LitigationBench. A Litigation Task-Based AI Benchmark

Show HN: LitigationBench. A Litigation Task-Based AI Benchmark

LitigationBench. A Litigation Task-Based AI Benchmark operates in show hn launch.

Profile

Adding to the sea of AI benchmarks, but with a focus on legal and litigation-based tasks and tests. E.g., hallucinating cases, misreading precedent, drafting, AI writing tics, etc.Developed as part of a litigation platform I've started, but not sharing this benchmark to promote that. Just thought the findings were interesting--namely, Anthropic's models (except for Haiku) producing zero hallucinated cases.Also, if anyone would like to see additional tests / benchmarks or models tested, let me know and I'll incorporate them into v3 if it makes sense.

As a business in show hn launch, LitigationBench. A Litigation Task-Based AI Benchmark is listed here with the public details available about it.

Its current recorded stage is Show HN launch.

Website: litco.ai/litigationbench