Skip to content

Add results for: e5-omni 3B/7B, Tevatron OmniEmbed, ebind-full#585

Merged
Samoed merged 1 commit into
mainfrom
add-omni-embedding-results
Jul 2, 2026
Merged

Add results for: e5-omni 3B/7B, Tevatron OmniEmbed, ebind-full#585
Samoed merged 1 commit into
mainfrom
add-omni-embedding-results

Conversation

@AdnanElAssadi56

Copy link
Copy Markdown
Contributor

Checklist

  • My model has a model sheet, report, or similar
  • My model has a reference implementation in mteb/models/model_implementations/, this can be as an API. Instruction on how to add a model can be found here
    • No, but there is an existing PR ___
  • The results submitted are obtained using the reference implementation
  • My model is available, either as a publicly accessible API or publicly on e.g., Huggingface
  • I solemnly swear that for all results submitted I have not trained on the evaluation dataset including training splits. If I have, I have disclosed it clearly.

@github-actions

github-actions Bot commented Jul 2, 2026

Copy link
Copy Markdown

Model Results Comparison

Reference models: intfloat/multilingual-e5-large, google/gemini-embedding-001
New models evaluated: Haon-Chen/e5-omni-3B, Haon-Chen/e5-omni-7B, Tevatron/OmniEmbed-v0.1, encord-team/ebind-full

Results for Haon-Chen/e5-omni-3B

task_name Haon-Chen/e5-omni-3B google/gemini-embedding-001 intfloat/multilingual-e5-large Max result Model with max result In Training Data
AROCocoOrder .216 nan nan .750 LCO-Embedding/LCO-Embedding-Omni-7B False
AROFlickrOrder .226 nan nan .718 BidirLM/BidirLM-Omni-2.5B-Embedding False
AROVisualAttribution .479 nan nan .769 Salesforce/blip-itm-base-coco False
AROVisualRelation .559 nan nan .592 royokong/e5-v False
AmazonCounterfactualClassification .600 .882 .697 .970 GeoGPT-Research-Project/GeoEmbedding False
ArXivHierarchicalClusteringP2P .587 .649 .557 .687 NovaSearch/jasper_en_vision_language_v1 False
ArXivHierarchicalClusteringS2S .597 .638 .537 .655 Qwen/Qwen3-Embedding-8B False
ArguAna .505 .864 .544 .898 voyageai/voyage-3-m-exp False
AskUbuntuDupQuestions .608 .642 .592 .753 IEITYuan/Yuan-embedding-2.0-en False
BIOSSES .757 .890 .846 .969 Gameselo/STS-multilingual-mpnet-base-v2 False
BLINKIT2IMultiChoice .726 nan nan .794 jinaai/jina-embeddings-v5-omni-small False
Banking77Classification .732 .943 .749 .943 google/gemini-embedding-001 False
BeijingOpera .776 nan nan .974 Qwen/Qwen2-Audio-7B False
BiorxivClusteringP2P.v2 .408 .539 .372 .842 codefuse-ai/F2LLM-4B False
BirdCLEF .241 nan nan .452 MIT/ast-finetuned-audioset-10-10-0.4593 False
CIFAR100ZeroShot .605 nan nan .911 QuanSun/EVA02-CLIP-bigE-14-plus False
CIRRIT2IRetrieval .217 nan nan .350 voyageai/voyage-multimodal-3 False
CQADupstackGamingRetrieval .525 .707 .587 .816 IEITYuan/Yuan-embedding-2.0-en False
CQADupstackUnixRetrieval .393 .537 .399 .720 voyageai/voyage-3-m-exp False
CREMADPairClassification .545 nan nan .689 Qwen/Qwen2-Audio-7B False
CREMA_D .290 nan nan .740 Qwen/Qwen2-Audio-7B False
CREMA_DClustering .008 nan nan .324 Qwen/Qwen2-Audio-7B False
CUB200I2IRetrieval .762 nan nan .862 facebook/dinov2-giant False
CVBenchCount .628 nan nan .698 LCO-Embedding/LCO-Embedding-Omni-7B False
CVBenchDepth .575 nan nan .748 LCO-Embedding/LCO-Embedding-Omni-3B False
CVBenchDistance .518 nan nan .650 LCO-Embedding/LCO-Embedding-Omni-7B False
CVBenchRelation .589 nan nan .862 LCO-Embedding/LCO-Embedding-Omni-7B False
ClimateFEVERHardNegatives .292 .311 .260 .591 IEITYuan/Yuan-embedding-2.0-en False
ClothoT2ARetrieval .399 nan nan .587 microsoft/msclap-2022 False
CommonLanguageAgeDetection .167 nan nan .205 laion/larger_clap_general False
CommonVoiceMini21T2ARetrieval .681 nan nan .831 jinaai/jina-embeddings-v5-omni-small False
Country211 .074 nan nan .325 google/siglip-so400m-patch14-384 False
Country211ZeroShot .092 nan nan .341 QuanSun/EVA02-CLIP-bigE-14-plus False
DTD .686 nan nan .811 QuanSun/EVA02-CLIP-bigE-14-plus False
EuroSAT .558 nan nan .939 QuanSun/EVA02-CLIP-bigE-14-plus False
FER2013ZeroShot .343 nan nan .627 BidirLM/BidirLM-Omni-2.5B-Embedding False
FEVERHardNegatives .698 .890 .838 .945 ByteDance-Seed/Seed1.5-Embedding False
FGVCAircraftZeroShot .124 nan nan .692 LCO-Embedding/LCO-Embedding-Omni-7B False
FSD2019Kaggle .377 nan nan .641 laion/larger_clap_general False
Fashion200kI2TRetrieval .036 nan nan .241 google/siglip-large-patch16-384 False
