FinMTEB

Rank	Model	Overall (EN)	Classification	Clustering	Pair Class.	Reranking	Retrieval	STS	Summarization
1	paraphrase-multilingual-MiniLM-L12-v2	0.692	0.757	0.565	0.801	0.990	0.711	0.434	0.480

Rank

Model

Overall (EN)

Classification

Clustering

Pair Class.

Reranking

Retrieval

STS

Summarization

paraphrase-multilingual-MiniLM-L12-v2

0.692

0.757

0.565

0.801

0.990

0.711

0.434

0.480

Rank	Model	Overall (EN)	Classification	Clustering	Pair Class.	Reranking	Retrieval	STS	Summarization
1	Fin-e5	0.692	0.757	0.565	0.801	0.990	0.711	0.434	0.480
2	voyage-3-large	0.692	0.686	0.594	0.652	0.994	0.746	0.415	0.648
3	text-embedding-3-large	0.675	0.660	0.608	0.731	0.991	0.711	0.362	0.567
4	e5-mistral-7b-instruct	0.654	0.645	0.578	0.739	0.988	0.675	0.380	0.527
5	NV-Embed v2	0.653	0.639	0.610	0.604	0.982	0.706	0.374	0.510
6	bge-large-en-v1.5	0.647	0.644	0.573	0.740	0.983	0.675	0.340	0.486
7	gte-Qwen1.5-7B-instruct	0.641	0.644	0.585	0.700	0.989	0.636	0.376	0.535
8	bge-m3	0.638	0.657	0.543	0.745	0.979	0.646	0.374	0.480
9	text-embedding-3-small	0.633	0.639	0.580	0.596	0.982	0.664	0.325	0.509
10	bge-en-icl	0.619	0.657	0.574	0.674	0.990	0.577	0.323	0.520
11	all-MiniLM-L12-v2	0.613	0.599	0.554	0.717	0.968	0.670	0.305	0.330
12	instructor-base	0.562	0.621	0.530	0.614	0.973	0.473	0.373	0.431
13	paraphrase-multilingual-MiniLM-L12-v2	0.557	0.591	0.473	0.740	0.921	0.566	0.259	0.254
14	msmarco-bert-base-dot-v5	0.554	0.568	0.512	0.643	0.934	0.525	0.301	0.401
15	BOW	0.387	0.470	0.255	0.714	0.763	0.208	0.485	0.258
16	FinBERT (CLS)	0.371	0.592	0.283	0.697	0.640	0.110	0.420	0.201
17	BERT (CLS)	0.292	0.550	0.174	0.711	0.393	0.021	0.379	0.169

Rank

Model

Overall (EN)

Classification

Clustering

Pair Class.

Reranking

Retrieval

STS

Summarization

Fin-e5

0.692

0.757

0.565

0.801

0.990

0.711

0.434

0.480

voyage-3-large

0.692

0.686

0.594

0.652

0.994

0.746

0.415

0.648

text-embedding-3-large

0.675

0.660

0.608

0.731

0.991

0.711

0.362

0.567

e5-mistral-7b-instruct

0.654

0.645

0.578

0.739

0.988

0.675

0.380

0.527

NV-Embed v2

0.653

0.639

0.610

0.604

0.982

0.706

0.374

0.510

bge-large-en-v1.5

0.647

0.644

0.573

0.740

0.983

0.675

0.340

0.486

gte-Qwen1.5-7B-instruct

0.641

0.644

0.585

0.700

0.989

0.636

0.376

0.535

bge-m3

0.638

0.657

0.543

0.745

0.979

0.646

0.374

0.480

text-embedding-3-small

0.633

0.639

0.580

0.596

0.982

0.664

0.325

0.509

bge-en-icl

0.619

0.657

0.574

0.674

0.990

0.577

0.323

0.520

all-MiniLM-L12-v2

0.613

0.599

0.554

0.717

0.968

0.670

0.305

0.330

instructor-base

0.562

0.621

0.530

0.614

0.973

0.473

0.373

0.431

paraphrase-multilingual-MiniLM-L12-v2

0.557

0.591

0.473

0.740

0.921

0.566

0.259

0.254

msmarco-bert-base-dot-v5

0.554

0.568

0.512

0.643

0.934

0.525

0.301

0.401

BOW

0.387

0.470

0.255

0.714

0.763

0.208

0.485

0.258

FinBERT (CLS)

