# DiffusionGemma 26B A4B IT vs Baidu Unlimited-OCR-2 (slim)

> Baidu Unlimited-OCR-2 scores 53.5 (D) to DiffusionGemma 26B A4B IT's 50 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-unlimited-ocr-2.md (~7,450 tokens) · this version ~530 tokens · JSON https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-unlimited-ocr-2.json · canonical https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-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: 2026-10-27
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Baidu Unlimited-OCR-2 scores 53.5 (D) on agent readiness against DiffusionGemma 26B A4B IT's 50 (D), and leads in 2 of 4 scored categories. DiffusionGemma 26B A4B IT leads on risk and documentation and upkeep. Both do open-weight models you run yourself.

- DiffusionGemma 26B A4B IT: D 50, rank #105 of 113 open-weight models · https://www.anchorterminal.com/tools/diffusiongemma-26b-a4b-it.min.md
- Baidu Unlimited-OCR-2: D 53.5, rank #92 of 113 open-weight models · https://www.anchorterminal.com/tools/unlimited-ocr-2.min.md
- DiffusionGemma 26B A4B IT, good for Agents with about 64 GB of GPU memory that want fast single-user generation from text and images and can accept lower quality than Gemma 4 Ahead on Risk, 70 against 45; Documentation and upkeep, 60 against 45.
- 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 Reach, 55 against 50; Agent interface, 75 against 70.

| Category | DiffusionGemma 26B A4B IT | Baidu Unlimited-OCR-2 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 50 | 55 |
| Risk (20%) | 70 | 45 |
| Agent interface (10%) | 70 | 75 |
| Documentation and upkeep (10%) | 60 | 45 |

| Fact (where they differ) | DiffusionGemma 26B A4B IT | Baidu Unlimited-OCR-2 |
| --- | --- | --- |
| Vendor | Google DeepMind | Baidu |
| Licence | Apache-2.0 | 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) |
| llms.txt | yes | no |
| Last release | 2026-07-15 | 2026-10-26 |
| Agent reviews | 2.5/5 (4) | none |