Skip to content

Add results for KaLM-Team/KaLM_Embedding-X-0605 in MMTEB #227

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
Samoed merged 1 commit into from
Jul 3, 2025
Merged

Add results for KaLM-Team/KaLM_Embedding-X-0605 in MMTEB #227

Samoed merged 1 commit into from
Jul 3, 2025

Conversation

@YanshekWoo
Copy link
Contributor

@YanshekWoo YanshekWoo commented Jun 25, 2025

Checklist

  • My model has a model sheet, report or similar: KaLM-Embedding
  • My model has a reference implementation in mteb/models/ this can be as an API. Instruction on how to add a model can be found here
  • The results submitted is 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 on the evaluation dataset including training splits. If I have I have disclosed it clearly.

@YanshekWoo YanshekWoo mentioned this pull request Jun 25, 2025
Closed
6 tasks
@github-actions
Copy link

github-actions bot commented Jun 25, 2025

Model Results Comparison

Reference models: intfloat/multilingual-e5-large, google/gemini-embedding-001
New models evaluated: KaLM-Team/KaLM-Embedding-X-0605
Tasks: AILAStatutes, AfriSentiClassification, AlloProfClusteringS2S.v2, AlloprofReranking, AmazonCounterfactualClassification, ArXivHierarchicalClusteringP2P, ArXivHierarchicalClusteringS2S, ArguAna, ArmenianParaphrasePC, BUCC.v2, BelebeleRetrieval, BibleNLPBitextMining, BigPatentClustering.v2, BiorxivClusteringP2P.v2, BornholmBitextMining, BrazilianToxicTweetsClassification, BulgarianStoreReviewSentimentClassfication, CEDRClassification, CLSClusteringP2P.v2, CSFDSKMovieReviewSentimentClassification, CTKFactsNLI, CataloniaTweetClassification, Core17InstructionRetrieval, CovidRetrieval, CyrillicTurkicLangClassification, CzechProductReviewSentimentClassification, DBpediaClassification, DalajClassification, DiaBlaBitextMining, EstonianValenceClassification, FaroeseSTS, FilipinoShopeeReviewsClassification, FinParaSTS, FinancialPhrasebankClassification, FloresBitextMining, GermanSTSBenchmark, GreekLegalCodeClassification, GujaratiNewsClassification, HALClusteringS2S.v2, HagridRetrieval, IN22GenBitextMining, IndicCrosslingualSTS, IndicGenBenchFloresBitextMining, IndicLangClassification, IndonesianIdClickbaitClassification, IsiZuluNewsClassification, ItaCaseholdClassification, JSICK, KorHateSpeechMLClassification, KorSarcasmClassification, KurdishSentimentClassification, LEMBPasskeyRetrieval, LegalBenchCorporateLobbying, MIRACLRetrievalHardNegatives, MLQARetrieval, MacedonianTweetSentimentClassification, MalteseNewsClassification, MasakhaNEWSClassification, MasakhaNEWSClusteringS2S, MassiveIntentClassification, MedrxivClusteringP2P.v2, MultiEURLEXMultilabelClassification, MultiHateClassification, NTREXBitextMining, NepaliNewsClassification, News21InstructionRetrieval, NollySentiBitextMining, NordicLangClassification, NorwegianCourtsBitextMining, NusaParagraphEmotionClassification, NusaTranslationBitextMining, NusaX-senti, NusaXBitextMining, OdiaNewsClassification, OpusparcusPC, PAC, PawsXPairClassification, PlscClusteringP2P.v2, PoemSentimentClassification, PolEmo2.0-OUT, PpcPC, PunjabiNewsClassification, RTE3, Robust04InstructionRetrieval, RomaniBibleClustering, RuBQReranking, SCIDOCS, SIB200ClusteringS2S, SICK-R, STS12, STS13, STS14, STS15, STS17, STS22.v2, STSB, STSBenchmark, STSES, ScalaClassification, SemRel24STS, SentimentAnalysisHindi, SinhalaNewsClassification, SiswatiNewsClassification, SlovakMovieReviewSentimentClassification, SpartQA, SprintDuplicateQuestions, StackExchangeClustering.v2, StackOverflowQA, StatcanDialogueDatasetRetrieval, SwahiliNewsClassification, SwednClusteringP2P, SwissJudgementClassification, T2Reranking, TERRa, TRECCOVID, Tatoeba, TempReasonL1, ToxicConversationsClassification, TswanaNewsClassification, TweetTopicSingleClassification, TwitterHjerneRetrieval, TwitterURLCorpus, VoyageMMarcoReranking, WebLINXCandidatesReranking, WikiCitiesClustering, WikiClusteringP2P.v2, WikipediaRerankingMultilingual, WikipediaRetrievalMultilingual, WinoGrande, XNLI, indonli