0.371

0.592

0.283

0.697

0.640

0.110

0.420

0.201

BERT (CLS)

0.292

0.550

0.174

0.711

0.393

0.021

0.379

0.169

Rank	Model	Overall (ZH)	Classification	Clustering	Pair Class.	Reranking	Retrieval	STS	Summarization
1	paraphrase-multilingual-MiniLM-L12-v2	0.998	-	-	-	-	-	-	-

Rank

Model

Overall (ZH)

Classification

Clustering

Pair Class.

Reranking

Retrieval

STS

Summarization

paraphrase-multilingual-MiniLM-L12-v2

0.998

Rank	Model	Overall (ZH)	Classification	Clustering	Pair Class.	Reranking	Retrieval	STS	Summarization
1	Qwen3-Reranker-8B true_logit RRF	0.998	-	-	-	0.998	-	-	-
2	gte-Qwen1.5-7B-instruct	0.636	0.620	0.617	0.597	0.992	0.642	0.571	0.493
3	bge-m3	0.625	0.621	0.711	0.533	0.990	0.624	0.508	0.358
4	bge-large-zh-v1.5	0.622	0.600	0.667	0.551	0.993	0.607	0.581	0.441
5	text-embedding-3-large	0.604	0.604	-	-	-	-	-	-
6	paraphrase-multilingual-MiniLM-L12-v2	0.457	0.559	0.461	0.388	0.967	0.379	0.278	0.344
7	BOW	0.394	0.469	0.420	0.338	0.909	0.300	0.203	0.343
8	all-MiniLM-L12-v2	0.312	0.440	0.224	0.338	0.794	0.178	0.145	0.473

Rank

Model

Overall (ZH)

Classification

Clustering

Pair Class.

Reranking

Retrieval

STS

Summarization

Qwen3-Reranker-8B true_logit RRF

0.998

gte-Qwen1.5-7B-instruct

0.636

0.620

0.617

0.597

0.992

0.642

0.571

0.493

bge-m3

0.625

0.621

0.711

0.533

0.990

0.624

0.508

0.358

bge-large-zh-v1.5

0.622

0.600

0.667

0.551

0.993

0.607

0.581

0.441

text-embedding-3-large

0.604

paraphrase-multilingual-MiniLM-L12-v2

0.457

0.559

0.461

0.388

0.967

0.379

0.278

0.344

BOW

0.394

0.469

0.420

0.338

0.909

0.300

0.203

0.343

all-MiniLM-L12-v2

0.312

0.440

0.224

0.338

0.794

0.178

0.145

0.473

Rank	Model	Avg.	FINAL	FinSTS
1	paraphrase-multilingual-MiniLM-L12-v2	0.485	0.700	0.269

Rank	Model	Avg.	FINAL	FinSTS
1	BOW	0.485	0.700	0.269
2	Fin-e5	0.434	0.557	0.311
3	FinBERT (CLS)	0.420	0.501	0.338
4	voyage-3-large	0.415	0.563	0.266
5	e5-mistral-7b-instruct	0.380	0.492	0.268
6	BERT (CLS)	0.379	0.497	0.261
7	gte-Qwen1.5-7B-instruct	0.376	0.510	0.241
8	NV-Embed v2	0.374	0.503	0.245
9	bge-m3	0.374	0.486	0.263
10	instructor-base	0.373	0.495	0.252
11	text-embedding-3-large	0.362	0.451	0.272
12	bge-large-en-v1.5	0.340	0.512	0.168
13	text-embedding-3-small	0.325	0.426	0.225
14	bge-en-icl	0.323	0.480	0.167
15	all-MiniLM-L12-v2	0.305	0.420	0.191
16	msmarco-bert-base-dot-v5	0.301	0.383	0.218
17	paraphrase-multilingual-MiniLM-L12-v2	0.259	0.391	0.127

