| Performance | Quality | |||||
|---|---|---|---|---|---|---|
| Model | Params | Throughput | Latency | NDCG@10 | F1 | AP |
| Alibaba-NLP/gte-Qwen2-7B-instruct Encode · Dense · Qwen2 | 7.6B | 3.5K tok/s | 845.9ms | — | — | — |
| GritLM/GritLM-7B Encode · Dense · Mistral | 7.2B | 1.4K tok/s | 2.1s | — | — | — |
| Linq-AI-Research/Linq-Embed-Mistral Encode · Dense · Mistral | 7.1B | 2.9K tok/s | 817.9ms | — | — | — |
| Salesforce/SFR-Embedding-2_R Encode · Dense · Mistral | 7.1B | 2.9K tok/s | 682.5ms | — | — | — |
| Salesforce/SFR-Embedding-Mistral Encode · Dense · Mistral | 7.1B | 3.0K tok/s | 887.5ms | — | — | — |
| intfloat/e5-mistral-7b-instruct Encode · Dense · Mistral | 7.1B | 3.0K tok/s | 915.3ms | — | — | — |
| vidore/colqwen2.5-v0.2 Encode · Multi-Vec · Qwen2 | 7.0B | 7.6 mpix/s | 1.9s | — | — | — |
| nvidia/llama-nemoretriever-colembed-3b-v1 Encode · Multi-Vec · llama_nemoretrievercolembed | 4.4B | 0.7 img/s | 6.2s | — | — | — |
| Qwen/Qwen3-Reranker-4B Score · Score · Qwen3 | 4.0B | — | — | — | — | — |
| Qwen/Qwen3-Embedding-4B Encode · Dense · Qwen3 | 4.0B | 5.7K tok/s | 464.5ms | — | — | — |
| vidore/colpali-v1.3-hf Encode · Multi-Vec · PaliGemma | 3.0B | 23.0 mpix/s | 581.7ms | — | — | — |
| Qwen/Qwen3-VL-Embedding-2B Encode · Dense · qwen3_vl | 2.1B | 494 tok/s | 35.9ms | — | — | — |
| Qwen/Qwen3-VL-Reranker-2B Score · Score · qwen3_vl | 2.1B | — | — | — | — | — |
| Alibaba-NLP/gte-Qwen2-1.5B-instruct Encode · Dense · Qwen2 | 1.8B | 12.3K tok/s | 261.1ms | — | — | — |
| mixedbread-ai/mxbai-rerank-large-v2 Score · Score · Qwen2 | 1.5B | 2.3K tok/s | 1.1s | — | — | — |
| NovaSearch/stella_en_1.5B_v5 Encode · Dense · Qwen2 | 1.5B | 12.8K tok/s | 265.9ms | — | — | — |
| zai-org/GLM-OCR Extract · Text (Markdown) · GLM-OCR | 1.3B | — | — | — | — | — |
| lightonai/LightOnOCR-2-1B Extract · Text (Markdown) · LightOnOCR | 1.0B | — | — | — | — | — |
| laion/CLIP-ViT-H-14-laion2B-s32B-b79K Encode · Dense · CLIP | 986M | 380 tok/s | 461.1ms | — | — | — |
| PaddlePaddle/PaddleOCR-VL-1.5 Extract · Text (Markdown) · PaddleOCR-VL | 959M | — | — | — | — | — |
| google/siglip-so400m-patch14-384 Encode · Dense · SigLIP | 878M | 399 tok/s | 452.5ms | — | — | — |
| google/siglip-so400m-patch14-224 Encode · Dense · SigLIP | 877M | 400 tok/s | 394.1ms | — | — | — |
| Qwen/Qwen3-Embedding-0.6B Encode · Dense · Qwen3 | 596M | 20.6K tok/s | 156.9ms | — | — | — |
| Qwen/Qwen3-Reranker-0.6B Score · Score · Qwen3 | 596M | — | — | — | — | — |
| BAAI/bge-m3 Encode · Dense /Sparse /Multi-Vec · XLM-RoBERTa | 568M | 33.2K tok/s | 93.4ms | — | — | — |
| BAAI/bge-m3 Score · Dense /Sparse /Multi-Vec · XLM-RoBERTa | 568M | 2.8K tok/s | 56.8ms | — | — | — |
| BAAI/bge-reranker-v2-m3 Score · Score · XLM-RoBERTa | 568M | 30.0K tok/s | 93.5ms | — | — | — |
| BAAI/bge-reranker-large Score · Score · XLM-RoBERTa | 560M | 6.6K tok/s | 41.4ms | — | — | — |
| intfloat/multilingual-e5-large Encode · Dense · XLM-RoBERTa | 560M | 29.8K tok/s | 108.6ms | — | — | — |
| intfloat/multilingual-e5-large-instruct Encode · Dense · XLM-RoBERTa | 560M | 29.4K tok/s | 106.9ms | — | — | — |
| jinaai/jina-colbert-v2 Encode · Multi-Vec · XLM-RoBERTa | 559M | 28.5K tok/s | 105.7ms | — | — | — |
| jinaai/jina-colbert-v2 Score · Multi-Vec · XLM-RoBERTa | 559M | 1.4K tok/s | 226.1ms | — | — | — |
