alibaba-NLP/gme-Qwen2-VL-2B-Instruct
  6. 0.78 Alibaba-NLP/gte-Qwen1.5-7B-instruct
  7. 0.77 Kingsoft-LLM/QZhou-Embedding
  8. 0.76 Qwen3-Embedding-8B
  9. 0.75 lier007/xiaobu-embedding-v2
  10. 0.75 iampanda/zpoint_large_embedding_zh
  11. 0.75 richinfoai/ritrieve_zh_v1
  12. 0.75 TencentBAC/Conan-embedding-v1
  13. 0.74 Qwen3-Embedding-4B
  14. 0.74 malenia1/ternary-weight-embedding
  15. 0.74 Alibaba-NLP/gte-Qwen2-1.5B-instruct
  16. 0.73 Bytedance/Seed1.6-embedding
  17. 0.73 sensenova/piccolo-large-zh-v2
  18. 0.73 Classical/Yinka
  19. 0.73 infgrad/Jasper-Token-Compression-600M
  20. 0.73 IEITYuan/Yuan-embedding-2.0-zh
  21. 0.72 tencent/Youtu-Embedding
  22. 0.71 dunzhang/stella-large-zh-v3-1792d
  23. 0.71 dunzhang/stella-mrl-large-zh-v3.5-1792d
  24. 0.70 infgrad/stella-base-zh-v3-1792d
  25. 0.70 DMetaSoul/Dmeta-embedding-zh-small
  26. 0.70 ByteDance-Seed/Seed1.5-Embedding
  27. 0.70 KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5
  28. 0.66 lier007/xiaobu-embedding
  29. 0.66 thenlper/gte-base-zh
  30. 0.65 moka-ai/m3e-large
  31. 0.65 Qwen3-Embedding-0.6B
  32. 0.64 thenlper/gte-large-zh
  33. 0.64 moka-ai/m3e-base
  34. 0.64 qihoo360/Zhinao-ChineseModernBert-Embedding
  35. 0.63 jinaai/jina-embeddings-v3
  36. 0.63 BAAI/bge-large-zh-v1.5
  37. 0.63 BAAI/bge-large-zh
  38. 0.63 sensenova/piccolo-base-zh
  39. 0.62 BAAI/bge-multilingual-gemma2
  40. 0.62 BAAI/bge-base-zh-v1.5
  41. 0.61 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v2
  42. 0.61 BAAI/bge-base-zh
  43. 0.61 jinaai/jina-embeddings-v5-text-small
  44. 0.61 jinaai/jina-embeddings-v5-omni-small
  45. 0.60 jinaai/jina-embeddings-v5-omni-nano
  46. 0.56 microsoft/harrier-oss-v1-0.6b
  47. 0.56 codefuse-ai/F2LLM-v2-1.7B
  48. 0.56 codefuse-ai/F2LLM-v2-14B
  49. 0.55 BAAI/bge-small-zh
  50. 0.55 BAAI/bge-small-zh-v1.5
  51. 0.55 codefuse-ai/F2LLM-v2-8B
  52. 0.55 microsoft/harrier-oss-v1-270m
  53. 0.55 codefuse-ai/F2LLM-v2-4B
  54. 0.55 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5
  55. 0.54 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1
  56. 0.54 codefuse-ai/F2LLM-v2-0.6B
  57. 0.53 codefuse-ai/F2LLM-v2-330M
  58. 0.52 Alibaba-NLP/gte-multilingual-base
  59. 0.52 HIT-TMG/KaLM-embedding-multilingual-mini-v1
  60. 0.51 codefuse-ai/F2LLM-v2-160M
  61. 0.51 intfloat/e5-mistral-7b-instruct
  62. 0.50 thenlper/gte-small-zh
  63. 0.49 codefuse-ai/F2LLM-v2-80M
  64. 0.49 GritLM/GritLM-7B
  65. 0.49 intfloat/multilingual-e5-large-instruct
  66. 0.48 izhx/udever-bloom-7b1
  67. 0.47 izhx/udever-bloom-3b
  68. 0.46 intfloat/multilingual-e5-large
  69. 0.46 izhx/udever-bloom-1b1
  70. 0.45 intfloat/multilingual-e5-base
  71. 0.45 openai/text-embedding-ada-002
  72. 0.45 ibm-granite/granite-embedding-311m-multilingual-r2
  73. 0.45 hotchpotch/bekko-embedding-v1-a25m
  74. 0.44 ibm-granite/granite-embedding-97m-multilingual-r2
  75. 0.44 izhx/udever-bloom-560m
  76. 0.43 intfloat/multilingual-e5-small
  77. 0.43 hotchpotch/bekko-embedding-v1-a8m
  78. 0.43 shibing624/text2vec-base-chinese
  79. 0.43 sentence-transformers/LaBSE
  80. 0.41 hotchpotch/bekko-static-embedding-v1
  81. 0.41 minishlab/potion-multilingual-128M
  82. 0.41 DMetaSoul/sbert-chinese-general-v1
  83. 0.41 sentence-transformers/static-similarity-mrl-multilingual-v1