Rank	Model	Avg.	AFQMC	BQCorpus
1	paraphrase-multilingual-MiniLM-L12-v2	0.581	0.471	0.691

Rank	Model	Avg.	AFQMC	BQCorpus
1	bge-large-zh-v1.5	0.581	0.471	0.691
2	gte-Qwen1.5-7B-instruct	0.571	0.506	0.637
3	bge-m3	0.508	0.421	0.595
4	paraphrase-multilingual-MiniLM-L12-v2	0.278	0.141	0.414
5	BOW	0.203	0.063	0.343
6	all-MiniLM-L12-v2	0.145	0.064	0.226

Rank	Model	Avg.	ESGClassification	FLSClassification	FOMCClassification	FiQAClassification	FinSentClassification	FinancialFraudClassification	FinancialPhraseBankClassification	SemEva2017Classification
1	paraphrase-multilingual-MiniLM-L12-v2	0.757	0.911	0.584	0.645	0.901	0.718	0.692	0.859	0.743

Rank	Model	Avg.	ESGClassification	FLSClassification	FOMCClassification	FiQAClassification	FinSentClassification	FinancialFraudClassification	FinancialPhraseBankClassification	SemEva2017Classification
1	Fin-e5	0.757	0.911	0.584	0.645	0.901	0.718	0.692	0.859	0.743
2	voyage-3-large	0.686	0.847	0.612	0.464	0.734	0.602	0.759	0.851	0.620
3	text-embedding-3-large	0.660	0.862	0.569	0.452	0.714	0.566	0.706	0.817	0.591
4	bge-en-icl	0.657	0.821	0.528	0.466	0.675	0.609	0.745	0.796	0.617
5	bge-m3	0.657	0.769	0.537	0.436	0.740	0.585	0.743	0.818	0.627
6	e5-mistral-7b-instruct	0.645	0.796	0.530	0.469	0.620	0.559	0.769	0.812	0.604
7	bge-large-en-v1.5	0.644	0.782	0.540	0.437	0.613	0.587	0.755	0.809	0.627
8	gte-Qwen1.5-7B-instruct	0.644	0.843	0.568	0.457	0.656	0.564	0.747	0.745	0.571
9	NV-Embed v2	0.639	0.846	0.584	0.445	0.631	0.533	0.731	0.791	0.552
10	text-embedding-3-small	0.639	0.837	0.549	0.437	0.657	0.539	0.731	0.774	0.585
11	instructor-base	0.621	0.769	0.538	0.429	0.633	0.563	0.708	0.784	0.542
12	all-MiniLM-L12-v2	0.599	0.764	0.516	0.419	0.578	0.537	0.710	0.782	0.488
13	FinBERT (CLS)	0.592	0.769	0.571	0.389	0.594	0.528	0.661	0.726	0.500
14	paraphrase-multilingual-MiniLM-L12-v2	0.591	0.737	0.514	0.411	0.560	0.551	0.706	0.733	0.519
15	msmarco-bert-base-dot-v5	0.568	0.746	0.494	0.407	0.596	0.466	0.702	0.668	0.466
16	BERT (CLS)	0.550	0.689	0.558	0.369	0.558	0.466	0.624	0.674	0.459
17	BOW	0.470	0.361	0.404	0.349	0.594	0.369	0.743	0.577	0.361

Rank	Model	Avg.	FinChinaSentimentClassification	FinFEClassification	FinNSPClassification	OpenFinDataSentimentClassification	Weibo21Classification
1	paraphrase-multilingual-MiniLM-L12-v2	0.621	0.346	0.545	0.897	0.643	0.672