FiQA2018 .475 .618 .438 .821 ai-sage/Giga-Embeddings-instruct False
FleursT2ARetrieval .544 nan nan .735 BidirLM/BidirLM-Omni-2.5B-Embedding False
Food101ZeroShot .660 nan nan .955 google/siglip-so400m-patch14-384 False
GTSRB .670 nan nan .890 QuanSun/EVA02-CLIP-bigE-14-plus False
GTZANAudioReranking .845 nan nan .854 OpenMuQ/MuQ-MuLan-large False
GTZANGenre .787 nan nan .931 Qwen/Qwen2-Audio-7B False
GigaSpeechT2ARetrieval .797 nan nan .833 LCO-Embedding/LCO-Embedding-Omni-7B False
HatefulMemesI2TRetrieval .416 nan nan .842 google/siglip-so400m-patch14-384 False
HotpotQAHardNegatives .747 .870 .706 .870 google/gemini-embedding-001 False
IEMOCAPGender .797 nan nan .936 laion/clap-htsat-fused False
ImageCoDe .124 nan nan .152 laion/CLIP-ViT-g-14-laion2B-s34B-b88K False
ImageNetDog15Clustering .718 nan nan .926 facebook/dinov2-giant False
ImdbClassification .677 .950 .887 .974 Qwen/Qwen3-Embedding-8B False
InfoSeekIT2TRetrieval .297 nan nan .272 LCO-Embedding/LCO-Embedding-Omni-7B False
JamAltArtistA2ARetrieval .869 nan nan .969 laion/larger_clap_music_and_speech False
JamAltLyricA2TRetrieval .304 nan nan .760 LCO-Embedding/LCO-Embedding-Omni-3B False
MACST2ARetrieval .280 nan nan .417 microsoft/msclap-2022 False
MInDS14 .640 nan nan .911 BidirLM/BidirLM-Omni-2.5B-Embedding False
MTOPDomainClassification .892 .980 .902 1.000 voyageai/voyage-3-m-exp False
MassiveIntentClassification .543 .819 .602 .919 voyageai/voyage-3-m-exp False
MassiveScenarioClassification .609 .873 .651 .993 voyageai/voyage-3-m-exp False
MedrxivClusteringP2P.v2 .355 .472 .343 .720 codefuse-ai/F2LLM-4B False
MedrxivClusteringS2S.v2 .362 .450 .315 .702 codefuse-ai/F2LLM-4B False
MindSmallReranking .303 .329 .302 .344 Kingsoft-LLM/QZhou-Embedding False
MridinghamTonic .299 nan nan .612 Qwen/Qwen2-Audio-7B False
NIGHTSI2IRetrieval .241 nan nan .265 QuanSun/EVA02-CLIP-bigE-14-plus False
NMSQAPairClassification .729 nan nan .976 LCO-Embedding/LCO-Embedding-Omni-7B False
OVENIT2TRetrieval .180 nan nan .207 LCO-Embedding/LCO-Embedding-Omni-7B False
OxfordPets .805 nan nan .951 google/siglip-large-patch16-384 False
OxfordPetsZeroShot .492 nan nan .968 google/siglip-large-patch16-384 False
PatchCamelyon .628 nan nan .773 google/siglip-large-patch16-384 False
RESISC45 .865 nan nan .928 QuanSun/EVA02-CLIP-bigE-14-plus False
RP2kI2IRetrieval .584 nan nan 1.000 BidirLM/BidirLM-Omni-2.5B-Embedding False
RavdessZeroshot .351 nan nan .342 BidirLM/BidirLM-Omni-2.5B-Embedding False
SCIDOCS .243 .252 .174 .599 IEITYuan/Yuan-embedding-2.0-en False
SIBFLEURS .329 nan nan .475 BidirLM/BidirLM-Omni-2.5B-Embedding False
SICK-R .780 .827 .802 .947 Gameselo/STS-multilingual-mpnet-base-v2 False
STS12 .706 .815 .800 .955 Gameselo/STS-multilingual-mpnet-base-v2 False
STS13 .781 .899 .816 .978 Gameselo/STS-multilingual-mpnet-base-v2 False
STS13VisualSTS .716 nan nan .843 LCO-Embedding/LCO-Embedding-Omni-3B False
STS14 .703 .854 .777 .975 Gameselo/STS-multilingual-mpnet-base-v2 False
STS15 .777 .904 .893 .981 Gameselo/STS-multilingual-mpnet-base-v2 False
