# Step 3.7 Flash vs Baidu Unlimited-OCR-2 (slim)

> Step 3.7 Flash scores 59.8 (C) to Baidu Unlimited-OCR-2's 54.2 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/step-3-7-flash-vs-unlimited-ocr-2.md (~9,950 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/step-3-7-flash-vs-unlimited-ocr-2.json · canonical https://www.anchorterminal.com/compare/step-3-7-flash-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)

Step 3.7 Flash scores 59.8 (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 documentation and upkeep. Both do open-weight models you run yourself.

- Step 3.7 Flash: C 59.8, rank #93 of 160 open-weight models · https://www.anchorterminal.com/tools/step-3-7-flash.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
- Step 3.7 Flash, good for Teams with a GPU server or a provider account that want an open, long-context agent model with vision Ahead on Reach, 70 against 55; Agent interface, 85 against 75.
- 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 Documentation and upkeep, 50 against 39.

| Category | Step 3.7 Flash | Baidu Unlimited-OCR-2 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 70 | 55 |
| Risk (20%) | 45 | 45 |
| Agent interface (10%) | 85 | 75 |
| Documentation and upkeep (10%) | 39 | 50 |

| Fact (where they differ) | Step 3.7 Flash | Baidu Unlimited-OCR-2 |
| --- | --- | --- |
| Vendor | StepFun | Baidu |
| Licence | Apache-2.0 (metadata and card; no LICENSE file) | 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 | 2026-06-03 | 2026-10-26 |

Why the edge:
- Reach, Step 3.7 Flash +15: Step 3.7 Flash 70 (Memory 5, the smallest build at 4 bits is StepFun's IQ4_XS GGUF, 104.99 GB with the 3.97 GB projector, and 108.96 GB × 1.2 = 130.8 GB, over what the reference m…); 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, Baidu Unlimited-OCR-2 +11: Step 3.7 Flash 39 (Model card 14, Intended use, the architecture, the parameters, the context and the language (in the metadata) are on the card.); 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, Step 3.7 Flash +10: Step 3.7 Flash 85 (Chat template 20, chat_template.jinja in the repository (5,723 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.)