| mixedbread-ai/mxbai-rerank-base-v2 Score · Score · Qwen2 | 494M | 6.0K tok/s | 454.0ms | — | — | — |
| nomic-ai/nomic-embed-text-v2-moe Encode · Dense · NomicBERT | 475M | 13.0K tok/s | 149.6ms | — | — | — |
| numind/NuNER_Zero Extract · Entities · DeBERTa | 449M | — | — | — | — | — |
| NovaSearch/stella_en_400M_v5 Encode · Dense · ModernBERT | 435M | 27.1K tok/s | 115.7ms | — | — | — |
| EmergentMethods/gliner_large_news-v2.1 Extract · Entities · DeBERTa | 435M | — | — | — | — | — |
| Ihor/gliner-biomed-large-v1.0 Extract · Entities · DeBERTa | 435M | — | — | — | — | — |
| jackboyla/glirel-large-v0 Extract · Relations · DeBERTa | 435M | — | — | — | — | — |
| urchade/gliner_large-v2.1 Extract · Entities · DeBERTa | 435M | — | — | — | — | — |
| urchade/gliner_multi_pii-v1 Extract · Entities · DeBERTa | 435M | — | — | — | — | — |
| openai/clip-vit-large-patch14 Encode · Dense · CLIP | 428M | 977 tok/s | 228.0ms | — | — | — |
| google/siglip2-base-patch16-224 Encode · Dense · SigLIP | 375M | 1.6K tok/s | 68.5ms | — | — | — |
| mixedbread-ai/mxbai-colbert-large-v1 Encode · Multi-Vec · BERT | 335M | 43.3K tok/s | 74.9ms | — | — | — |
| mixedbread-ai/mxbai-colbert-large-v1 Score · Multi-Vec · BERT | 335M | 4.0K tok/s | 45.6ms | — | — | — |
| intfloat/e5-large-v2 Encode · Dense · BERT | 335M | 33.2K tok/s | 86.6ms | — | — | — |
| Alibaba-NLP/gte-multilingual-base Encode · Dense · ModernBERT | 305M | 55.1K tok/s | 63.1ms | — | — | — |
| Snowflake/snowflake-arctic-embed-m-v2.0 Encode · Dense · gte | 305M | — | — | — | — | — |
| google/embeddinggemma-300m Encode · Dense · Gemma 3 | 303M | 79.6K tok/s | 55.7ms | — | — | — |
| urchade/gliner_multi-v2.1 Extract · Entities · DeBERTa | 289M | — | — | — | — | — |
| jinaai/jina-reranker-v2-base-multilingual Score · Score · XLM-RoBERTa | 278M | 8.3K tok/s | 32.0ms | — | — | — |
| BAAI/bge-reranker-base Score · Score · XLM-RoBERTa | 278M | 5.0K tok/s | 33.2ms | — | — | — |
| mynkchaudhry/Florence-2-FT-DocVQA Extract · text_regions · Florence-2 | 271M | — | — | — | — | — |
| IDEA-Research/grounding-dino-base Extract · Bounding Boxes · Swin | 233M | 0.8 mpix/s | 785.8ms | — | — | — |
| microsoft/Florence-2-base Extract · text_regions · Florence-2 | 232M | — | — | — | — | — |
| fastino/gliner2-base-v1 Extract · Entities · extractor | 208M | — | — | — | — | — |
| urchade/gliner_medium-v2.1 Extract · Entities · DeBERTa | 195M | — | — | — | — | — |
| IDEA-Research/grounding-dino-tiny Extract · Bounding Boxes · Swin | 172M | 0.9 mpix/s | 532.6ms | — | — | — |
| google/owlv2-base-patch16-ensemble Extract · Bounding Boxes · CLIP | 155M | 1.0 mpix/s | 954.6ms | — | — | — |
| laion/CLIP-ViT-B-32-laion2B-s34B-b79K Encode · Dense · CLIP | 151M | 1.0K tok/s | 219.4ms | — | — | — |
| openai/clip-vit-base-patch32 Encode · Dense · CLIP | 151M | 958 tok/s | 234.0ms | — | — | — |
| Alibaba-NLP/gte-reranker-modernbert-base Score · Score · ModernBERT | 150M | 6.2K tok/s | 41.9ms | — | — | — |
| lightonai/GTE-ModernColBERT-v1 Encode · Multi-Vec · ModernBERT | 149M | 28.0K tok/s | 103.9ms | — | — | — |
| lightonai/GTE-ModernColBERT-v1 Score · Multi-Vec · ModernBERT | 149M | 231 tok/s | 313.4ms | — | — | — |
| lightonai/Reason-ModernColBERT Encode · Multi-Vec · ModernBERT | 149M | 33.0K tok/s | 82.2ms | — | — | — |
| lightonai/Reason-ModernColBERT Score · Multi-Vec · ModernBERT | 149M | — | — | — | — | — |
