Codesota · Models1,870 models indexed · 790 match filter
Editorial · Models
Every model, measured.
Start with a research area, drill into a vendor, or page through the full index. Only models with at least one benchmark score appear — a model without a recorded score can’t be ranked.
Vendor:Areas overviewUnknown · 509speakleash · 253OpenAI · 75Google · 67Research · 52Qwen · 47Alibaba · 43Anthropic · 40Microsoft · 34Mistral · 30Meta · 29DeepSeek · 25google · 19meta-llama · 19mistralai · 19Meta AI · 15Academic · 14CYFRAGOVPL · 14Zhipu AI · 12SpeakLeash · 10internlm · 10xAI · 10ByteDance · 9Baidu · 8PLLuM · 8ibm-granite · 8microsoft · 8 · 7Alibaba Cloud · 7Google DeepMind · 7Remek · 7allenai · 7utter-project · 7CohereForAI · 6Microsoft Research · 6MiniMax · 6NVIDIA · 6Salesforce · 6Shanghai AI Lab · 601-ai · 5Amazon · 5Mistral AI · 5Moonshot AI · 5NousResearch · 5THUML · 5deepseek-ai · 5Cohere · 4DeepMind · 4Facebook AI · 4Meituan · 4Stanford · 4THUDM · 4UC San Diego · 4VikParuchuri · 4gguf-iq · 4nvidia · 4openchat · 4tiiuae · 4Allen AI · 3BAAI · 3Du et al. · 3Fudan University · 3IDEA Research · 3Liao et al. · 3Moonshot.AI · 3Nam Tuan Ly / NII · 3OPI-PG · 3OpenDataLab · 3ViCoS Lab Ljubljana · 3Xiaomi · 3Zhao et al. · 3gguf · 3gguf11bv30 · 3gguf7bv30 · 3upstage · 3347yth03847tyhy03847yt · 2AAAI 2024 · 2Castorini (Waterloo) · 2Fang et al. · 2German Cancer Research Center (DKFZ) · 2Google / UNC · 2HIT & iFLYTEK · 2HuggingFaceH4 · 2IBM Research · 2Independent · 2Jina AI · 2Liao et al. (USTC) · 2LlamaIndex · 2Meta AI / FAIR · 2MiniMaxAI · 2MonkeyOCR · 2NVIDIA (MONAI) · 2Nanjing University · 2Nanonets · 2Nexusflow · 2Nondzu · 2OpenGVLab · 2RedNote HILab · 2Sarvam AI · 2Simular AI · 2Su et al. · 2TeeZee · 2Ultralytics · 2University of Leicester · 2Voicelab · 2Wan et al. (Baidu) · 2Zhang et al. · 2Zheng et al. · 2Ziyan Huang et al. · 2alpindale · 2cjvt · 2h2oai · 2meditsolutions · 2openGPT-X · 2teknium · 2AAAI 2020 · 1AAAI 2023 · 1Adobe Research · 1Alibaba Qwen · 1Alibaba iDST · 1Alibaba/Qwen · 1Amazon Web Services · 1Anonymous (ECCV 2024) · 1Anonymous (arXiv 2023) · 1Anonymous (arXiv 2025) · 1Anonymous / ACL community · 1Anonymous / arxiv preprint · 1Anysphere · 1Apple · 1AssemblyAI · 1Audio Research · 1BAAI (Beijing Academy of AI) · 1BAAI / PKU · 1BRIDO Authors · 1Baidu PaddlePaddle · 1Baidu Qianfan · 1BigCode · 1BigCode / Salesforce · 1Biology · 1CASIA / UCAS · 1CLIP-based · 1CMU · 1CUHK / HIT · 1CVPR 2019 · 1CVPR 2020 · 1CVPR 2021 · 1CW · 1Case Western Reserve University · 1ChatDoc · 1Chen et al. · 1Chen et al. (JHU) · 1Chen, Zhang et al. · 1Cheng et al. · 1Cognition · 1Cohen Lab · 1CohereLabs · 1Columbia University · 1Community · 1Coqui AI · 1DAIR-Group · 1DCASE · 1DFKI / TU Kaiserslautern · 1DMLC · 1DeepL SE · 1DeepMind / TU Warsaw · 1ETH Zurich · 1East China Normal University · 1Edresson Casanova et al. · 1Emergence AI · 1Extend · 1FAIR & UW · 1FSOFT AI Lab · 1Fudan University / Alibaba · 1Fujitake · 1Georgia Tech (Peng et al.) · 1Ghent University · 1Google (Open Source) · 1Google AI · 1Google Brain · 1Google Cloud · 1Google Research · 1Google/CMU · 1Hanvon_WuHan · 1Harvard/MIT · 1Hikvision Research Institute · 1Huawei · 1HuggingFaceTB · 1ICCV 2019 · 1ICT, Chinese Academy of Sciences · 1IDEA-Research · 1IFLYTEK / USTC (Zhang et al.) · 1IIT Bombay LEAP-OCR · 1IJCAI 2025 · 1JD Explore Academy · 1JaidedAI · 1Jiahao Lyu et al., Fudan University · 1Jiang et al. · 1KAIST · 1KAIST / NAVER · 1Kakao · 1Kim et al. · 1Knowledgator · 1LGAI-EXAONE · 1LandingAI · 1Layer 6 AI · 1LightOn · 1Longhuang Wu et al. · 1MBZUAI · 1Meta AI / UIUC · 1Meta AI / WSU · 1Microsoft STCA AIC · 1Mila · 1Mila / Intel · 1Mila / Valence · 1Momenta · 1MultiOn · 1NEC / UIUC · 1NUS · 1NVIDIA / NeMo · 1NVIDIA / Suno · 1NYU · 1NYU / Google · 1Nixtla · 1Oxford / Twitter · 1PAII Insight Team · 1PJLab & Tsinghua · 1Ping An Life Insurance · 1PriorLabs (University of Freiburg) · 1RedNote · 1Reducto · 1Research (IDEA Research) · 1SFU · 1SJTU · 1SUTD · 1Saifullah et al. · 1Scylla Technologies · 1SenseTime · 1Sensetime / Sense-X · 1Sentence-Transformers · 1ServiceNow · 1ServiceNow-AI · 1Sogou OCR team · 1SonarSource · 1Stanford ML Group · 1Stanford NLP · 1StepFun · 1Studio Ousia · 1SumHiS Authors · 1TPAMI 2021 · 1TPAMI 2022 · 1Takaya Kawakatsu · 1TeamQuest · 1TildeAI · 1Timm · 1Tongji University / Ant Group · 1TriSum Authors · 1Tsinghua · 1Tsinghua / MEGVII · 1Tsinghua / MILA · 1Tsinghua University · 1Tsinghua University / Baidu · 1U. Toronto · 1UBTECH · 1UC Berkeley · 1UC Davis · 1UCLA / Columbia · 1UCLA / Columbia University · 1USTC / Microsoft Research Asia · 1UTTER · 1UW-Madison / Microsoft · 1Uber AI · 1Uber Technologies · 1University Medical Center Hamburg-Eppendorf et al. · 1Unknown (ICDAR 2021 participant) · 1Upstage AI · 1Verified XiaoPAI · 1ViTAE-Transformer · 1Voyage AI · 1Wang et al. (University of Toronto) · 1Weizmann Institute · 1Xing et al. · 1Xingwen Cao et al. (LIESMARS, Wuhan University) · 1Yale NLP · 1Yan et al. · 1Yongkun Du et al. · 1Zhang et al. (HCIILAB) · 1Zhong and Gao · 1Zhou et al. · 1Zhu et al. · 1berkeley-nest · 1community · 1datalab-to · 1deepcogito · 1djstrong · 1dnhkng · 1dreamgen · 1jxm · 1lex-hue · 1lmsys · 1mlabonne · 1moonshotai · 1openai · 1piotr-ai · 1scikit-learn · 1swiss-ai · 1szymonrucinski · 1
§ 01 · Natural Language Processing models
790 models in Natural Language Processing · page 1 of 16.