Rank	Model	Avg.	FinChinaSentimentClassification	FinFEClassification	FinNSPClassification	OpenFinDataSentimentClassification	Weibo21Classification
1	bge-m3	0.621	0.346	0.545	0.897	0.643	0.672
2	gte-Qwen1.5-7B-instruct	0.620	0.305	0.558	0.894	0.604	0.739
3	text-embedding-3-large	0.604	0.316	0.519	0.933	0.556	0.696
4	bge-large-zh-v1.5	0.600	0.312	0.558	0.900	0.500	0.729
5	paraphrase-multilingual-MiniLM-L12-v2	0.559	0.316	0.456	0.795	0.552	0.674
6	BOW	0.469	0.293	0.372	0.712	0.335	0.635
7	all-MiniLM-L12-v2	0.440	0.220	0.358	0.673	0.283	0.665

Rank	Model	Avg.	Apple10KRetrieval	FiQA2018Retrieval	FinQARetrieval	FinanceBenchRetrieval	HC3Retrieval	TATQARetrieval	TheGoldmanEnRetrieval	TradeTheEventEncyclopediaRetrieval	TradeTheEventNewsRetrieval	USNewsRetrieval
1	paraphrase-multilingual-MiniLM-L12-v2	0.746	0.908	0.591	0.331	0.898	0.709	0.351	0.738	0.992	0.976	0.968

Rank	Model	Avg.	Apple10KRetrieval	FiQA2018Retrieval	FinQARetrieval	FinanceBenchRetrieval	HC3Retrieval	TATQARetrieval	TheGoldmanEnRetrieval	TradeTheEventEncyclopediaRetrieval	TradeTheEventNewsRetrieval	USNewsRetrieval
1	voyage-3-large	0.746	0.908	0.591	0.331	0.898	0.709	0.351	0.738	0.992	0.976	0.968
2	Fin-e5	0.711	0.858	0.549	0.201	0.842	0.679	0.288	0.755	0.989	0.984	0.959
3	text-embedding-3-large	0.711	0.896	0.549	0.166	0.815	0.655	0.274	0.817	0.997	0.974	0.969
4	NV-Embed v2	0.706	0.904	0.605	0.161	0.814	0.725	0.277	0.657	0.996	0.971	0.951
5	bge-large-en-v1.5	0.675	0.879	0.501	0.166	0.826	0.619	0.261	0.578	0.995	0.974	0.951
6	e5-mistral-7b-instruct	0.675	0.879	0.501	0.166	0.826	0.619	0.261	0.578	0.995	0.974	0.951
7	all-MiniLM-L12-v2	0.670	0.873	0.527	0.166	0.759	0.646	0.245	0.573	0.992	0.969	0.946
8	text-embedding-3-small	0.664	0.922	0.452	0.147	0.791	0.571	0.261	0.572	0.993	0.971	0.961
9	bge-m3	0.646	0.880	0.475	0.156	0.747	0.592	0.260	0.449	0.990	0.964	0.952
10	gte-Qwen1.5-7B-instruct	0.636	0.892	0.425	0.173	0.757	0.546	0.266	0.384	0.992	0.970	0.954
11	bge-en-icl	0.577	0.879	0.392	0.100	0.668	0.505	0.176	0.329	0.980	0.920	0.823
12	paraphrase-multilingual-MiniLM-L12-v2	0.566	0.841	0.389	0.085	0.680	0.514	0.192	0.355	0.988	0.861	0.750
13	msmarco-bert-base-dot-v5	0.525	0.823	0.228	0.106	0.600	0.340	0.178	0.298	0.969	0.903	0.810
14	instructor-base	0.473	0.811	0.209	0.064	0.461	0.316	0.148	0.247	0.956	0.754	0.763
15	BOW	0.208	0.573	0.034	0.075	0.069	0.071	0.134	0.077	0.509	0.418	0.123
16	FinBERT (CLS)	0.110	0.547	0.005	0.034	0.171	0.021	0.066	0.039	0.145	0.053	0.020
17	BERT (CLS)	0.021	0.139	0.001	0.002	0.023	0.007	0.004	0.011	0.002	0.005	0.013

