ModelsSelected

Unsiloed 在 olmOCR-Bench 得分 88.0,超过 GPT-5.5 的 84.6

Why we picked it

文档识别这块有个新结果:Unsiloed 在 Ai2 的 olmOCR-Bench 上拿了 88.0 分,比 GPT-5.5 的 84.6 还高。做 PDF 解析、数据抽取的团队可以看看排行榜再决定用哪个模型,通用模型不一定是最优解。

Ai2 官方账号发布消息称,UnsiloedHQ 在其开源基准 olmOCR-Bench 上拿到 88.0 分,超过 GPT-5.

Image · Allen AI (Ai2)
Body

5 的 84.6 分。

olmOCR-Bench 由 Allen Institute for AI(Ai2)维护,用于衡量模型读取复杂文档的能力,并提供公开排行榜。这次结果意味着一个较小的专用系统在文档解析这一具体任务上压过了通用大模型。

对做文档处理、RAG 管道或数据抽取的团队来说,排行榜可以直接用来选型。

Original · Allen AI (Ai2)

Open benchmarks help move AI forward. 📄

@UnsiloedHQ reports scoring 88.0 on our olmOCR-Bench, ahead of GPT-5.5 at 84.6.

Great to see our open benchmark helping the field measure progress on reading complex documents!

Explore the leaderboard: https://t.co/G8Yz3dHSh6

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include olmOCR-Bench, Unsiloed, GPT-5.5, Ai2.

Source attribution: curated from Allen AI (Ai2) (@allen_ai).