STS15VisualSTS .800 nan nan .882 LCO-Embedding/LCO-Embedding-Omni-7B False
STS17 .783 .886 .821 .957 jcorners/ingot-8b-r3 False
STS17MultilingualVisualSTS .758 nan nan .833 LCO-Embedding/LCO-Embedding-Omni-7B False
STS22.v2 .681 .717 .643 .772 Kingsoft-LLM/QZhou-Embedding False
STSBenchmark .773 .891 .873 .950 Kingsoft-LLM/QZhou-Embedding False
STSBenchmarkMultilingualVisualSTS .729 nan nan .830 LCO-Embedding/LCO-Embedding-Omni-7B False
SUN397 .697 nan nan .805 QuanSun/EVA02-CLIP-bigE-14-plus False
SpeechCommandsZeroshotv0.02 .938 nan nan .974 jinaai/jina-embeddings-v5-omni-small False
SpokenSQuADT2ARetrieval .727 nan nan .743 BidirLM/BidirLM-Omni-2.5B-Embedding False
SprintDuplicateQuestions .858 .969 .931 .984 Kingsoft-LLM/QZhou-Embedding False
StackExchangeClustering.v2 .495 .921 .464 .921 google/gemini-embedding-001 False
StackExchangeClusteringP2P.v2 .393 .509 .385 .551 Kingsoft-LLM/QZhou-Embedding False
StanfordCarsZeroShot .540 nan nan .946 google/siglip-so400m-patch14-384 False
SummEvalSummarization.v2 .247 .383 .314 .389 annamodels/LGAI-Embedding-Preview False
TRECCOVID .794 .863 .712 .983 IEITYuan/Yuan-embedding-2.0-en False
TinyImageNetClustering .642 nan nan .836 QuanSun/EVA02-CLIP-bigE-14 False
Touche2020Retrieval.v3 .446 .524 .496 .762 jcorners/ingot-8b-r3 False
ToxicConversationsClassification .565 .887 .660 .976 voyageai/voyage-3-m-exp False
TweetSentimentExtractionClassification .467 .699 .628 .882 voyageai/voyage-3-m-exp False
TwentyNewsgroupsClustering.v2 .474 .574 .392 .876 GeoGPT-Research-Project/GeoEmbedding False
TwitterSemEval2015 .614 .792 .753 .901 jcorners/ingot-8b-r3 False
TwitterURLCorpus .798 .870 .858 .957 TencentBAC/Conan-embedding-v2 False
UrbanSound8KT2ARetrieval .009 nan nan .010 laion/clap-htsat-unfused False
VQA2IT2TRetrieval .231 nan nan .209 LCO-Embedding/LCO-Embedding-Omni-3B False
VehicleSoundClustering .038 nan nan .134 MIT/ast-finetuned-audioset-10-10-0.4593 False
VidoreDocVQARetrieval .492 nan nan .687 webAI-Official/webAI-ColVec1-9b False
VidoreInfoVQARetrieval .905 nan nan .952 webAI-Official/webAI-ColVec1-9b False
VidoreShiftProjectRetrieval .802 nan nan .947 DataScience-UIBK/Argus-Colqwen3.5-4b-v0 False
VidoreSyntheticDocQAAIRetrieval .970 nan nan 1.000 athrael-soju/colqwen3.5-4.5B-v3 False
VidoreTabfquadRetrieval .903 nan nan .981 nvidia/nemotron-colembed-vl-4b-v2 False
VidoreTatdqaRetrieval .626 nan nan .857 DataScience-UIBK/Argus-Colqwen3.5-9b-v0-bf16 False
VisualNewsI2TRetrieval .037 nan nan .464 QuanSun/EVA02-CLIP-bigE-14-plus False
VoxCelebSA .381 nan nan .495 BidirLM/BidirLM-Omni-2.5B-Embedding False
VoxPopuliAccentPairClassification .510 nan nan .554 openai/whisper-medium False
VoxPopuliGenderClustering .010 nan nan .527 laion/clap-htsat-fused False
VoxPopuliLanguageID .594 nan nan .994 speechbrain/m-ctc-t-large False
WITT2IRetrieval .488 nan nan .634 LCO-Embedding/LCO-Embedding-Omni-7B False
WebQAT2ITRetrieval .633 nan nan .656 voyageai/voyage-multimodal-3 False
Winoground .062 nan nan .150 LCO-Embedding/LCO-Embedding-Omni-7B False
XM3600T2IRetrieval .531 nan nan .666 royokong/e5-v False
Average .529 .729 .618 .738 nan -

