ExtractBench

What is ExtractBench?

ExtractBench evaluates schema-guided extraction from enterprise documents. Given a document and a user-defined JSON schema, systems must return schema-valid…

Released

2026-07-31

Evaluates

Factuality, General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.29677

ExtractBench paper, code and dataset

• Paper https://arxiv.org/abs/2607.29677
• Code https://github.com/run-llama/ExtractBench
• Dataset https://huggingface.co/datasets/llamaindex/ExtractBench

Which sources cite ExtractBench?

• ExtractBench

Related Factuality, General AI, Language & Knowledge, cs.AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench