---
format: "aidr-story-markdown/v1"
id: "98717367a446b8f4cb5d2f215d9257208695e1c831203e89b318a3f0dacaf95a"
canonical_url: "https://aidr.today/98717367?lang=en"
title: "Grok 4.7 Tops New Legal AI Benchmark With 9.4% Score"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-08T19:09:33.000Z"
category: "Models"
topics: ["xai","llm"]
source_urls: ["https://marketbrief.now/ai/grok-47-tops-new-legal-ai-benchmark-with-94percent-score-ba062967","https://huggingnews.com/ai/grok-47-tops-new-legal-ai-benchmark-with-94percent-score-ba062967"]
summary: "xAI's Grok 4.7 leads the Harvey LAB-AA v1.1 legal AI benchmark with a 9.4% Hallucination-Gated All-Pass Rate, followed by Meta's Muse Spark 1.3 and OpenAI's GPT-6 Astra. The benchmark penalizes models for fabricated content or contradictions, and Grok 4.7 costs approximately $9.50 per task."
---

# Grok 4\.7 Tops New Legal AI Benchmark With 9\.4% Score

> [Open the canonical story](<https://aidr.today/98717367?lang=en>)

**Published:** 2026-10-08T19:09:33.000Z
**Category:** Models
**Topics:** xai, llm

## Summary

xAI's Grok 4\.7 leads the Harvey LAB\-AA v1\.1 legal AI benchmark with a 9\.4% Hallucination\-Gated All\-Pass Rate, followed by Meta's Muse Spark 1\.3 and OpenAI's GPT\-6 Astra\. The benchmark penalizes models for fabricated content or contradictions, and Grok 4\.7 costs approximately $9\.50 per task\.

## Sources

- [Story source](<https://marketbrief.now/ai/grok-47-tops-new-legal-ai-benchmark-with-94percent-score-ba062967>)
- [Story source](<https://huggingnews.com/ai/grok-47-tops-new-legal-ai-benchmark-with-94percent-score-ba062967>)