Primary sourceJerry Liu
View sourceEvent ·Multi-source
LlamaIndex 发布文档抽取基准 ExtractBench Pro,Codex with Astra 仅得约 58%
LlamaIndex 推出面向企业真实文档抽取场景的基准 ExtractBench Pro,覆盖图例规则、内部术语、跨页聚合、图表读数、井测曲线等长尾复杂度。现有基准已被前沿模型刷爆(最便宜模式在原 ExtractBench 得分超 93%),而新基准上最强的 Codex with Astra 在 Value F1 上也只有约 58%,且成本接近每页 1 美元。LlamaParse 的 agentic/agentic plus 模式得分 20-40%,价格更适合生产环境。该基准已上线网站,并发布在 GitHub 和 Hugging Face。
Current read
LlamaIndex 做了个真实企业文档抽取的基准,连最贵的 Codex with Astra 也才 58 分,还开源在 GitHub 和 HuggingFace 上,做文档抽取的可以去试试。
11 sources58° AI heatLast updated 2026/10/18 18:26:33
Evidence
11 sourcesRelated source 1TestingCatalog
View sourceRelated source 2OpenAI
View sourceRelated source 3Teortaxes
View sourceRelated source 4elvis
View sourceRelated source 5Tw93
View sourceRelated source 6Browser Use
View sourceRelated source 7@koltregaskes
View sourceRelated source 8kimmonismus
View sourceRelated source 9Bindu Reddy
View sourceRelated source 10shao__meng
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.