Unverified50% confidenceFactExact time
MarathonDocBench is a new hundred-page-level document parsing benchmark proposed by the Unlimited OCR 2 team to fill the gap in existing evaluations on the ultra-long document range.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLlamaIndex launched ExtractBench Pro, a benchmark for complex PDF document extraction that focuses on two dimensions: "frontier accuracy and cost."60% similarUnverifiedParagraph-level retrieval splits documents into chunks of around a few hundred characters, each chunk being vectorized separately and indexed, in order to improve recall precision and directly locate specific content.58% similarUnverifiedThe full name of DoGBench is Documentation Generation Benchmark.57% similarUnverifiedOmniParseBench is a unified benchmark leaderboard for document parsers released by Datalab.56% similarUnverifiedGlyphSprout's workflow starts from A4 templates with 35 cells per page, and a project can cover at most 512 supported BMP characters distributed across 15 pages.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1113977API
curl https://kongchang.com/api/v1/knowledge/claims/1113977MCP
get_claim(id=1113977)