Evaluating several spanish embedding models

[bukosabino]

python mteb_benchmark.py

Benchmark	dariolopez__roberta-base-bne-finetuned-msmarco-qa-es-mnrl-mn	intfloat__multilingual-e5-large	BAAI/bge-m3
AmazonReviewsClassification	0.28194	0.42702	0.44678000000000007
CataloniaTweetClassification	0.48369999999999996	0.5025000000000001	0.4875999999999999
MassiveIntentClassification	0.5473100201748486	0.6470073974445192	0.6703429724277068
MassiveScenarioClassification	0.6322797579018158	0.689340954942838	0.721990585070612
MintakaRetrieval	0.16548	0.2836	0.22341
MIRACLRetrieval	0.70137	0.82005	-
MLSUMClusteringS2S.v2	0.42841628413893035	0.48075917245775485	-
MTOPDomainClassification	0.7924616410940628	0.8998999332888593	0.9183789192795198
MTOPIntentClassification	0.5307538358905937	0.6673782521681121	0.6644096064042696
MultiEURLEXMultilabelClassification	0.05144	0.05226000000000001	-
MultiHateClassification	0.5578	0.639	0.6253
PawsX	0.6015684593563027	0.5639685167829116	0.5735093608198505
PublicHealthQA	0.62516	0.80811	0.79986
SIB200Classification	0.6549019607843137	0.7348039215686275	0.7313725490196079
SIB200ClusteringS2S	0.3347573603718645	0.3637865013678009	0.34998316595531576
SpanishNewsClassification	0.81318359375	0.880517578125	-
SpanishNewsClusteringP2P	0.379918321557151	0.4399933663826367	-
SpanishSentimentClassification	0.6378378378378378	0.9141891891891893	0.9395270270270271
STS17	0.23167578806693545	0.8092850520982419	0.7557298844031564
STS22	0.49970798735740846	0.7865922376187726
STSBenchmarkMultilingualSTS	0.7724973718736371	0.8646354604520479	0.8468700424822017
STSES	0.6040795444089487	0.7923804835012699	0.7743978294342545
TweetSentimentClassification	0.408203125	0.508984375	0.54765625
XMarket	0.11391	0.14136	-
XNLI	0.5793703625227221	0.7603625574106656	0.8076605260070395
XPQARetrieval	0.47322	0.61619	0.62131
XQuADRetrieval	0.81996	0.97644	0.96649