Vals AI says OpenAI used its Legal Research Bench to validate Astra for Law. OpenAI-reported results show Astra for Law ahead of GPT-6 Astra with web search at every price point: 90.0% versus 84.1% on the weighted rubric and 53.7% versus 39.6% all-pass; Vals is validating the claim on a held-out set.
Key Takeaways
- βOpenAI reports Astra for Law at 90.0% on Vals weighted legal-research scoring versus 84.1% for GPT-6 Astra with web search.
- βThe reported all-pass rate is 53.7% versus 39.6%, pending Vals validation on a held-out set.
- βThe result shows how specialized instructions, tools, and retrieval configuration can materially change model benchmark and price comparisons.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.