  84. 0.40 Rebine/Etsu-Embedding-0.8B-Memory
  85. 0.39 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
  86. 0.38 sonar
  87. 0.36 sentence-transformers/paraphrase-multilingual-mpnet-base-v2
  88. 0.24 sentence-transformers/all-MiniLM-L6-v2
  89. 0.23 sentence-transformers/all-MiniLM-L12-v2
  90. 0.21 sentence-transformers/all-mpnet-base-v2
  91. 0.20 minishlab/M2V_base_output
  92. 0.20 minishlab/potion-base-8M
  93. 0.20 minishlab/potion-base-4M
  94. 0.19 minishlab/potion-base-2M
  95. 0.12 axiotic/ogma-micro
  96. 0.12 NeuML/pubmedbert-base-embeddings-500K
  97. 0.12 axiotic/ogma-mini
  98. 0.11 NeuML/pubmedbert-base-embeddings-1M
  99. 0.10 axiotic/ogma-small
  100. 0.09 NeuML/pubmedbert-base-embeddings-8M
  101. 0.09 NeuML/pubmedbert-base-embeddings-2M
  1. 1 Alibaba-NLP/gte-Qwen2-7B-instruct 0.81
  2. 2 Kingsoft-LLM/QZhou-Embedding-Zh 0.81
  3. 3 Alibaba-NLP/gme-Qwen2-VL-7B-Instruct 0.79
  4. 4 TencentBAC/Conan-embedding-v2 0.79
  5. 5 Alibaba-NLP/gme-Qwen2-VL-2B-Instruct 0.78
  6. 6 Alibaba-NLP/gte-Qwen1.5-7B-instruct 0.78
  7. 7 Kingsoft-LLM/QZhou-Embedding 0.77
  8. 8 Qwen3-Embedding-8B 0.76
  9. 9 lier007/xiaobu-embedding-v2 0.75
  10. 10 iampanda/zpoint_large_embedding_zh 0.75
  11. 11 richinfoai/ritrieve_zh_v1 0.75
  12. 12 TencentBAC/Conan-embedding-v1 0.75
  13. 13 Qwen3-Embedding-4B 0.74
  14. 14 malenia1/ternary-weight-embedding 0.74
  15. 15 Alibaba-NLP/gte-Qwen2-1.5B-instruct 0.74
  16. 16 Bytedance/Seed1.6-embedding 0.73
  17. 17 sensenova/piccolo-large-zh-v2 0.73
  18. 18 Classical/Yinka 0.73
  19. 19 infgrad/Jasper-Token-Compression-600M 0.73
  20. 20 IEITYuan/Yuan-embedding-2.0-zh 0.73
  21. 21 tencent/Youtu-Embedding 0.72
  22. 22 dunzhang/stella-large-zh-v3-1792d 0.71
  23. 23 dunzhang/stella-mrl-large-zh-v3.5-1792d 0.71
  24. 24 infgrad/stella-base-zh-v3-1792d 0.70
  25. 25 DMetaSoul/Dmeta-embedding-zh-small 0.70
  26. 26 ByteDance-Seed/Seed1.5-Embedding 0.70
  27. 27 KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5 0.70
  28. 28 lier007/xiaobu-embedding 0.66
  29. 29 thenlper/gte-base-zh 0.66
  30. 30 moka-ai/m3e-large 0.65
  31. 31 Qwen3-Embedding-0.6B 0.65
  32. 32 thenlper/gte-large-zh 0.64
  33. 33 moka-ai/m3e-base 0.64
  34. 34 qihoo360/Zhinao-ChineseModernBert-Embedding 0.64
  35. 35 jinaai/jina-embeddings-v3 0.63
  36. 36 BAAI/bge-large-zh-v1.5 0.63
  37. 37 BAAI/bge-large-zh 0.63
  38. 38 sensenova/piccolo-base-zh 0.63
  39. 39 BAAI/bge-multilingual-gemma2 0.62
  40. 40 BAAI/bge-base-zh-v1.5 0.62
  41. 41 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v2 0.61
  42. 42 BAAI/bge-base-zh 0.61
  43. 43 jinaai/jina-embeddings-v5-text-small 0.61
  44. 44 jinaai/jina-embeddings-v5-omni-small 0.61
  45. 45 jinaai/jina-embeddings-v5-omni-nano 0.60
  46. 46 microsoft/harrier-oss-v1-0.6b 0.56
  47. 47 codefuse-ai/F2LLM-v2-1.7B 0.56
  48. 48 codefuse-ai/F2LLM-v2-14B 0.56
  49. 49 BAAI/bge-small-zh 0.55
  50. 50 BAAI/bge-small-zh-v1.5 0.55
  51. 51 codefuse-ai/F2LLM-v2-8B 0.55
  52. 52 microsoft/harrier-oss-v1-270m 0.55
  53. 53 codefuse-ai/F2LLM-v2-4B 0.55
  54. 54 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5 0.55
  55. 55 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 0.54
  56. 56 codefuse-ai/F2LLM-v2-0.6B 0.54
  57. 57 codefuse-ai/F2LLM-v2-330M 0.53
  58. 58 Alibaba-NLP/gte-multilingual-base 0.52
