Splitting Performance
This page is for version v2026-02-09 (default).
For other versions, use one of these documentation indexes:
- v2026-02-09 (default): https://docs.extend.ai/2026-02-09/llms.txt
- v2025-04-21: https://docs.extend.ai/2025-04-21/llms.txt
- v2024-12-23: https://docs.extend.ai/2024-12-23/llms.txt
Our highest performance (in terms of accuracy and reliability) base splitting processor. Always stays up to date with the best foundation models available across all of our benchmarks.
Versions
| Version | Date | Changelog |
|---|---|---|
1.6.0 | 2026-03-30 | Minor model version upgrade for increased performance on complex split cases and better rule adherence. |
1.5.0 | 2026-01-26 | Introduces a new splitter engine that provides superior latency and slight performance improvements across all document sizes. |
1.4.0 | 2025-12-15 | Updates to the splitting method to increase accuracy, speed and reliability with the new models rolled out in version 1.3.0. |
1.3.0 | 2025-12-15 | Model upgrade for core reasoning and splitting step in the pipeline. New hybrid model approach for large document splitting. |
1.2.0 | 2025-06-06 | Add support for page overlap detection as an advanced option. Small performance improvements to split identifier generation and type detection for splitters with complex rules. |
1.1.0 | 2025-04-17 | Promoting a new, higher performing foundation model on splitter evals to default. Improvements to the “High Precision” splitting method, particularly for documents that might have a lot of small subdocuments. |
1.0.0 | 2024-07-01 | Initial splitter release. |