| # | Model | Vendor | Parameters | Architecture | SOTA | Benchmarks | Results |
|---|---|---|---|---|---|---|---|
| 001 | GPT-4o | OpenAI | Undisclosed | Multimodal LLM | 16 | 46 | 57 |
| 002 | Gemini-3.1-Pro-Preview | — | — | 7 | 1 | 7 | |
| 003 | gemma-3-27b-it | — | — | 6 | 1 | 9 | |
| 004 | DeBERTa-v3-large | Microsoft | 304M | DeBERTa-v3-large | 4 | 5 | 6 |
| 005 | Claude Sonnet 4 | Anthropic | — | Multimodal LLM | 3 | 14 | 20 |
| 006 | Gemini 1.5 Pro | — | Multimodal LLM | 3 | 16 | 20 | |
| 007 | GPT-4 | OpenAI | — | Transformer (LLM) | 3 | 6 | 13 |
| 008 | BRIO | Yale NLP | Unknown | BART-large with contrastive learning objective | 3 | 2 | 6 |
| 009 | Claude 3.5 Sonnet | Anthropic | Undisclosed | Multimodal LLM | 2 | 27 | 32 |
| 010 | Claude Opus 4 | Anthropic | Undisclosed | — | 2 | 15 | 22 |
| 011 | Phi-4 | Microsoft | 14B | transformer | 2 | 3 | 17 |
| 012 | Mistral-Small-3.1-24B-Instruct-2503 | Mistral | — | — | 2 | 1 | 9 |
| 013 | gemma-3-12b-it | — | — | 2 | 1 | 9 | |
| 014 | Gemini-3.0-Pro-Preview | — | — | 2 | 1 | 7 | |
| 015 | gemini-2.0-flash-001 | — | — | 2 | 1 | 5 | |
| 016 | NV-Embed-v2 | NVIDIA | 7B | Mistral-7B (LLM-based embedding) | 2 | 2 | 2 |
| 017 | Mistral-Large-Instruct-2407 | mistralai | 123B | — | 1 | 3 | 14 |
| 018 | Mistral-Large-Instruct-2411 | mistralai | 123B | — | 1 | 3 | 14 |
| 019 | Qwen2.5-14B-Instruct | Qwen | 14.8B | — | 1 | 3 | 14 |
| 020 | Qwen2.5-72B-Instruct | Qwen | 72.7B | — | 1 | 3 | 14 |
| 021 | Llama-4-Scout-17B-16E-Instruct | meta-llama | 109B | — | 1 | 2 | 13 |
| 022 | Gemma-2-27b-it | — | — | 1 | 1 | 9 | |
| 023 | Meta-Llama-3.1-405B-Instruct-FP8 | meta-llama | — | — | 1 | 2 | 9 |
| 024 | Mistral-Large-Instruct-2407 | Mistral | — | — | 1 | 1 | 9 |
| 025 | Mistral-Small-24B-Instruct-2501 | Mistral | — | — | 1 | 1 | 9 |
| 026 | Mistral-Small-Instruct-2409 | Mistral | — | — | 1 | 1 | 9 |
| 027 | Qwen2.5-32B-Instruct | Alibaba | — | — | 1 | 1 | 9 |
| 028 | aya-expanse-32b | Unknown | — | — | 1 | 1 | 9 |
| 029 | Bielik-11B-v3.0-Instruct.Q4_K_M.gguf | gguf11bv30 | — | — | 1 | 1 | 8 |
| 030 | Qwen2.5-32B | Qwen | — | — | 1 | 1 | 8 |
| 031 | b11t2 | 347yth03847tyhy03847yt | — | — | 1 | 1 | 8 |
| 032 | Qwen/Qwen3.5-27B thinking (API) | Qwen | 27B | — | 1 | 1 | 5 |
| 033 | Qwen/Qwen3.5-35B-A3B thinking (API) | Qwen | 35B | — | 1 | 1 | 5 |
| 034 | deepseek-ai/DeepSeek-V3.2 (API) | deepseek-ai | 685B | — | 1 | 1 | 5 |
| 035 | GTE-Qwen2-7B-instruct | Alibaba | 7B | Qwen2-7B (LLM-based embedding) | 1 | 3 | 3 |
| 036 | GLiNER-multitask | Knowledgator | Unknown | DeBERTa-based generalist IE model | 1 | 1 | 1 |
| 037 | RankLLaMA-7B | Castorini (Waterloo) | 7B | LLaMA-2-7B (pointwise reranker) | 1 | 1 | 1 |
| 038 | Vega v2 (6B) | JD Explore Academy | — | — | 1 | 1 | 1 |
| 039 | DeepSeek R1 | DeepSeek | 671B MoE | — | 13 | 19 | |
| 040 | GPT-3.5-turbo | OpenAI | — | — | 3 | 17 | |
| 041 | Mixtral-8x22b | Mistral | — | — | 3 | 17 | |
| 042 | Grok 4 | xAI | — | — | 7 | 16 | |
| 043 | Llama-PLLuM-70B-chat | PLLuM | — | — | 2 | 16 | |
| 044 | Llama-PLLuM-8B-chat | PLLuM | — | — | 2 | 16 | |
| 045 | Mixtral-8x7b | Mistral | — | — | 2 | 16 | |
| 046 | PLLuM-12B-chat | PLLuM | — | — | 2 | 16 | |
| 047 | PLLuM-12B-nc-chat | PLLuM | — | — | 2 | 16 | |
| 048 | PLLuM-8x7B-chat | PLLuM | — | — | 2 | 16 | |
| 049 | PLLuM-8x7B-nc-chat | PLLuM | — | — | 2 | 16 | |
| 050 | DeepSeek-V3 | DeepSeek | — | LLM | 9 | 15 |