Codesota · Models2,268 models indexed · 854 match filter
Editorial · Models
Models with recorded evidence.
Start with a research area, drill into a vendor, or page through the full index. Vendor aliases and legacy area IDs are grouped here; original model IDs and model links stay unchanged. Only models with at least one benchmark score appear — a model without a recorded score can’t be ranked.
Vendor:Areas overviewSpeakLeash · 263Alibaba · 104Google · 102OpenAI · 86Meta · 68Microsoft · 49Anthropic · 44DeepSeek · 34Mistral · 30mistralai · 19CYFRAGOVPL · 14NVIDIA · 14Zhipu AI · 13internlm · 10xAI · 10ByteDance · 9Baidu · 8ibm-granite · 8PLLuM · 8allenai · 7Amazon · 7MiniMax · 7Mistral AI · 7Remek · 7Shanghai AI Lab · 7utter-project · 7CohereForAI · 6Salesforce · 601-ai · 5Cohere · 5Moonshot AI · 5NousResearch · 5THUML · 5gguf-iq · 4IBM · 4Meituan · 4openchat · 4Stanford · 4THUDM · 4tiiuae · 4UC San Diego · 4VikParuchuri · 4Allen AI · 3BAAI · 3Du et al. · 3ForgeCode · 3Fudan University · 3gguf · 3gguf11bv30 · 3gguf7bv30 · 3IDEA Research · 3Liao et al. · 3Moonshot.AI · 3Nam Tuan Ly / NII · 3OpenDataLab · 3OPI-PG · 3upstage · 3ViCoS Lab Ljubljana · 3Xiaomi · 3Zhao et al. · 3+ 243 smaller vendors (288 models)
§ 01 · Natural Language Processing models
854 models in Natural Language Processing · page 16 of 18.
| # | Model | Vendor | Parameters | Architecture | Benchmarks | Results |
|---|---|---|---|---|---|---|
| 751 | OLMo-2-7B-1124 (olmOCR-peS2o) | — | — | — | 5 | 5 |
| 752 | openai/gpt-oss-120b (API) | OpenAI | 120B | — | 1 | 5 |
| 753 | Qwen/Qwen2.5-0.5B-Instruct | Alibaba | 0.49B | — | 1 | 5 |
| 754 | Qwen/Qwen3-14B non-thinking (API) | Alibaba | 14B | — | 1 | 5 |
| 755 | Qwen/Qwen3-235B-A22B non-thinking (API) | Alibaba | 235B | — | 1 | 5 |
| 756 | Qwen/Qwen3-30B-A3B non-thinking (API) | Alibaba | 30B | — | 1 | 5 |
| 757 | Qwen/Qwen3-32B non-thinking (API) | Alibaba | 32B | — | 1 | 5 |
| 758 | Qwen/Qwen3.5-27B non-thinking (API) | Alibaba | 27B | — | 1 | 5 |
| 759 | Qwen/Qwen3.5-27B thinking (API) | Alibaba | 27B | — | 1 | 5 |
| 760 | Qwen/Qwen3.5-35B-A3B non-thinking (API) | Alibaba | 35B | — | 1 | 5 |
| 761 | Qwen/Qwen3.5-35B-A3B thinking (API) | Alibaba | 35B | — | 1 | 5 |
| 762 | Qwen/Qwen3.5-9B non-thinking (API, FP8) | Alibaba | 9B | — | 1 | 5 |
| 763 | Qwen/Qwen3-8B non-thinking (API) | Alibaba | 8B | — | 1 | 5 |
| 764 | speakleash/Bielik-Minitron-7B-v3.0-Instruct | SpeakLeash | 7.35B | — | 1 | 5 |
| 765 | E5-Mistral-7B-instruct | Microsoft | 7B | Mistral-7B (LLM-based embedding) | 3 | 4 |
| 766 | GTE-Qwen2-7B-instruct | Alibaba | 7B | Qwen2-7B (LLM-based embedding) | 3 | 4 |
| 767 | Helium | — | — | — | 4 | 4 |
| 768 | T5-11B | Unknown | Unknown | 2 | 4 | |
| 769 | Trinity Large Preview | Arcee AI | — | — | 4 | 4 |
| 770 | Claude 3.5 Sonnet | Anthropic | — | Transformer (LLM) | 3 | 3 |
| 771 | Gemini Ultra | Unknown | Transformer (decoder-only) | 3 | 3 | |
| 772 | GLM-5.1 | — | — | — | 3 | 3 |
| 773 | NV-Embed-v2 | NVIDIA | 7B | Mistral-7B (LLM-based embedding) | 2 | 3 |
| 774 | PEGASUS-Large | Unknown | Transformer encoder-decoder (gap-sentence generation pre-training) | 1 | 3 | |
| 775 | ALBERT ensemble | — | — | — | 2 | 2 |
| 776 | BART | — | — | — | 2 | 2 |
| 777 | ByT5 XXL | — | — | — | 2 | 2 |
| 778 | ColBERTv2 | Stanford | 110M | BERT (late interaction) | 2 | 2 |
| 779 | HunyuanOCR (1B) | Unknown | — | — | 2 | 2 |
| 780 | Mistral 7B | Mistral AI | Unknown | Transformer (decoder-only, GQA + sliding window attention) | 2 | 2 |
| 781 | ST-MoE-32B | Google Brain | Unknown | Sparse Mixture-of-Experts Transformer | 2 | 2 |
| 782 | ALBERT-xxlarge-v2 | 235M | ALBERT-xxlarge | 1 | 1 | |
| 783 | all-MiniLM-L6-v2 | Sentence-Transformers | 22M | MiniLM-L6 (BERT-like) | 1 | 1 |
| 784 | BERT + AoA | HIT & iFLYTEK | — | — | 1 | 1 |
| 785 | BERT + ConvLSTM + MTL + Verifier (ensemble) | Layer 6 AI | — | — | 1 | 1 |
| 786 | BERT + DAE + AoA (single model) | HIT & iFLYTEK | — | — | 1 | 1 |
| 787 | BERT (Google AI) | Google AI | — | — | 1 | 1 |
| 788 | BERT Large | — | — | — | 1 | 1 |
| 789 | DeBERTa (ensemble) | Microsoft | — | — | 1 | 1 |
| 790 | DeepL | DeepL SE | — | Transformer (NMT) | 1 | 1 |
| 791 | embeddinggemma-300m | — | — | — | 1 | 1 |
| 792 | Enhanced Albert+Verifier3 (ensemble) | Microsoft STCA AIC | — | — | 1 | 1 |
| 793 | ERNIE 3.0 | Baidu | — | — | 1 | 1 |
| 794 | F2LLM-0.6B | — | — | — | 1 | 1 |
| 795 | F2LLM-1.7B | — | — | — | 1 | 1 |
| 796 | F2LLM-4B | — | — | — | 1 | 1 |
| 797 | F2LLM-v2-0.6B | — | — | — | 1 | 1 |
| 798 | F2LLM-v2-14B | — | — | — | 1 | 1 |
| 799 | F2LLM-v2-1.7B | — | — | — | 1 | 1 |
| 800 | F2LLM-v2-330M | — | — | — | 1 | 1 |