| Alibaba-NLP/gte-modernbert-base Encode · Dense · ModernBERT | 149M | — | — | — | — | — |
| ibm-granite/granite-embedding-english-r2 Encode · Dense · ModernBERT | 149M | — | — | — | — | — |
| opensearch-project/opensearch-neural-sparse-encoding-doc-v3-gte Encode · Sparse · ModernBERT | 137M | 34.2K tok/s | 93.7ms | — | — | — |
| opensearch-project/opensearch-neural-sparse-encoding-v1 Encode · Sparse · BERT | 133M | 48.7K tok/s | 69.0ms | — | — | — |
| naver-clova-ix/donut-base-finetuned-cord-v2 Extract · text_regions · Encoder-Decoder | 110M | — | — | — | — | — |
| naver-clova-ix/donut-base-finetuned-docvqa Extract · text_regions · Encoder-Decoder | 110M | — | — | — | — | — |
| naver/splade-cocondenser-selfdistil Encode · Sparse · BERT | 110M | 40.0K tok/s | 72.4ms | — | — | — |
| naver/splade-v3 Encode · Sparse · BERT | 110M | 29.6K tok/s | 83.7ms | — | — | — |
| numind/NuNER_Zero-span Extract · Entities · DeBERTa | 110M | — | — | — | — | — |
| prithivida/Splade_PP_en_v2 Encode · Sparse · BERT | 110M | 57.5K tok/s | 55.4ms | — | — | — |
| colbert-ir/colbertv2.0 Encode · Multi-Vec · BERT | 110M | 43.0K tok/s | 65.7ms | — | — | — |
| colbert-ir/colbertv2.0 Score · Multi-Vec · BERT | 110M | 3.8K tok/s | 51.4ms | — | — | — |
| intfloat/e5-base-v2 Encode · Dense · BERT | 109M | 53.2K tok/s | 57.9ms | — | — | — |
| Extract · Parsed Document · Docling | 80M | — | — | — | — | — |
| opensearch-project/opensearch-neural-sparse-encoding-doc-v2-distill Encode · Sparse · DistilBERT | 67M | 49.1K tok/s | 63.3ms | — | — | — |
| opensearch-project/opensearch-neural-sparse-encoding-doc-v3-distill Encode · Sparse · DistilBERT | 67M | 50.1K tok/s | 60.7ms | — | — | — |
| opensearch-project/opensearch-neural-sparse-encoding-v2-distill Encode · Sparse · DistilBERT | 67M | 44.2K tok/s | 63.3ms | — | — | — |
| urchade/gliner_small-v2.1 Extract · Entities · DeBERTa | 60M | — | — | — | — | — |
| ibm-granite/granite-embedding-small-english-r2 Encode · Dense · ModernBERT | 48M | — | — | — | — | — |
| answerdotai/answerai-colbert-small-v1 Encode · Multi-Vec · BERT | 33M | 59.1K tok/s | 47.9ms | — | — | — |
| answerdotai/answerai-colbert-small-v1 Score · Multi-Vec · BERT | 33M | 1.7K tok/s | 121.7ms | — | — | — |
| cross-encoder/ms-marco-MiniLM-L-12-v2 Score · Score · BERT | 33M | 8.2K tok/s | 31.7ms | — | — | — |
| intfloat/e5-small-v2 Encode · Dense · BERT | 33M | 58.3K tok/s | 49.7ms | — | — | — |
| mixedbread-ai/mxbai-edge-colbert-v0-32m Encode · Multi-Vec · ModernBERT | 32M | 45.9K tok/s | 59.7ms | — | — | — |
| mixedbread-ai/mxbai-edge-colbert-v0-32m Score · Multi-Vec · ModernBERT | 32M | — | — | — | — | — |
| ibm-granite/granite-embedding-30m-sparse Encode · Sparse · RoBERTa | 30M | 31.9K tok/s | 105.2ms | — | — | — |
| opensearch-project/opensearch-neural-sparse-encoding-doc-v2-mini Encode · Sparse · BERT | 23M | 51.1K tok/s | 54.5ms | — | — | — |
| cross-encoder/ms-marco-MiniLM-L-6-v2 Score · Score · BERT | 23M | 52.4K tok/s | 45.1ms | — | — | — |
| sentence-transformers/all-MiniLM-L6-v2 Encode · Dense · BERT | 23M | 55.3K tok/s | 53.3ms | — | — | — |
| rasyosef/splade-mini Encode · Sparse · BERT | 11M | 56.3K tok/s | 56.0ms | — | — | — |
| knowledgator/gliner-bi-base-v2.0 Extract · Entities · | null | — | — | — | — | — |
| knowledgator/modern-gliner-bi-base-v1.0 Extract · Entities · | null | — | — | — | — | — |