Results for KaLM-Team/KaLM-Embedding-X-0605

task_name KaLM-Team/KaLM-Embedding-X-0605 google/gemini-embedding-001 intfloat/multilingual-e5-large Max result
AILAStatutes 0.47 0.49 0.21 0.01
AfriSentiClassification 0.54 0.54 0.46 0.01
AlloProfClusteringS2S.v2 0.59 0.56 0.33 0.01
AlloprofReranking 0.81 0.82 0.69 0.01
AmazonCounterfactualClassification 0.88 0.88 0.70 0.92
ArXivHierarchicalClusteringP2P 0.64 0.65 0.56 0.01
ArXivHierarchicalClusteringS2S 0.64 0.64 0.54 0.01
ArguAna 0.58 0.86 0.54 0.64
ArmenianParaphrasePC 0.96 0.97 0.95 0.01
BUCC.v2 0.99 0.99 0.99 0.01
BelebeleRetrieval 0.85 0.91 0.78 0.01
BibleNLPBitextMining 0.20 0.21 0.17 0.01
BigPatentClustering.v2 0.46 0.38 0.31 0.00
BiorxivClusteringP2P.v2 0.49 0.54 0.37 0.01
BornholmBitextMining 0.52 0.52 0.44 0.01
BrazilianToxicTweetsClassification 0.24 0.28 0.21 0.00
BulgarianStoreReviewSentimentClassfication 0.80 0.78 0.64 0.01
CEDRClassification 0.43 0.57 0.45 0.01
CLSClusteringP2P.v2 0.47 0.43 0.40 0.01
CSFDSKMovieReviewSentimentClassification 0.57 0.49 0.35 0.01
CTKFactsNLI 0.83 0.88 0.80 0.01
CataloniaTweetClassification 0.48 0.55 0.50 0.01
Core17InstructionRetrieval 0.05 0.08 -0.02 0.00
CovidRetrieval 0.82 0.79 0.76 0.01
CyrillicTurkicLangClassification 0.81 0.95 0.41 0.01
CzechProductReviewSentimentClassification 0.67 0.68 0.57 0.01
DBpediaClassification 0.95 0.95 0.88 0.01
DalajClassification 0.50 0.50 0.50 0.01
DiaBlaBitextMining 0.88 0.87 0.85 0.01
EstonianValenceClassification 0.68 0.54 0.43 0.01
FaroeseSTS 0.80 0.86 0.72 0.01
FilipinoShopeeReviewsClassification 0.50 0.48 0.35 0.01
FinParaSTS 0.26 0.29 0.25 0.00
FinancialPhrasebankClassification 0.94 0.89 0.84 0.01
FloresBitextMining 0.78 0.84 0.81 0.01
GermanSTSBenchmark 0.85 0.88 0.84 0.01
GreekLegalCodeClassification 0.42 0.44 0.37 0.01
GujaratiNewsClassification 0.92 0.92 0.77 0.01
HALClusteringS2S.v2 0.32 0.32 0.23 0.00
HagridRetrieval 0.99 0.99 0.99 0.01
IN22GenBitextMining 0.92 0.94 0.77 0.01
IndicCrosslingualSTS 0.53 0.63 0.44 0.01
IndicGenBenchFloresBitextMining 0.96 0.97 0.89 0.01
IndicLangClassification 0.86 0.88 0.20 0.01
IndonesianIdClickbaitClassification 0.64 0.67 0.61 0.01
IsiZuluNewsClassification 0.33 0.41 0.32 0.00
ItaCaseholdClassification 0.68 0.73 0.67 0.01
JSICK 0.85 0.85 0.80 0.01
KorHateSpeechMLClassification 0.22 0.18 0.10 0.00
KorSarcasmClassification 0.66 0.61 0.57 0.01
KurdishSentimentClassification 0.83 0.86 0.77 0.01
LEMBPasskeyRetrieval 0.39 0.39 0.38 0.01
LegalBenchCorporateLobbying 0.94 0.96 0.90 0.01
MIRACLRetrievalHardNegatives 0.61 0.70 0.67 0.01
MLQARetrieval 0.81 0.84 0.76 0.01
MacedonianTweetSentimentClassification 0.72 0.72 0.62 0.01
MalteseNewsClassification 0.47 0.37 0.24 0.00
MasakhaNEWSClassification 0.84 0.84 0.78 0.01
MasakhaNEWSClusteringS2S 0.64 0.57 0.38 0.01
MassiveIntentClassification 0.77 0.82 0.60 0.85
MedrxivClusteringP2P.v2 0.40 0.47 0.34 0.01
MultiEURLEXMultilabelClassification 0.05 0.05 0.05 0.00
MultiHateClassification 0.83 0.72 0.64 0.01
NTREXBitextMining 0.90 0.94 0.91 0.01
NepaliNewsClassification 0.98 0.98 0.88 0.01
News21InstructionRetrieval 0.02 0.10 -0.00 0.00
NollySentiBitextMining 0.58 0.69 0.67 0.01
NordicLangClassification 0.72 0.86 0.80 0.01
NorwegianCourtsBitextMining 0.93 0.93 0.94 0.01
