# Surya OCR 2.5 vs Baidu Unlimited-OCR-2 (slim)

> Surya OCR 2.5 scores 61 (C) to Baidu Unlimited-OCR-2's 54.2 (C) for ocr. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/surya-ocr-2-5-vs-unlimited-ocr-2.md (~6,950 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/surya-ocr-2-5-vs-unlimited-ocr-2.json · canonical https://www.anchorterminal.com/compare/surya-ocr-2-5-vs-unlimited-ocr-2
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Surya OCR 2.5 scores 61 (C) on agent readiness against Baidu Unlimited-OCR-2's 54.2 (C), and leads in 2 of 4 scored categories. Baidu Unlimited-OCR-2 leads on agent interface. Both do ocr.

- Surya OCR 2.5: C 61, rank #82 of 160 open-weight models · https://www.anchorterminal.com/tools/surya-ocr-2-5.min.md
- Baidu Unlimited-OCR-2: C 54.2, rank #133 of 160 open-weight models · https://www.anchorterminal.com/tools/unlimited-ocr-2.min.md
- Surya OCR 2.5, good for Small companies and researchers who need quick OCR with layout on a laptop or a small GPU and fit the licence Ahead on Reach, 90 against 55; Documentation and upkeep, 57 against 50.
- Baidu Unlimited-OCR-2, good for Pipelines with an NVIDIA GPU that need long scanned or rendered documents parsed in one pass, with page order, cross-page tables and boxes kept Ahead on Agent interface, 75 against 70.

| Category | Surya OCR 2.5 | Baidu Unlimited-OCR-2 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 55 |
| Risk (20%) | 45 | 45 |
| Agent interface (10%) | 70 | 75 |
| Documentation and upkeep (10%) | 57 | 50 |

| Fact (where they differ) | Surya OCR 2.5 | Baidu Unlimited-OCR-2 |
| --- | --- | --- |
| Vendor | Endless Labs, Inc. (Datalab) | Baidu |
| Licence | Modified OpenRAIL-M (free for research, personal use and companies under $5M in revenue and funding) | MIT (Hub metadata; the Hugging Face repository has no LICENSE file, and the GitHub code repository's LICENSE is the MIT text, copyright 2026 Baidu) |
| Last release | 2026-10-29 | 2026-10-26 |
| Terms last updated | not read yet | no document linked |

Why the edge:
- Reach, Surya OCR 2.5 +35: Surya OCR 2.5 90 (Memory 30, Datalab's own Q8_0 GGUF is 0.63 GB with a 0.21 GB projector, and 0.84 GB × 1.2 = 1.0 GB, within 16 GB.); Baidu Unlimited-OCR-2 55 (Memory earns the full 30, since the only build is 6.69 GB of BF16 weights that need about 8 GB with the fifth added.)
- Documentation and upkeep, Surya OCR 2.5 +7: Surya OCR 2.5 57 (Model card 17, Intended use, limitations, the architecture (a Qwen 3.5-style vision-language model with separate detection models), parameters (689M), the servi…); Baidu Unlimited-OCR-2 50 (The card covers intended use and the new attention, and misses limitations, parameters, context length, languages and a cut-off (5).)
- Agent interface, Baidu Unlimited-OCR-2 +5: Surya OCR 2.5 70 (Chat template 20, chat_template.jinja in the repository (2,872 characters).); Baidu Unlimited-OCR-2 75 (Read for a document parser, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns.)