  59. 59 HIT-TMG/KaLM-embedding-multilingual-mini-v1 0.52
  60. 60 codefuse-ai/F2LLM-v2-160M 0.51
  61. 61 intfloat/e5-mistral-7b-instruct 0.51
  62. 62 thenlper/gte-small-zh 0.50
  63. 63 codefuse-ai/F2LLM-v2-80M 0.49
  64. 64 GritLM/GritLM-7B 0.49
  65. 65 intfloat/multilingual-e5-large-instruct 0.49
  66. 66 izhx/udever-bloom-7b1 0.48
  67. 67 izhx/udever-bloom-3b 0.47
  68. 68 intfloat/multilingual-e5-large 0.46
  69. 69 izhx/udever-bloom-1b1 0.46
  70. 70 intfloat/multilingual-e5-base 0.45
  71. 71 openai/text-embedding-ada-002 0.45
  72. 72 ibm-granite/granite-embedding-311m-multilingual-r2 0.45
  73. 73 hotchpotch/bekko-embedding-v1-a25m 0.45
  74. 74 ibm-granite/granite-embedding-97m-multilingual-r2 0.44
  75. 75 izhx/udever-bloom-560m 0.44
  76. 76 intfloat/multilingual-e5-small 0.43
  77. 77 hotchpotch/bekko-embedding-v1-a8m 0.43
  78. 78 shibing624/text2vec-base-chinese 0.43
  79. 79 sentence-transformers/LaBSE 0.43
  80. 80 hotchpotch/bekko-static-embedding-v1 0.41
  81. 81 minishlab/potion-multilingual-128M 0.41
  82. 82 DMetaSoul/sbert-chinese-general-v1 0.41
  83. 83 sentence-transformers/static-similarity-mrl-multilingual-v1 0.41
  84. 84 Rebine/Etsu-Embedding-0.8B-Memory 0.40
  85. 85 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 0.39
  86. 86 sonar 0.38
  87. 87 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 0.36
  88. 88 sentence-transformers/all-MiniLM-L6-v2 0.24
  89. 89 sentence-transformers/all-MiniLM-L12-v2 0.23
  90. 90 sentence-transformers/all-mpnet-base-v2 0.21
  91. 91 minishlab/M2V_base_output 0.20
  92. 92 minishlab/potion-base-8M 0.20
  93. 93 minishlab/potion-base-4M 0.20
  94. 94 minishlab/potion-base-2M 0.19
  95. 95 axiotic/ogma-micro 0.12
  96. 96 NeuML/pubmedbert-base-embeddings-500K 0.12
  97. 97 axiotic/ogma-mini 0.12
  98. 98 NeuML/pubmedbert-base-embeddings-1M 0.11
  99. 99 axiotic/ogma-small 0.10
  100. 100 NeuML/pubmedbert-base-embeddings-8M 0.09
  101. 101 NeuML/pubmedbert-base-embeddings-2M 0.09

Source: Official Bank Question Corpus leaderboard

#EntryScoreSettingDateLinkSource
1 Alibaba-NLP/gte-Qwen2-7B-instruct open weights, 7.1B 0.81 huggingface.co Official leaderboard
2 Kingsoft-LLM/QZhou-Embedding-Zh open weights, 7.6B 0.81 huggingface.co Official leaderboard
3 Alibaba-NLP/gme-Qwen2-VL-7B-Instruct open weights, 7.7B 0.79 huggingface.co Official leaderboard
4 TencentBAC/Conan-embedding-v2 closed weights 0.79 huggingface.co Official leaderboard
5 Alibaba-NLP/gme-Qwen2-VL-2B-Instruct open weights, 2.2B 0.78 huggingface.co Official leaderboard
6 Alibaba-NLP/gte-Qwen1.5-7B-instruct open weights, 7.1B 0.78 huggingface.co Official leaderboard
7 Kingsoft-LLM/QZhou-Embedding open weights, 7.1B 0.77 huggingface.co Official leaderboard
8 Qwen3-Embedding-8B 0.76 Jun 2025 huggingface.co Official leaderboard
9 lier007/xiaobu-embedding-v2 open weights, 0.3B 0.75 huggingface.co Official leaderboard
10 iampanda/zpoint_large_embedding_zh open weights, 0.3B 0.75 huggingface.co Official leaderboard
11 richinfoai/ritrieve_zh_v1 open weights, 0.3B 0.75 huggingface.co Official leaderboard
12 TencentBAC/Conan-embedding-v1 open weights, 0.3B 0.75 huggingface.co Official leaderboard
13 Qwen3-Embedding-4B 0.74 Jun 2025 huggingface.co Official leaderboard
