Updated daily at 05:00 UTC
Models
AI models
1521 current models, newest first. Each links to its benchmark results, with who ran them.
Best by specialty
Independent and third-party results only · method category-2026-09-29.1
All current models
Best for
- Knowledge & reasoning
- Scientific reasoning
- Mathematics
- Coding & software engineering
- Agentic tool use
- Computer & browser use
- Professional knowledge work
- Long context
- Vision & multimodal understanding
- OCR & documents
- Law
- Medicine & health
- Finance
- Multilingual
- Factuality & hallucination
- Instruction following
- Writing
- Speech & audio
- Human preference
Kind· OCR document
Context
Input price
Weights· Proprietary
Reasoning
| Model | Maker | Kind | Released | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|
| Mistral OCR 4.1Mistral OCR | Mistral AI | OCR document | 16 Jul 2026 | — | — | — |
| Mistral OCR 4.0Mistral OCR | Mistral AI | OCR document | 23 Jun 2026 | — | — | — |
| Qwen3.5-OCRQwen-OCR | Alibaba Group | OCR document | 16 Jun 2026 | — | — | — |
| Mistral OCR 3Mistral OCR | Mistral AI | OCR document | 18 Dec 2025 | — | — | — |
| Qwen-VL-OCRQwen-OCR | Alibaba Group | OCR document | 28 Oct 2024 | — | — | — |
| Document ParseUpstage Document AI | Upstage | OCR document | 10 Sep 2024 | — | — | — |
| Document OCRUpstage Document AI | Upstage | OCR document | 10 Apr 2023 | — | — | — |
| Parse v5.0Cohere Parse | Cohere | OCR document | — | — | — | — |
- Mistral OCR 4.1Mistral AI · 16 Jul 2026 · — context—in / 1M
- Mistral OCR 4.0Mistral AI · 23 Jun 2026 · — context—in / 1M
- Qwen3.5-OCRAlibaba Group · 16 Jun 2026 · — context—in / 1M
- Mistral OCR 3Mistral AI · 18 Dec 2025 · — context—in / 1M
- Qwen-VL-OCRAlibaba Group · 28 Oct 2024 · — context—in / 1M
- Document ParseUpstage · 10 Sep 2024 · — context—in / 1M
- Document OCRUpstage · 10 Apr 2023 · — context—in / 1M
- Parse v5.0Cohere · — · — context—in / 1M