News for hackers. Stuff that matters.

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

https://litco.ai/litigationbench

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.

( no comments | 2 points | on HN )

There are no comments yet.