Model have high performance on these tasks: RavdessZeroshot,InfoSeekIT2TRetrieval,VQA2IT2TRetrieval


Results for Haon-Chen/e5-omni-7B

task_name Haon-Chen/e5-omni-7B google/gemini-embedding-001 intfloat/multilingual-e5-large Max result Model with max result In Training Data
AROCocoOrder .424 nan nan .750 LCO-Embedding/LCO-Embedding-Omni-7B False
AROFlickrOrder .459 nan nan .718 BidirLM/BidirLM-Omni-2.5B-Embedding False
AROVisualAttribution .742 nan nan .769 Salesforce/blip-itm-base-coco False
AROVisualRelation .577 nan nan .592 royokong/e5-v False
AmazonCounterfactualClassification .603 .882 .697 .970 GeoGPT-Research-Project/GeoEmbedding False
ArXivHierarchicalClusteringP2P .578 .649 .557 .687 NovaSearch/jasper_en_vision_language_v1 False
ArXivHierarchicalClusteringS2S .577 .638 .537 .655 Qwen/Qwen3-Embedding-8B False
ArguAna .397 .864 .544 .898 voyageai/voyage-3-m-exp False
AskUbuntuDupQuestions .598 .642 .592 .753 IEITYuan/Yuan-embedding-2.0-en False
BIOSSES .780 .890 .846 .969 Gameselo/STS-multilingual-mpnet-base-v2 False
BLINKIT2IMultiChoice .764 nan nan .794 jinaai/jina-embeddings-v5-omni-small False
Banking77Classification .757 .943 .749 .943 google/gemini-embedding-001 False
BeijingOpera .818 nan nan .974 Qwen/Qwen2-Audio-7B False
BiorxivClusteringP2P.v2 .419 .539 .372 .842 codefuse-ai/F2LLM-4B False
BirdCLEF .248 nan nan .452 MIT/ast-finetuned-audioset-10-10-0.4593 False
CIFAR100ZeroShot .707 nan nan .911 QuanSun/EVA02-CLIP-bigE-14-plus False
CIRRIT2IRetrieval .223 nan nan .350 voyageai/voyage-multimodal-3 False
CQADupstackGamingRetrieval .559 .707 .587 .816 IEITYuan/Yuan-embedding-2.0-en False
CQADupstackUnixRetrieval .380 .537 .399 .720 voyageai/voyage-3-m-exp False
CREMADPairClassification .554 nan nan .689 Qwen/Qwen2-Audio-7B False
CREMA_D .306 nan nan .740 Qwen/Qwen2-Audio-7B False
CREMA_DClustering .010 nan nan .324 Qwen/Qwen2-Audio-7B False
CUB200I2IRetrieval .760 nan nan .862 facebook/dinov2-giant False
CVBenchCount .633 nan nan .698 LCO-Embedding/LCO-Embedding-Omni-7B False
CVBenchDepth .605 nan nan .748 LCO-Embedding/LCO-Embedding-Omni-3B False
CVBenchDistance .628 nan nan .650 LCO-Embedding/LCO-Embedding-Omni-7B False
CVBenchRelation .834 nan nan .862 LCO-Embedding/LCO-Embedding-Omni-7B False
ClimateFEVERHardNegatives .233 .311 .260 .591 IEITYuan/Yuan-embedding-2.0-en False
ClothoT2ARetrieval .425 nan nan .587 microsoft/msclap-2022 False
CommonLanguageAgeDetection .152 nan nan .205 laion/larger_clap_general False
CommonVoiceMini21T2ARetrieval .663 nan nan .831 jinaai/jina-embeddings-v5-omni-small False
Country211 .114 nan nan .325 google/siglip-so400m-patch14-384 False
Country211ZeroShot .201 nan nan .341 QuanSun/EVA02-CLIP-bigE-14-plus False
DTD .739 nan nan .811 QuanSun/EVA02-CLIP-bigE-14-plus False
EuroSAT .697 nan nan .939 QuanSun/EVA02-CLIP-bigE-14-plus False
FER2013ZeroShot .345 nan nan .627 BidirLM/BidirLM-Omni-2.5B-Embedding False
FEVERHardNegatives .690 .890 .838 .945 ByteDance-Seed/Seed1.5-Embedding False
FGVCAircraftZeroShot .259 nan nan .692 LCO-Embedding/LCO-Embedding-Omni-7B False
FSD2019Kaggle .532 nan nan .641 laion/larger_clap_general False