NusaParagraphEmotionClassification 0.47 0.56 0.42 0.01
NusaTranslationBitextMining 0.71 0.78 0.67 0.01
NusaX-senti 0.78 0.80 0.71 0.01
NusaXBitextMining 0.83 0.83 0.73 0.01
OdiaNewsClassification 0.85 0.92 0.80 0.01
OpusparcusPC 0.96 0.97 0.95 0.01
PAC 0.70 0.72 0.70 0.01
PawsXPairClassification 0.60 0.60 0.55 0.01
PlscClusteringP2P.v2 0.75 0.74 0.72 0.01
PoemSentimentClassification 0.72 0.60 0.51 0.01
PolEmo2.0-OUT 0.76 0.78 0.36 0.01
PpcPC 0.94 0.96 0.92 0.01
PunjabiNewsClassification 0.84 0.83 0.81 0.01
RTE3 0.89 0.90 0.88 0.01
Robust04InstructionRetrieval -0.01 -0.02 -0.07 0.00
RomaniBibleClustering 0.43 0.43 0.41 0.00
RuBQReranking 0.76 0.74 0.76 0.01
SCIDOCS 0.22 0.25 0.17 0.25
SIB200ClusteringS2S 0.45 0.42 0.24 0.00
SICK-R 0.81 0.83 0.80 0.82
STS12 0.81 0.82 0.80 0.80
STS13 0.86 0.90 0.82 0.89
STS14 0.82 0.85 0.78 0.85
STS15 0.88 0.90 0.89 0.89
STS17 0.83 0.89 0.82 0.91
STS22.v2 0.72 0.72 0.64 0.01
STSB 0.82 0.85 0.82 0.01
STSBenchmark 0.86 0.89 0.87 0.88
STSES 0.77 0.82 0.80 0.01
ScalaClassification 0.51 0.52 0.52 0.01
SemRel24STS 0.68 0.73 0.63 0.01
SentimentAnalysisHindi 0.79 0.76 0.64 0.01
SinhalaNewsClassification 0.80 0.82 0.67 0.01
SiswatiNewsClassification 0.52 0.62 0.54 0.01
SlovakMovieReviewSentimentClassification 0.94 0.90 0.74 0.01
SpartQA 0.10 0.10 0.06 0.00
SprintDuplicateQuestions 0.95 0.97 0.93 0.96
StackExchangeClustering.v2 0.66 0.92 0.46 0.01
StackOverflowQA 0.93 0.97 0.89 0.01
StatcanDialogueDatasetRetrieval 0.47 0.51 0.11 0.01
SwahiliNewsClassification 0.65 0.66 0.60 0.01
SwednClusteringP2P 0.49 0.46 0.37 0.01
SwissJudgementClassification 0.55 0.58 0.54 0.01
T2Reranking 0.67 0.68 0.66 0.01
TERRa 0.57 0.64 0.58 0.01
TRECCOVID 0.85 0.86 0.71 0.85
Tatoeba 0.81 0.82 0.76 0.01
TempReasonL1 0.02 0.03 0.01 0.00
ToxicConversationsClassification 0.86 0.89 0.66 0.87
TswanaNewsClassification 0.51 0.53 0.47 0.01
TweetTopicSingleClassification 0.78 0.71 0.65 0.01
TwitterHjerneRetrieval 0.79 0.98 0.35 0.01
TwitterURLCorpus 0.87 0.87 0.86 0.87
VoyageMMarcoReranking 0.71 0.67 0.68 0.01
WebLINXCandidatesReranking 0.16 0.11 0.08 0.00
WikiCitiesClustering 0.94 0.92 0.76 0.01
WikiClusteringP2P.v2 0.32 0.28 0.26 0.00
WikipediaRerankingMultilingual 0.89 0.92 0.89 0.01
WikipediaRetrievalMultilingual 0.90 0.94 0.90 0.01
WinoGrande 0.47 0.61 0.55 0.01
XNLI 0.82 0.85 0.75 0.01
indonli 0.58 0.61 0.52 0.01
Average 0.66 0.68 0.59 0.10

@KennethEnevoldsen KennethEnevoldsen added the waiting for review of implementation This PR is waiting for an implementation review before merging the results. label Jun 25, 2025
@YanshekWoo
Copy link
Contributor Author

YanshekWoo commented Jul 3, 2025

@KennethEnevoldsen
The Model Card for the implementation has just been merged into the MTEB. What is the status of progress here?
Is there anything that I need to do?

@Samoed Samoed merged commit f050a02 into embeddings-benchmark:main Jul 3, 2025
4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@Samoed Samoed Samoed approved these changes

Assignees

No one assigned

Labels

waiting for review of implementation This PR is waiting for an implementation review before merging the results.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@YanshekWoo @Samoed @KennethEnevoldsen