14 malenia1/ternary-weight-embedding open weights, 0.1B 0.74 huggingface.co Official leaderboard
15 Alibaba-NLP/gte-Qwen2-1.5B-instruct open weights, 1.5B 0.74 huggingface.co Official leaderboard
16 Bytedance/Seed1.6-embedding closed weights 0.73 seed1-6-embedding.github.io Official leaderboard
17 sensenova/piccolo-large-zh-v2 closed weights 0.73 huggingface.co Official leaderboard
18 Classical/Yinka open weights, 0.3B 0.73 huggingface.co Official leaderboard
19 infgrad/Jasper-Token-Compression-600M open weights, 0.6B 0.73 huggingface.co Official leaderboard
20 IEITYuan/Yuan-embedding-2.0-zh open weights, 0.3B 0.73 huggingface.co Official leaderboard
21 tencent/Youtu-Embedding open weights, 2.7B 0.72 huggingface.co Official leaderboard
22 dunzhang/stella-large-zh-v3-1792d open weights, 0.3B 0.71 huggingface.co Official leaderboard
23 dunzhang/stella-mrl-large-zh-v3.5-1792d open weights, 0.3B 0.71 huggingface.co Official leaderboard
24 infgrad/stella-base-zh-v3-1792d open weights, 0.1B 0.70 huggingface.co Official leaderboard
25 DMetaSoul/Dmeta-embedding-zh-small open weights, 0.1B 0.70 huggingface.co Official leaderboard
26 ByteDance-Seed/Seed1.5-Embedding closed weights 0.70 seed1-5-embedding.github.io Official leaderboard
27 KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5 open weights, 0.5B 0.70 huggingface.co Official leaderboard
28 lier007/xiaobu-embedding open weights, 0.3B 0.66 huggingface.co Official leaderboard
29 thenlper/gte-base-zh open weights, 0.1B 0.66 huggingface.co Official leaderboard
30 moka-ai/m3e-large open weights, 0.3B 0.65 huggingface.co Official leaderboard
31 Qwen3-Embedding-0.6B 0.65 Jun 2025 huggingface.co Official leaderboard
32 thenlper/gte-large-zh open weights, 0.3B 0.64 huggingface.co Official leaderboard
33 moka-ai/m3e-base open weights, 0.1B 0.64 huggingface.co Official leaderboard
34 qihoo360/Zhinao-ChineseModernBert-Embedding open weights, 0.2B 0.64 huggingface.co Official leaderboard
35 jinaai/jina-embeddings-v3 open weights, 0.6B 0.63 huggingface.co Official leaderboard
36 BAAI/bge-large-zh-v1.5 open weights, 0.3B 0.63 huggingface.co Official leaderboard
37 BAAI/bge-large-zh open weights, 0.3B 0.63 huggingface.co Official leaderboard
38 sensenova/piccolo-base-zh open weights, 0.1B 0.63 huggingface.co Official leaderboard
39 BAAI/bge-multilingual-gemma2 open weights, 9.2B 0.62 huggingface.co Official leaderboard
40 BAAI/bge-base-zh-v1.5 open weights, 0.1B 0.62 huggingface.co Official leaderboard
41 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v2 open weights, 0.5B 0.61 huggingface.co Official leaderboard
42 BAAI/bge-base-zh open weights, 0.1B 0.61 huggingface.co Official leaderboard
43 jinaai/jina-embeddings-v5-text-small open weights, 0.6B 0.61 huggingface.co Official leaderboard
44 jinaai/jina-embeddings-v5-omni-small open weights, 1.6B 0.61 huggingface.co Official leaderboard
45 jinaai/jina-embeddings-v5-omni-nano open weights, 1B 0.60 huggingface.co Official leaderboard
46 microsoft/harrier-oss-v1-0.6b open weights, 0.6B 0.56 huggingface.co Official leaderboard
47 codefuse-ai/F2LLM-v2-1.7B open weights, 1.7B 0.56 huggingface.co Official leaderboard
48 codefuse-ai/F2LLM-v2-14B open weights, 14B 0.56 huggingface.co Official leaderboard
49 BAAI/bge-small-zh open weights, 0B 0.55 huggingface.co Official leaderboard