Rank	Model	Avg.	AlphaFinRetrieval	DISCFinLLMComputingRetrieval	DISCFinLLMRetrieval	DuEEFinRetrieval	FinEvaEncyclopediaRetrieval	FinEvaRetrieval	FinTruthQARetrieval	SmoothNLPRetrieval	THUCNewsRetrieval	TheGoldmanZhRetrieval
1	paraphrase-multilingual-MiniLM-L12-v2	0.642	0.688	0.988	0.667	0.202	0.459	0.960	0.401	0.806	0.627	0.622

Rank	Model	Avg.	AlphaFinRetrieval	DISCFinLLMComputingRetrieval	DISCFinLLMRetrieval	DuEEFinRetrieval	FinEvaEncyclopediaRetrieval	FinEvaRetrieval	FinTruthQARetrieval	SmoothNLPRetrieval	THUCNewsRetrieval	TheGoldmanZhRetrieval
1	gte-Qwen1.5-7B-instruct	0.642	0.688	0.988	0.667	0.202	0.459	0.960	0.401	0.806	0.627	0.622
2	bge-m3	0.624	0.706	0.921	0.664	0.251	0.450	0.961	0.422	0.751	0.653	0.465
3	bge-large-zh-v1.5	0.607	0.664	0.948	0.672	0.243	0.432	0.955	0.433	0.695	0.588	0.442
4	paraphrase-multilingual-MiniLM-L12-v2	0.379	0.487	0.807	0.646	0.036	0.316	0.878	0.242	0.049	0.140	0.195
5	BOW	0.300	0.362	0.728	0.456	0.023	0.176	0.794	0.095	0.179	0.109	0.077
6	all-MiniLM-L12-v2	0.178	0.125	0.478	0.381	0.018	0.128	0.479	0.052	0.054	0.037	0.024

Rank	Model	Avg.	ComplaintsClustering	FinanceArxivP2PClustering	FinanceArxivS2SClustering	MInDS14EnClustering	PiiClustering	WikiCompany2IndustryClustering
1	paraphrase-multilingual-MiniLM-L12-v2	0.610	0.514	0.287	0.291	0.923	0.900	0.741

Rank	Model	Avg.	ComplaintsClustering	FinanceArxivP2PClustering	FinanceArxivS2SClustering	MInDS14EnClustering	PiiClustering	WikiCompany2IndustryClustering
1	NV-Embed v2	0.610	0.514	0.287	0.291	0.923	0.900	0.741
2	text-embedding-3-large	0.608	0.462	0.282	0.297	0.930	0.926	0.752
3	voyage-3-large	0.594	0.436	0.288	0.303	0.910	0.877	0.752
4	gte-Qwen1.5-7B-instruct	0.585	0.505	0.297	0.295	0.870	0.885	0.659
5	text-embedding-3-small	0.580	0.449	0.275	0.265	0.911	0.889	0.692
6	e5-mistral-7b-instruct	0.578	0.470	0.274	0.279	0.799	0.911	0.736
7	bge-en-icl	0.574	0.498	0.281	0.274	0.812	0.882	0.699
8	bge-large-en-v1.5	0.573	0.415	0.259	0.257	0.906	0.866	0.732
9	Fin-e5	0.565	0.459	0.256	0.259	0.773	0.879	0.764
10	all-MiniLM-L12-v2	0.554	0.369	0.251	0.253	0.898	0.863	0.692
11	bge-m3	0.543	0.340	0.243	0.235	0.908	0.885	0.648
12	instructor-base	0.530	0.343	0.234	0.229	0.906	0.834	0.635
13	msmarco-bert-base-dot-v5	0.512	0.267	0.206	0.209	0.896	0.842	0.648
14	paraphrase-multilingual-MiniLM-L12-v2	0.473	0.285	0.165	0.172	0.869	0.819	0.529
15	FinBERT (CLS)	0.283	0.059	0.075	0.069	0.423	0.703	0.371
16	BOW	0.255	0.044	0.025	0.015	0.627	0.663	0.153
17	BERT (CLS)	0.174	0.033	0.052	0.051	0.196	0.631	0.083

