---
tags:
- mteb
model-index:
- name: json_results
  results:
  - task:
      type: Classification
    dataset:
      type: mteb/amazon_counterfactual
      name: MTEB AmazonCounterfactualClassification (en)
      config: en
      split: test
      revision: e8379541af4e31359cca9fbcf4b00f2671dba205
    metrics:
    - type: accuracy
      value: 57.49253731343285
    - type: ap
      value: 23.59442736353998
    - type: f1
      value: 52.20223389089595
  - task:
      type: Classification
    dataset:
      type: mteb/amazon_reviews_multi
      name: MTEB AmazonReviewsClassification (en)
      config: en
      split: test
      revision: 1399c76144fd37290681b995c656ef9b2e06e26d
    metrics:
    - type: accuracy
      value: 30.59
    - type: f1
      value: 30.418224700389747
  - task:
      type: Classification
    dataset:
      type: mteb/banking77
      name: MTEB Banking77Classification
      config: default
      split: test
      revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
    metrics:
    - type: accuracy
      value: 73.41883116883116
    - type: f1
      value: 73.3645582123564
  - task:
      type: Clustering
    dataset:
      type: mteb/biorxiv-clustering-p2p
      name: MTEB BiorxivClusteringP2P
      config: default
      split: test
      revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
    metrics:
    - type: v_measure
      value: 29.33118844069676
  - task:
      type: Clustering
    dataset:
      type: mteb/biorxiv-clustering-s2s
      name: MTEB BiorxivClusteringS2S
      config: default
      split: test
      revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
    metrics:
    - type: v_measure
      value: 27.812326878347093
  - task:
      type: Classification
    dataset:
      type: mteb/emotion
      name: MTEB EmotionClassification
      config: default
      split: test
      revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
    metrics:
    - type: accuracy
      value: 33.62
    - type: f1
      value: 29.639357232727388
  - task:
      type: Classification
    dataset:
      type: mteb/imdb
      name: MTEB ImdbClassification
      config: default
      split: test
      revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
    metrics:
    - type: accuracy
      value: 56.1716
    - type: ap
      value: 53.588732808885574
    - type: f1
      value: 55.863727214981004
  - task:
      type: Classification
    dataset:
      type: mteb/mtop_domain
      name: MTEB MTOPDomainClassification (en)
      config: en
      split: test
      revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
    metrics:
    - type: accuracy
      value: 87.07250341997262
    - type: f1
      value: 86.63685613523198
  - task:
      type: Classification
    dataset:
      type: mteb/mtop_intent
      name: MTEB MTOPIntentClassification (en)
      config: en
      split: test
      revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
    metrics:
    - type: accuracy
      value: 61.95622435020519
    - type: f1
      value: 41.66240550937103
  - task:
      type: Classification
    dataset:
      type: mteb/amazon_massive_intent
      name: MTEB MassiveIntentClassification (en)
      config: en
      split: test
      revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
    metrics:
    - type: accuracy
      value: 62.96234028244788
    - type: f1
      value: 60.20385917259002
  - task:
      type: Classification
    dataset:
      type: mteb/amazon_massive_scenario
      name: MTEB MassiveScenarioClassification (en)
      config: en
      split: test
      revision: 7d571f92784cd94a019292a1f45445077d0ef634
    metrics:
    - type: accuracy
      value: 71.46603900470747
    - type: f1
      value: 70.96623988750936
  - task:
      type: Classification
    dataset:
      type: mteb/tweet_sentiment_extraction
      name: MTEB TweetSentimentExtractionClassification
      config: default
      split: test
      revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
    metrics:
    - type: accuracy
      value: 49.34352009054896
    - type: f1
      value: 49.58635289569058
---

license: apache-2.0


Here we estimate the performance of the CLIP embeddings (contrastive training between text - image data).