50 BAAI/bge-small-zh-v1.5 open weights, 0B 0.55 huggingface.co Official leaderboard
51 codefuse-ai/F2LLM-v2-8B open weights, 7.6B 0.55 huggingface.co Official leaderboard
52 microsoft/harrier-oss-v1-270m open weights, 0.3B 0.55 huggingface.co Official leaderboard
53 codefuse-ai/F2LLM-v2-4B open weights, 4B 0.55 huggingface.co Official leaderboard
54 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5 open weights, 0.5B 0.55 huggingface.co Official leaderboard
55 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 open weights, 0.5B 0.54 huggingface.co Official leaderboard
56 codefuse-ai/F2LLM-v2-0.6B open weights, 0.6B 0.54 huggingface.co Official leaderboard
57 codefuse-ai/F2LLM-v2-330M open weights, 0.3B 0.53 huggingface.co Official leaderboard
58 Alibaba-NLP/gte-multilingual-base open weights, 0.3B 0.52 huggingface.co Official leaderboard
59 HIT-TMG/KaLM-embedding-multilingual-mini-v1 open weights, 0.5B 0.52 huggingface.co Official leaderboard
60 codefuse-ai/F2LLM-v2-160M open weights, 0.2B 0.51 huggingface.co Official leaderboard
61 intfloat/e5-mistral-7b-instruct open weights, 7.1B 0.51 huggingface.co Official leaderboard
62 thenlper/gte-small-zh open weights, 0B 0.50 huggingface.co Official leaderboard
63 codefuse-ai/F2LLM-v2-80M open weights, 0.1B 0.49 huggingface.co Official leaderboard
64 GritLM/GritLM-7B open weights, 7.2B 0.49 huggingface.co Official leaderboard
65 intfloat/multilingual-e5-large-instruct open weights, 0.6B 0.49 huggingface.co Official leaderboard
66 izhx/udever-bloom-7b1 open weights 0.48 huggingface.co Official leaderboard
67 izhx/udever-bloom-3b open weights, 3B 0.47 huggingface.co Official leaderboard
68 intfloat/multilingual-e5-large open weights, 0.6B 0.46 huggingface.co Official leaderboard
69 izhx/udever-bloom-1b1 open weights, 1.1B 0.46 huggingface.co Official leaderboard
70 intfloat/multilingual-e5-base open weights, 0.3B 0.45 huggingface.co Official leaderboard
71 openai/text-embedding-ada-002 closed weights 0.45 openai.com Official leaderboard
72 ibm-granite/granite-embedding-311m-multilingual-r2 open weights, 0.3B 0.45 huggingface.co Official leaderboard
73 hotchpotch/bekko-embedding-v1-a25m open weights, 0.1B 0.45 huggingface.co Official leaderboard
74 ibm-granite/granite-embedding-97m-multilingual-r2 open weights, 0.1B 0.44 huggingface.co Official leaderboard
75 izhx/udever-bloom-560m open weights, 0.6B 0.44 huggingface.co Official leaderboard
76 intfloat/multilingual-e5-small open weights, 0.1B 0.43 huggingface.co Official leaderboard
77 hotchpotch/bekko-embedding-v1-a8m open weights, 0.1B 0.43 huggingface.co Official leaderboard
78 shibing624/text2vec-base-chinese open weights, 0.1B 0.43 huggingface.co Official leaderboard
79 sentence-transformers/LaBSE open weights, 0.5B 0.43 huggingface.co Official leaderboard
80 hotchpotch/bekko-static-embedding-v1 open weights, 0.2B 0.41 huggingface.co Official leaderboard
81 minishlab/potion-multilingual-128M open weights, 0.1B 0.41 huggingface.co Official leaderboard
82 DMetaSoul/sbert-chinese-general-v1 open weights, 0.1B 0.41 huggingface.co Official leaderboard
83 sentence-transformers/static-similarity-mrl-multilingual-v1 open weights, 0.1B 0.41 huggingface.co Official leaderboard
