MTEB(eng, v2) Classification Leaderboard

Ranking basisThis mteb(eng, v2) classification AI model leaderboard uses descending official leaderboard task-type mean in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

1. 01
   TE

   Conan-embedding-v2Tencentbac

   Official leaderboard task-type mean

   92.2%

   Strengths

   • Ranks #1 of 253 compared models
   • A evidence result

   Considerations

   • This result measures MTEB(eng, v2) Classification, not total model capability
2. 02
   JC

   ingot-8b-r3Jcorners

   Official leaderboard task-type mean

   92.1%

   Strengths

   • Ranks #2 of 253 compared models
   • A evidence result

   Considerations

   • This result measures MTEB(eng, v2) Classification, not total model capability
3. 03
   VO

   voyage-3-m-expVoyageai

   Official leaderboard task-type mean

   90.8%

   Strengths

   • Ranks #3 of 253 compared models
   • A evidence result

   Considerations

   • This result measures MTEB(eng, v2) Classification, not total model capability
4. 04
   KL

   QZhou-EmbeddingKingsoft Llm

   Official leaderboard task-type mean

   90.7%

   Strengths

   • Ranks #4 of 253 compared models
   • A evidence result

   Considerations

   • This result measures MTEB(eng, v2) Classification, not total model capability
5. 05
   IN

   Jasper-Token-Compression-600MInfgrad

   Official leaderboard task-type mean

   90.3%

   Strengths

   • Ranks #5 of 253 compared models
   • A evidence result

   Considerations

   • This result measures MTEB(eng, v2) Classification, not total model capability