Fashion200kI2TRetrieval .068 nan nan .241 google/siglip-large-patch16-384 False
FiQA2018 .477 .618 .438 .821 ai-sage/Giga-Embeddings-instruct False
FleursT2ARetrieval .600 nan nan .735 BidirLM/BidirLM-Omni-2.5B-Embedding False
Food101ZeroShot .810 nan nan .955 google/siglip-so400m-patch14-384 False
GTSRB .719 nan nan .890 QuanSun/EVA02-CLIP-bigE-14-plus False
GTZANAudioReranking .867 nan nan .854 OpenMuQ/MuQ-MuLan-large False
GTZANGenre .851 nan nan .931 Qwen/Qwen2-Audio-7B False
GigaSpeechT2ARetrieval .828 nan nan .833 LCO-Embedding/LCO-Embedding-Omni-7B False
HatefulMemesI2TRetrieval .564 nan nan .842 google/siglip-so400m-patch14-384 False
HotpotQAHardNegatives .691 .870 .706 .870 google/gemini-embedding-001 False
IEMOCAPGender .812 nan nan .936 laion/clap-htsat-fused False
ImageCoDe .125 nan nan .152 laion/CLIP-ViT-g-14-laion2B-s34B-b88K False
ImageNetDog15Clustering .796 nan nan .926 facebook/dinov2-giant False
ImdbClassification .711 .950 .887 .974 Qwen/Qwen3-Embedding-8B False
InfoSeekIT2TRetrieval .341 nan nan .272 LCO-Embedding/LCO-Embedding-Omni-7B False
JamAltArtistA2ARetrieval .920 nan nan .969 laion/larger_clap_music_and_speech False
JamAltLyricA2TRetrieval .542 nan nan .760 LCO-Embedding/LCO-Embedding-Omni-3B False
MACST2ARetrieval .293 nan nan .417 microsoft/msclap-2022 False
MInDS14 .705 nan nan .911 BidirLM/BidirLM-Omni-2.5B-Embedding False
MTOPDomainClassification .904 .980 .902 1.000 voyageai/voyage-3-m-exp False
MassiveIntentClassification .545 .819 .602 .919 voyageai/voyage-3-m-exp False
MassiveScenarioClassification .633 .873 .651 .993 voyageai/voyage-3-m-exp False
MedrxivClusteringP2P.v2 .362 .472 .343 .720 codefuse-ai/F2LLM-4B False
MedrxivClusteringS2S.v2 .349 .450 .315 .702 codefuse-ai/F2LLM-4B False
MindSmallReranking .308 .329 .302 .344 Kingsoft-LLM/QZhou-Embedding False
MridinghamTonic .308 nan nan .612 Qwen/Qwen2-Audio-7B False
NIGHTSI2IRetrieval .252 nan nan .265 QuanSun/EVA02-CLIP-bigE-14-plus False
NMSQAPairClassification .891 nan nan .976 LCO-Embedding/LCO-Embedding-Omni-7B False
OVENIT2TRetrieval .199 nan nan .207 LCO-Embedding/LCO-Embedding-Omni-7B False
OxfordPets .915 nan nan .951 google/siglip-large-patch16-384 False
OxfordPetsZeroShot .802 nan nan .968 google/siglip-large-patch16-384 False
PatchCamelyon .641 nan nan .773 google/siglip-large-patch16-384 False
RESISC45 .891 nan nan .928 QuanSun/EVA02-CLIP-bigE-14-plus False
RP2kI2IRetrieval .636 nan nan 1.000 BidirLM/BidirLM-Omni-2.5B-Embedding False
RavdessZeroshot .406 nan nan .342 BidirLM/BidirLM-Omni-2.5B-Embedding False
SCIDOCS .228 .252 .174 .599 IEITYuan/Yuan-embedding-2.0-en False
SIBFLEURS .384 nan nan .475 BidirLM/BidirLM-Omni-2.5B-Embedding False
SICK-R .795 .827 .802 .947 Gameselo/STS-multilingual-mpnet-base-v2 False
STS12 .732 .815 .800 .955 Gameselo/STS-multilingual-mpnet-base-v2 False
STS13 .796 .899 .816 .978 Gameselo/STS-multilingual-mpnet-base-v2 False
STS13VisualSTS .764 nan nan .843 LCO-Embedding/LCO-Embedding-Omni-3B False
STS14 .698 .854 .777 .975 Gameselo/STS-multilingual-mpnet-base-v2 False
STS15 .776 .904 .893 .981 Gameselo/STS-multilingual-mpnet-base-v2 False
