Codesota · Models2,268 models indexed · 896 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 · Computer Vision models
896 models in Computer Vision · page 9 of 18.
| # | Model | Vendor | Parameters | Architecture | Benchmarks | Results |
|---|---|---|---|---|---|---|
| 401 | HEADoC-Base | — | 27.7M | Transformer | 2 | 2 |
| 402 | HEADoC-Large | — | 90.58M | Transformer | 2 | 2 |
| 403 | HTR-JAND | Unknown | 1.5M | CNN (FullGatedConv2d + SE blocks) + Combined Attention + Knowledge Distillation | 1 | 2 |
| 404 | HunyuanOCR (1B) | Unknown | — | — | 2 | 2 |
| 405 | I2L-STRIPS | Unknown | Unknown | Unknown | 2 | 2 |
| 406 | IAST | Academic | — | Reading-Order Estimation + Dynamic Sampling | 1 | 2 |
| 407 | Infinity-Parser 7B | Unknown | 7B | Vision-Language Model | 1 | 2 |
| 408 | InternViT-6B (InternVL) | OpenGVLab | 6B | InternViT vision encoder (InternVL family) | 2 | 2 |
| 409 | JSTR | Fujitake | Unknown | DTrOCR + judgment module for image-text matching to reduce misrecognition | 2 | 2 |
| 410 | KOSMOS-2.5 | Microsoft | — | — | 1 | 2 |
| 411 | LBDM | Unknown | Unknown | Unknown | 1 | 2 |
| 412 | LGPMA | Unknown | Unknown | Unknown | 1 | 2 |
| 413 | LRANet++ | Academic | — | Low-Rank Approximation Network | 1 | 2 |
| 414 | LSGSpotter | Academic | — | Arbitrary Reading Order, Local Semantics Guidance | 1 | 2 |
| 415 | LSTM-reg (single model) | Unknown | Unknown | Unknown | 2 | 2 |
| 416 | LeJEPA ViT-L (304M) | — | — | — | 2 | 2 |
| 417 | Leaky LP Cell | Unknown | Unknown | Unknown | 1 | 2 |
| 418 | MAGNET | Unknown | Unknown | Unknown | 2 | 2 |
| 419 | MBD | Unknown | Unknown | Unknown | 1 | 2 |
| 420 | MPAD-path | Unknown | Unknown | Unknown | 2 | 2 |
| 421 | Marker 1.10.0 | VikParuchuri | — | PDF Parser | 1 | 2 |
| 422 | MaskTextSpotter v2 | Unknown | Unknown | Unknown | 1 | 2 |
| 423 | MetaWriter | Unknown | Unknown | Meta-learned prompt tuning on HTR backbone (CVPR 2025) | 1 | 2 |
| 424 | MinerU2.5 | — | — | — | 2 | 2 |
| 425 | MonkeyOCR-3B | MonkeyOCR | — | — | 1 | 2 |
| 426 | Multi-Task Learning Model | Unknown | Unknown | Unknown | 1 | 2 |
| 427 | NCP+BTA | — | — | — | 1 | 2 |
| 428 | NRTR+TPS++ | Unknown | Unknown | Unknown | 2 | 2 |
| 429 | OmniParser | Alibaba | — | Unified framework: text spotting, KIE, table recognition | 1 | 2 |
| 430 | OrigamiNet-18 | Unknown | Unknown | Unknown | 1 | 2 |
| 431 | OrigamiNet-24 | Unknown | Unknown | Unknown | 1 | 2 |
| 432 | PASTA | Unknown | Unknown | Unknown | 1 | 2 |
| 433 | PyLaia (all transcriptions + agreement-based split) | Unknown | Unknown | Unknown | 1 | 2 |
| 434 | PyLaia (human transcriptions + agreement-based split) | Unknown | Unknown | Unknown | 1 | 2 |
| 435 | PyLaia (human transcriptions + random split) | Unknown | Unknown | Unknown | 1 | 2 |
| 436 | PyLaia (rover consensus + agreement-based split) | Unknown | Unknown | Unknown | 1 | 2 |
| 437 | Qwen2.5-VL 32B | Alibaba | — | Vision-Language Model | 2 | 2 |
| 438 | Qwen3-VL-4B | Alibaba Qwen | 4B | Vision-Language Model (4B params) | 2 | 2 |
| 439 | ReasTAP-Large | Unknown | Unknown | Unknown | 1 | 2 |
| 440 | SANA | — | — | — | 1 | 2 |
| 441 | SEMv3 | IFLYTEK / USTC (Zhang et al.) | Unknown | Keypoint Offset Regression (KOR) module; split-and-merge paradigm for table separation line detection | 1 | 2 |
| 442 | SIGA_S | Unknown | Unknown | Unknown | 2 | 2 |
| 443 | SLANet | Unknown | Unknown | Unknown | 1 | 2 |
| 444 | SPECTER | Unknown | Unknown | Unknown | 2 | 2 |
| 445 | SSD300 (VGG-16) | Google / UNC | ~24M | Single-shot multibox detector with VGG-16 backbone, 300x300 input | 1 | 2 |
| 446 | SSD512 (VGG-16) | Google / UNC | ~27M | Single-shot multibox detector with VGG-16 backbone, 512x512 input | 1 | 2 |
| 447 | Salience-aware TAPAS | Unknown | Unknown | Unknown | 1 | 2 |
| 448 | SciNCL | Unknown | Unknown | Unknown | 2 | 2 |
| 449 | Selective Search | Unknown | Unknown | Unknown | 1 | 2 |
| 450 | Span | Unknown | Unknown | Unknown | 1 | 2 |