Model catalog
This embedding model leaderboard compares the available benchmark ranking, score status, pricing and vector specifications across text and multimodal models.
Data as of 2026-09-08
Browse the embedding leaderboard ranking alongside the full catalog. Models without enough comparable benchmark evidence remain unscored.
Model | LLMBoard score | Input -> output | Context | Parameters | Capabilities | Released |
|---|
| ModelKLQZhou-EmbeddingKingsoft Llm | LLMBoard score90.18 | Input -> outputtext -> embedding | Context8.2K | Parameters7.1B | CapabilitiesN/A | Released |
| ModelJCingot-8b-r3Jcorners | LLMBoard score89.89 | Input -> outputtext -> embedding | Context32.8K | Parameters7.6B | CapabilitiesN/A | Released |
| ModelINJasper-Token-Compression-600MInfgrad | LLMBoard score89.23 | Input -> outputtext -> embedding | Context32.8K | Parameters607M | CapabilitiesN/A | Released |
| ModelAC | LLMBoard score89.07 | Input -> outputtext -> embedding | Context32.8K | Parameters7.6B | CapabilitiesN/A | Released |
| ModelBSSeed1.5-EmbeddingBytedance Seed | LLMBoard score88.41 | Input -> outputtext -> embedding | Context32.8K | ParametersN/A | CapabilitiesN/A | Released |
| ModelAC | LLMBoard score87.69 | Input -> outputtext -> embedding | Context32.8K | Parameters4B | CapabilitiesN/A | Released |
| ModelBY | LLMBoard score87.33 | Input -> outputtext, image -> embedding | Context32.8K | ParametersN/A | CapabilitiesN/A | Released |
| ModelANLGAI-Embedding-PreviewAnnamodels | LLMBoard score86.76 | Input -> outputtext -> embedding | Context32.8K | Parameters7.1B | CapabilitiesN/A | Released |
| ModelCAF2LLM-v2-14BCodefuse Ai | LLMBoard score85.90 | Input -> outputtext -> embedding | Context41K | Parameters14B | CapabilitiesN/A | Released |
| ModelGO | LLMBoard score85.37 | Input -> outputtext -> text | Context2K | ParametersN/A | CapabilitiesN/A | Released |
| ModelCAF2LLM-v2-8BCodefuse Ai | LLMBoard score85.03 | Input -> outputtext -> embedding | Context41K | Parameters7.6B | CapabilitiesN/A | Released |
| ModelASGiga-Embeddings-instruct-3B-0826Ai Sage | LLMBoard score83.68 | Input -> outputtext -> embedding | Context8.2K | Parameters3.2B | CapabilitiesN/A | Released |
| ModelASGiga-Embeddings-instruct-10B-A1.8B-0826Ai Sage | LLMBoard score83.25 | Input -> outputtext -> embedding | Context8.2K | Parameters10.5B | CapabilitiesN/A | Released |
| ModelCAF2LLM-4BCodefuse Ai | LLMBoard score82.99 | Input -> outputtext -> embedding | Context8.2K | Parameters4B | CapabilitiesN/A | Released |
| ModelJIjina-embeddings-v5-text-smallJinaai | LLMBoard score82.89 | Input -> outputtext -> embedding | Context32.8K | Parameters596M | CapabilitiesN/A | Released |
| ModelCAF2LLM-v2-4BCodefuse Ai | LLMBoard score82.57 | Input -> outputtext -> embedding | Context41K | Parameters4B | CapabilitiesN/A | Released |
| ModelIEYuan-embedding-2.0-enIeityuan | LLMBoard score82.17 | Input -> outputtext -> embedding | Context2K | Parameters596M | CapabilitiesN/A | Released |
| ModelLALinq-Embed-MistralLinq Ai Research | LLMBoard score80.70 | Input -> outputtext -> embedding | Context32.8K | Parameters7.1B | CapabilitiesN/A | Released |
| ModelJIjina-embeddings-v5-text-nanoJinaai | LLMBoard score80.42 | Input -> outputtext -> embedding | Context8.2K | Parameters212M | CapabilitiesN/A | Released |
| ModelNOjasper_en_vision_language_v1Novasearch | LLMBoard score80.29 | Input -> outputtext -> embedding | Context131.1K | Parameters1.6B | CapabilitiesN/A | Released |
| ModelASGiga-Embeddings-instructAi Sage | LLMBoard score80.03 | Input -> outputtext -> embedding | Context4.1K | Parameters3.2B | CapabilitiesN/A | Released |
| ModelCAF2LLM-v2-1.7BCodefuse Ai | LLMBoard score80.00 | Input -> outputtext -> embedding | Context41K | Parameters1.7B | CapabilitiesN/A | Released |
| ModelAC | LLMBoard score79.89 | Input -> outputtext -> embedding | Context32.8K | Parameters596M | CapabilitiesN/A | Released |
| ModelCAF2LLM-1.7BCodefuse Ai | LLMBoard score79.83 | Input -> outputtext -> embedding | Context8.2K | Parameters1.7B | CapabilitiesN/A | Released |
| ModelSASFR-Embedding-MistralSalesforce | LLMBoard score79.55 | Input -> outputtext -> embedding | Context32.8K | Parameters7.1B | CapabilitiesN/A | Released |
| ModelNV | LLMBoard score79.21 | Input -> outputtext -> embedding | Context32.8K | Parameters7.9B | CapabilitiesN/A | Released |
| ModelKEKaLM-embedding-multilingual-mini-instruct-v2.5Kalm Embedding | LLMBoard score78.85 | Input -> outputtext -> embedding | Context512 | Parameters494M | CapabilitiesN/A | Released |
| ModelGO | LLMBoard score78.18 | Input -> outputtext -> embedding | Context2K | ParametersN/A | CapabilitiesN/A | Released |
| ModelGO | LLMBoard score78.16 | Input -> outputtext -> embedding | Context2K | ParametersN/A | CapabilitiesN/A | Released |
| ModelANgte-Qwen2-7B-instructAlibaba Nlp | LLMBoard score78.06 | Input -> outputtext -> embedding | Context32.8K | Parameters7.1B | CapabilitiesN/A | Released |
This leaderboard uses evaluation and benchmark evidence only for scores. Price, context and model specifications remain separate from the ranking.
Compare input and output support alongside the leaderboard; modality support does not change the benchmark ranking.
363 models currently have a domain-specific LLMBoard score. The leaderboard ranking uses matched benchmark evidence, while coverage and provisional status identify incomplete evidence.
No positive native-unit price is currently available.
QZhou-Embedding leads the available LLMBoard scores at 90.18.
105 of 365 catalog models have more than one listed input modality.
365 catalog models currently have no positive native-unit price listing.
Prices retain the unit returned by the catalog, such as per image, per second, per minute or per million characters. They are never shown as token prices.
Some models do not have a current price listing in their native billing unit.