STS15VisualSTS .846 nan nan .882 LCO-Embedding/LCO-Embedding-Omni-7B False
STS17 .795 .886 .821 .957 jcorners/ingot-8b-r3 False
STS17MultilingualVisualSTS .790 nan nan .833 LCO-Embedding/LCO-Embedding-Omni-7B False
STS22.v2 .076 .717 .643 .772 Kingsoft-LLM/QZhou-Embedding False
STSBenchmark .762 .891 .873 .950 Kingsoft-LLM/QZhou-Embedding False
STSBenchmarkMultilingualVisualSTS .782 nan nan .830 LCO-Embedding/LCO-Embedding-Omni-7B False
SUN397 .750 nan nan .805 QuanSun/EVA02-CLIP-bigE-14-plus False
SpeechCommandsZeroshotv0.02 .971 nan nan .974 jinaai/jina-embeddings-v5-omni-small False
SpokenSQuADT2ARetrieval .767 nan nan .743 BidirLM/BidirLM-Omni-2.5B-Embedding False
SprintDuplicateQuestions .923 .969 .931 .984 Kingsoft-LLM/QZhou-Embedding False
StackExchangeClustering.v2 .506 .921 .464 .921 google/gemini-embedding-001 False
StackExchangeClusteringP2P.v2 .431 .509 .385 .551 Kingsoft-LLM/QZhou-Embedding False
StanfordCarsZeroShot .767 nan nan .946 google/siglip-so400m-patch14-384 False
SummEvalSummarization.v2 .232 .383 .314 .389 annamodels/LGAI-Embedding-Preview False
TRECCOVID .800 .863 .712 .983 IEITYuan/Yuan-embedding-2.0-en False
TinyImageNetClustering .671 nan nan .836 QuanSun/EVA02-CLIP-bigE-14 False
Touche2020Retrieval.v3 .428 .524 .496 .762 jcorners/ingot-8b-r3 False
ToxicConversationsClassification .595 .887 .660 .976 voyageai/voyage-3-m-exp False
TweetSentimentExtractionClassification .535 .699 .628 .882 voyageai/voyage-3-m-exp False
TwentyNewsgroupsClustering.v2 .449 .574 .392 .876 GeoGPT-Research-Project/GeoEmbedding False
TwitterSemEval2015 .564 .792 .753 .901 jcorners/ingot-8b-r3 False
TwitterURLCorpus .780 .870 .858 .957 TencentBAC/Conan-embedding-v2 False
UrbanSound8KT2ARetrieval .009 nan nan .010 laion/clap-htsat-unfused False
VQA2IT2TRetrieval .190 nan nan .209 LCO-Embedding/LCO-Embedding-Omni-3B False
VehicleSoundClustering .024 nan nan .134 MIT/ast-finetuned-audioset-10-10-0.4593 False
VidoreDocVQARetrieval .575 nan nan .687 webAI-Official/webAI-ColVec1-9b False
VidoreInfoVQARetrieval .925 nan nan .952 webAI-Official/webAI-ColVec1-9b False
VidoreShiftProjectRetrieval .856 nan nan .947 DataScience-UIBK/Argus-Colqwen3.5-4b-v0 False
VidoreSyntheticDocQAAIRetrieval .989 nan nan 1.000 athrael-soju/colqwen3.5-4.5B-v3 False
VidoreTabfquadRetrieval .934 nan nan .981 nvidia/nemotron-colembed-vl-4b-v2 False
VidoreTatdqaRetrieval .710 nan nan .857 DataScience-UIBK/Argus-Colqwen3.5-9b-v0-bf16 False
VisualNewsI2TRetrieval .303 nan nan .464 QuanSun/EVA02-CLIP-bigE-14-plus False
VoxCelebSA .359 nan nan .495 BidirLM/BidirLM-Omni-2.5B-Embedding False
VoxPopuliAccentPairClassification .521 nan nan .554 openai/whisper-medium False
VoxPopuliGenderClustering .019 nan nan .527 laion/clap-htsat-fused False
VoxPopuliLanguageID .796 nan nan .994 speechbrain/m-ctc-t-large False
WITT2IRetrieval .636 nan nan .634 LCO-Embedding/LCO-Embedding-Omni-7B False
WebQAT2ITRetrieval .652 nan nan .656 voyageai/voyage-multimodal-3 False
Winoground .100 nan nan .150 LCO-Embedding/LCO-Embedding-Omni-7B False
XM3600T2IRetrieval .687 nan nan .666 royokong/e5-v False
Average .569 .729 .618 .738 nan -

