Show HN: Unsiloed AI – #1 on OlmOCR-Bench,Beats Reducto, LlamaParse and GPT-5.5
Unsiloed AI has developed a new document parser that excels in handling complex real-world challenges. Their latest version, v3.1, achieved the top rank on olmOCR-Bench, outperforming several other OCR services. The parser's performance was evaluated across a large dataset, revealing that many errors were related to formatting rather than OCR accuracy.
- ▪Unsiloed Parser v3.1 scored 88.0 strict pass-rate on olmOCR-Bench.
- ▪It outperformed 18 other OCR services, including GPT-5.5 and Azure Document Intelligence.
- ▪A secondary evaluation raised the corrected score to 94.8 by classifying real misses versus semantic equivalents.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,381 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Ycombinator |
| Canonical URL | https://news.ycombinator.com/item?id=48271937 |
| Publication time | Mon, 25 May 2026 21:35:03 +0000 |
| Retrieval time | 2026-05-25T21:52:40.535Z |
| Last seen | 2026-05-25T21:52:41.799Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | -XzgyIbs_uHw |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Most of the document parsers fail on real world challenges like complex tables, handwritten documents, historical document scans, equations, multi-column layouts, complex reading order, etc. We built Unsiloed Parser to handle exactly these cases.Our latest parser v3.1 achieved #1 rank and scored 88.0 strict pass-rate on olmOCR-Bench. We ran the evaluation across 1,403 PDFs and 8,413 unit tests using the unmodified upstream Allen AI scorer (olmocr==0.4.27) and found Unsiloed beats 18 other OCR services, including GPT-5.5, Claude Opus 4.7, LlamaParse, Reducto, Azure Document Intelligence, AWS Textract, and Unstructured.When we dug deeper into the failure cases, we found many errors were not OCR errors but things like \frac vs \dfrac, whitespace differences, or equivalent LaTeX renderings.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Ycombinator.