84 Rebine/Etsu-Embedding-0.8B-Memory open weights, 0.8B 0.40 huggingface.co Official leaderboard
85 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 open weights, 0.1B 0.39 huggingface.co Official leaderboard
86 sonar 0.38 Jan 2025 ai.meta.com Official leaderboard
87 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 open weights, 0.3B 0.36 huggingface.co Official leaderboard
88 sentence-transformers/all-MiniLM-L6-v2 open weights, 0B 0.24 huggingface.co Official leaderboard
89 sentence-transformers/all-MiniLM-L12-v2 open weights, 0B 0.23 huggingface.co Official leaderboard
90 sentence-transformers/all-mpnet-base-v2 open weights, 0.1B 0.21 huggingface.co Official leaderboard
91 minishlab/M2V_base_output open weights, 0B 0.20 huggingface.co Official leaderboard
92 minishlab/potion-base-8M open weights, 0B 0.20 huggingface.co Official leaderboard
93 minishlab/potion-base-4M open weights, 0B 0.20 huggingface.co Official leaderboard
94 minishlab/potion-base-2M open weights, 0B 0.19 huggingface.co Official leaderboard
95 axiotic/ogma-micro open weights, 0B 0.12 huggingface.co Official leaderboard
96 NeuML/pubmedbert-base-embeddings-500K open weights, 0B 0.12 huggingface.co Official leaderboard
97 axiotic/ogma-mini open weights, 0B 0.12 huggingface.co Official leaderboard
98 NeuML/pubmedbert-base-embeddings-1M open weights, 0B 0.11 huggingface.co Official leaderboard
99 axiotic/ogma-small open weights, 0B 0.10 huggingface.co Official leaderboard
100 NeuML/pubmedbert-base-embeddings-8M open weights, 0B 0.09 huggingface.co Official leaderboard
101 NeuML/pubmedbert-base-embeddings-2M open weights, 0B 0.09 huggingface.co Official leaderboard
#ModelScoreSettingDateLinkSource
1 Qwen3-Embedding-8B 0.76 Jun 2025 huggingface.co Official leaderboard
2 Qwen3-Embedding-4B 0.74 Jun 2025 huggingface.co Official leaderboard
3 Qwen3-Embedding-0.6B 0.65 Jun 2025 huggingface.co Official leaderboard
4 sonar 0.38 Jan 2025 ai.meta.com Official leaderboard

2 models have held number one on the official leaderboard since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Perplexity Qwen
Own leaderboard Not tested since Jun 2025

Source: Official Bank Question Corpus leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
0.40 0.50 0.60 0.70 0.80 2025 0.40 0.50 0.60 0.70 0.80 2025

Source: Official Bank Question Corpus leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Law, finance and medicine

All 637 in Law, finance and medicine
  • MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy. Qwen 3.8 Max 80.4%
  • HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
  • HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
  • FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy. Ling-3.1-flash 81.7%
  • KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
  • Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 17 months ago, in June 2025, for Qwen3-Embedding-0.6B. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (101 entries).
  • Pass Models scored 4 models we track, plus 97 other entries on its leaderboard.
  • Warning Newest score The newest came 17 months ago, in June 2025, for Qwen3-Embedding-0.6B.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on mteb-leaderboard.hf.space: 4 rows for models we track and 97 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check