classification benchmark
MTEB English v2 Classification is the current leaderboard for MTEB(eng, v2) classification.
Updated Sep 8, 2026
Higher official leaderboard task-type mean ranks better on this benchmark.
Rank | Model | Official leaderboard task-type mean | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelTEConan-embedding-v2Tencentbac | Official leaderboard task-type mean92.23% | Percentile100.00% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank02 | ModelJCingot-8b-r3Jcorners | Official leaderboard task-type mean92.10% | Percentile99.61% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank03 | ModelVOvoyage-3-m-expVoyageai | Official leaderboard task-type mean90.81% | Percentile99.22% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank04 | ModelKLQZhou-EmbeddingKingsoft Llm | Official leaderboard task-type mean90.70% | Percentile98.83% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank05 | ModelINJasper-Token-Compression-600MInfgrad | Official leaderboard task-type mean90.25% | Percentile98.44% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank06 | ModelASGiga-Embeddings-instruct-10B-A1.8B-0826Ai Sage | Official leaderboard task-type mean89.41% | Percentile98.05% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank07 | ModelANLGAI-Embedding-PreviewAnnamodels | Official leaderboard task-type mean89.32% | Percentile97.66% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank08 | ModelSASFR-Embedding-2_RSalesforce | Official leaderboard task-type mean89.31% | Percentile97.27% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank09 | ModelASGiga-Embeddings-instruct-3B-0826Ai Sage | Official leaderboard task-type mean89.29% | Percentile96.88% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank10 | ModelNOjasper_en_vision_language_v1Novasearch | Official leaderboard task-type mean89.21% | Percentile96.48% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank11 | ModelBAbge-en-iclBaai | Official leaderboard task-type mean89.18% | Percentile96.09% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank12 | ModelAC | Official leaderboard task-type mean88.98% | Percentile95.70% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank13 | ModelGO | Official leaderboard task-type mean88.88% | Percentile95.31% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank14 | ModelCAF2LLM-v2-14BCodefuse Ai | Official leaderboard task-type mean88.85% | Percentile94.92% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank15 | ModelCAF2LLM-v2-8BCodefuse Ai | Official leaderboard task-type mean88.83% | Percentile94.53% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank16 | ModelBY | Official leaderboard task-type mean88.75% | Percentile94.14% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank17 | ModelKINano-Em1-0.6B-v2.1Kitefishai | Official leaderboard task-type mean88.74% | Percentile93.75% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank18 | ModelYILENS-d8000Yibinlei | Official leaderboard task-type mean88.72% | Percentile93.36% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank19 | ModelNOstella_en_1.5B_v5Novasearch | Official leaderboard task-type mean88.70% | Percentile92.97% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank20 | ModelBSSeed1.5-EmbeddingBytedance Seed | Official leaderboard task-type mean88.63% | Percentile92.58% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank21 | ModelCAF2LLM-v2-1.7BCodefuse Ai | Official leaderboard task-type mean88.61% | Percentile92.19% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank22 | ModelKEKaLM-embedding-multilingual-mini-instruct-v2.5Kalm Embedding | Official leaderboard task-type mean88.57% | Percentile91.80% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank23 | ModelYILENS-d4000Yibinlei | Official leaderboard task-type mean88.51% | Percentile91.41% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank24 | ModelAC | Official leaderboard task-type mean88.43% | Percentile91.02% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank25 | ModelASGiga-Embeddings-instructAi Sage | Official leaderboard task-type mean88.39% | Percentile90.63% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank26 | ModelCAF2LLM-v2-4BCodefuse Ai | Official leaderboard task-type mean88.39% | Percentile90.23% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank27 | ModelNV | Official leaderboard task-type mean87.94% | Percentile89.84% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank28 | ModelCAF2LLM-v2-0.6BCodefuse Ai | Official leaderboard task-type mean87.92% | Percentile89.45% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank29 | ModelJIjina-embeddings-v5-omni-smallJinaai | Official leaderboard task-type mean87.85% | Percentile89.06% | Participants257 | EvidenceA | EvaluatedN/A |
| Rank30 | ModelJIjina-embeddings-v5-text-smallJinaai | Official leaderboard task-type mean87.85% | Percentile88.67% | Participants257 | EvidenceA | EvaluatedN/A |
The leading models and scores on this benchmark.
A closer view of the leading scores on this benchmark.
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What MTEB English v2 Classification measures and how its scores work.
MTEB English v2 Classification is a classification benchmark.
It reports the Official leaderboard task-type mean as a ratio.
Scores are shown in ratio. This benchmark is verified and has an evidence level of A.
MTEB. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about MTEB English v2 Classification.
Conan-embedding-v2 is currently ranked first with 92.23%.
The current leaders are Conan-embedding-v2 (92.23%), ingot-8b-r3 (92.10%), and voyage-3-m-exp (90.81%).
Gemini Embedding 001 has the lowest matched official input price at $0.15 input per 1M tokens.
No matched runtime record is currently available.
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.
It reports the Official leaderboard task-type mean as a ratio.
Yes. Higher values rank better for this benchmark.
100 model results are currently shown.
No. This benchmark is shown for reference but does not contribute to the overall score.
Ranking basisThis mteb english v2 classification AI model leaderboard uses descending official leaderboard task-type mean in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
Selection summary
Conan-embedding-v2 currently leads MTEB English v2 Classification with 92.23%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.