Rank	Model	Avg.	CCKS2019Clustering	CCKS2020Clustering	CCKS2022Clustering	FinNLClustering	MInDS14ZhClustering
1	paraphrase-multilingual-MiniLM-L12-v2	0.711	0.431	0.976	0.789	0.452	0.906

Rank	Model	Avg.	CCKS2019Clustering	CCKS2020Clustering	CCKS2022Clustering	FinNLClustering	MInDS14ZhClustering
1	bge-m3	0.711	0.431	0.976	0.789	0.452	0.906
2	bge-large-zh-v1.5	0.667	0.354	0.927	0.784	0.398	0.872
3	gte-Qwen1.5-7B-instruct	0.617	0.346	0.919	0.533	0.423	0.865
4	paraphrase-multilingual-MiniLM-L12-v2	0.461	0.173	0.349	0.624	0.345	0.815
5	BOW	0.420	0.323	0.875	0.229	0.155	0.520
6	all-MiniLM-L12-v2	0.224	0.172	0.255	0.128	0.175	0.391

Rank	Model	Avg.	FiQA2018Reranking	FinFactReranking	HC3Reranking
1	paraphrase-multilingual-MiniLM-L12-v2	0.994	0.990	0.997	0.994

Rank	Model	Avg.	FiQA2018Reranking	FinFactReranking	HC3Reranking
1	voyage-3-large	0.994	0.990	0.997	0.994
2	text-embedding-3-large	0.991	0.983	0.999	0.992
3	Fin-e5	0.990	0.983	0.995	0.991
4	bge-en-icl	0.990	0.984	0.991	0.995
5	gte-Qwen1.5-7B-instruct	0.989	0.986	0.994	0.988
6	e5-mistral-7b-instruct	0.988	0.979	0.994	0.990
7	bge-large-en-v1.5	0.983	0.968	0.993	0.986
8	NV-Embed v2	0.982	0.973	0.984	0.990
9	text-embedding-3-small	0.982	0.964	0.996	0.987
10	bge-m3	0.979	0.958	0.994	0.983
11	instructor-base	0.973	0.949	0.993	0.979
12	all-MiniLM-L12-v2	0.968	0.947	0.975	0.982
13	msmarco-bert-base-dot-v5	0.934	0.872	0.985	0.946
14	paraphrase-multilingual-MiniLM-L12-v2	0.921	0.856	0.960	0.949
15	BOW	0.763	0.581	0.924	0.783
16	FinBERT (CLS)	0.640	0.570	0.676	0.675
17	BERT (CLS)	0.393	0.339	0.460	0.381

Rank	Model	Avg.	DISCFinLLMReranking	FinEvaReranking
1	paraphrase-multilingual-MiniLM-L12-v2	0.998	0.996	1.000

Rank	Model	Avg.	DISCFinLLMReranking	FinEvaReranking
1	Qwen3-Reranker-8B true_logit RRF	0.998	0.996	1.000
2	bge-large-zh-v1.5	0.993	0.996	0.991
3	gte-Qwen1.5-7B-instruct	0.992	0.984	1.000
4	bge-m3	0.990	0.990	0.991
5	paraphrase-multilingual-MiniLM-L12-v2	0.967	0.975	0.959
6	BOW	0.909	0.867	0.951
7	all-MiniLM-L12-v2	0.794	0.767	0.822

Rank	Model	Avg.	Ectsum	FINDsum	FNS2022sum
1	paraphrase-multilingual-MiniLM-L12-v2	0.648	0.399	0.700	0.847

Rank	Model	Avg.	Ectsum	FINDsum	FNS2022sum
1	voyage-3-large	0.648	0.399	0.700	0.847
2	text-embedding-3-large	0.567	0.236	0.605	0.860
3	gte-Qwen1.5-7B-instruct	0.535	0.235	0.564	0.807
4	e5-mistral-7b-instruct	0.527	0.221	0.504	0.857
5	bge-en-icl	0.520	0.216	0.487	0.855
6	NV-Embed v2	0.510	0.281	0.427	0.823
7	text-embedding-3-small	0.509	0.195	0.486	0.845
8	bge-large-en-v1.5	0.486	0.202	0.405	0.851
9	Fin-e5	0.480	0.254	0.416	0.768
10	bge-m3	0.480	0.218	0.383	0.840
11	instructor-base	0.431	0.146	0.336	0.812
12	msmarco-bert-base-dot-v5	0.401	0.107	0.320	0.775
13	all-MiniLM-L12-v2	0.330	0.092	0.140	0.757
14	BOW	0.258	0.054	0.357	0.364
15	paraphrase-multilingual-MiniLM-L12-v2	0.254	0.064	0.091	0.607
16	FinBERT (CLS)	0.201	0.042	0.225	0.336
17	BERT (CLS)	0.169	0.045	0.177	0.283

Rank	Model	Avg.	FiNNAsum	FinEvaHeadlinesum	FinEvasum
1	paraphrase-multilingual-MiniLM-L12-v2	0.493	0.863	-0.249	0.528

Rank	Model	Avg.	FiNNAsum	FinEvaHeadlinesum	FinEvasum
1	gte-Qwen1.5-7B-instruct	0.493	0.863	0.089	0.528
2	all-MiniLM-L12-v2	0.473	0.689	0.307	0.423
3	bge-large-zh-v1.5	0.441	0.866	0.093	0.366
4	bge-m3	0.358	0.866	0.029	0.180
5	paraphrase-multilingual-MiniLM-L12-v2	0.344	0.854	0.092	0.086
6	BOW	0.343	0.806	-0.249	0.473

Rank	Model	Avg.	HeadlineACPairClassification	HeadlinePDDPairClassification	HeadlinePDUPairClassification
1	paraphrase-multilingual-MiniLM-L12-v2	0.801	0.777	0.848	0.778

Rank	Model	Avg.	HeadlineACPairClassification	HeadlinePDDPairClassification	HeadlinePDUPairClassification
1	Fin-e5	0.801	0.777	0.848	0.778
2	bge-m3	0.745	0.752	0.731	0.752
3	bge-large-en-v1.5	0.740	0.752	0.703	0.766
4	paraphrase-multilingual-MiniLM-L12-v2	0.740	0.757	0.698	0.765
5	e5-mistral-7b-instruct	0.739	0.750	0.719	0.750
6	text-embedding-3-large	0.731	0.764	0.664	0.764
7	all-MiniLM-L12-v2	0.717	0.757	0.635	0.757
8	BOW	0.714	0.773	0.602	0.768
9	BERT (CLS)	0.711	0.771	0.590	0.771
10	gte-Qwen1.5-7B-instruct	0.700	0.733	0.609	0.757
11	FinBERT (CLS)	0.697	0.748	0.594	0.748
12	bge-en-icl	0.674	0.661	0.699	0.661
13	voyage-3-large	0.652	0.640	0.675	0.640
14	msmarco-bert-base-dot-v5	0.643	0.562	0.593	0.773
15	instructor-base	0.614	0.602	0.637	0.602
16	NV-Embed v2	0.604	0.593	0.628	0.593
17	text-embedding-3-small	0.596	0.584	0.619	0.584

Rank	Model	Avg.	AFQMCPairClassification
1	paraphrase-multilingual-MiniLM-L12-v2	0.597	0.597

Rank	Model	Avg.	AFQMCPairClassification
1	gte-Qwen1.5-7B-instruct	0.597	0.597
2	bge-large-zh-v1.5	0.551	0.551
3	bge-m3	0.533	0.533
4	paraphrase-multilingual-MiniLM-L12-v2	0.388	0.388
5	BOW	0.338	0.338
6	all-MiniLM-L12-v2	0.338	0.338

We welcome results from any embedding model. To add your model to the leaderboard, email the per-dataset scores to ytangch@connect.ust.hk.

Please include:

Model name and a link to the model page or paper
Per-dataset scores for each task and language
Any relevant methodology notes

We review submissions regularly. Thank you for contributing.

English

Chinese

English

Chinese

English

Chinese

English

Chinese

English

Chinese

English

Chinese

English

Chinese

English

Chinese

Submit results