Model have high performance on these tasks: GTZANAudioReranking,SpokenSQuADT2ARetrieval,XM3600T2IRetrieval,WITT2IRetrieval,RavdessZeroshot,InfoSeekIT2TRetrieval


Results for Tevatron/OmniEmbed-v0.1

task_name Tevatron/OmniEmbed-v0.1 google/gemini-embedding-001 intfloat/multilingual-e5-large Max result Model with max result In Training Data
AROCocoOrder .372 nan nan .750 LCO-Embedding/LCO-Embedding-Omni-7B False
AROFlickrOrder .397 nan nan .718 BidirLM/BidirLM-Omni-2.5B-Embedding False
AROVisualAttribution .716 nan nan .769 Salesforce/blip-itm-base-coco False
AROVisualRelation .591 nan nan .592 royokong/e5-v False
AmazonCounterfactualClassification .641 .882 .697 .970 GeoGPT-Research-Project/GeoEmbedding False
ArXivHierarchicalClusteringP2P .583 .649 .557 .687 NovaSearch/jasper_en_vision_language_v1 False
ArXivHierarchicalClusteringS2S .606 .638 .537 .655 Qwen/Qwen3-Embedding-8B False
ArguAna .733 .864 .544 .898 voyageai/voyage-3-m-exp False
AskUbuntuDupQuestions .617 .642 .592 .753 IEITYuan/Yuan-embedding-2.0-en False
BIOSSES .824 .890 .846 .969 Gameselo/STS-multilingual-mpnet-base-v2 False
BLINKIT2IMultiChoice .734 nan nan .794 jinaai/jina-embeddings-v5-omni-small False
Banking77Classification .737 .943 .749 .943 google/gemini-embedding-001 False
BeijingOpera .835 nan nan .974 Qwen/Qwen2-Audio-7B False
BiorxivClusteringP2P.v2 .409 .539 .372 .842 codefuse-ai/F2LLM-4B False
BirdCLEF .242 nan nan .452 MIT/ast-finetuned-audioset-10-10-0.4593 False
CIFAR100ZeroShot .650 nan nan .911 QuanSun/EVA02-CLIP-bigE-14-plus False
CIRRIT2IRetrieval .159 nan nan .350 voyageai/voyage-multimodal-3 False
CQADupstackGamingRetrieval .545 .707 .587 .816 IEITYuan/Yuan-embedding-2.0-en False
CQADupstackUnixRetrieval .421 .537 .399 .720 voyageai/voyage-3-m-exp False
CREMADPairClassification .601 nan nan .689 Qwen/Qwen2-Audio-7B False
CREMA_D .491 nan nan .740 Qwen/Qwen2-Audio-7B False
CREMA_DClustering .063 nan nan .324 Qwen/Qwen2-Audio-7B False
CUB200I2IRetrieval .791 nan nan .862 facebook/dinov2-giant False
CVBenchCount .294 nan nan .698 LCO-Embedding/LCO-Embedding-Omni-7B False
CVBenchDepth .493 nan nan .748 LCO-Embedding/LCO-Embedding-Omni-3B False
CVBenchDistance .412 nan nan .650 LCO-Embedding/LCO-Embedding-Omni-7B False
CVBenchRelation .580 nan nan .862 LCO-Embedding/LCO-Embedding-Omni-7B False
ClimateFEVERHardNegatives .249 .311 .260 .591 IEITYuan/Yuan-embedding-2.0-en False
ClothoT2ARetrieval .423 nan nan .587 microsoft/msclap-2022 False
CommonLanguageAgeDetection .147 nan nan .205 laion/larger_clap_general False
CommonVoiceMini21T2ARetrieval .587 nan nan .831 jinaai/jina-embeddings-v5-omni-small False
Country211 .101 nan nan .325 google/siglip-so400m-patch14-384 False
Country211ZeroShot .116 nan nan .341 QuanSun/EVA02-CLIP-bigE-14-plus False
DTD .758 nan nan .811 QuanSun/EVA02-CLIP-bigE-14-plus False
EuroSAT .702 nan nan .939 QuanSun/EVA02-CLIP-bigE-14-plus False
FER2013ZeroShot .350 nan nan .627 BidirLM/BidirLM-Omni-2.5B-Embedding False
FEVERHardNegatives .711 .890 .838 .945 ByteDance-Seed/Seed1.5-Embedding True
FGVCAircraftZeroShot .177 nan nan .692 LCO-Embedding/LCO-Embedding-Omni-7B False
FSD2019Kaggle .521 nan nan .641 laion/larger_clap_general False
Fashion200kI2TRetrieval .027 nan nan .241 google/siglip-large-patch16-384 False
FiQA2018 .490 .618 .438 .821 ai-sage/Giga-Embeddings-instruct False
FleursT2ARetrieval .298 nan nan .735 BidirLM/BidirLM-Omni-2.5B-Embedding False
Food101ZeroShot .547 nan nan .955 google/siglip-so400m-patch14-384 False
GTSRB .731 nan nan .890 QuanSun/EVA02-CLIP-bigE-14-plus Fa

Note: Content truncated due to GitHub API limits. See the full report in the workflow artifacts.

@Samoed Samoed merged commit 1a45191 into main Jul 2, 2026
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants