Z.ai GLM-Legal Outperforms Claude Fable 5 and Kimi K3 on Harvey Legal Benchmark
The new legal AI model achieves a 19.2% all-pass score on the benchmark, nearly tripling its base performance.
The story so far
2 publishers have covered this in 2 articles since 12 Oct 2026. Hacker News published first, on 12 October at 16:11 UTC; marktechpost.com followed 16h 08m later. The most recent article, from marktechpost.com, appeared on 13 October at 08:19 UTC.
Outlets reporting it: Hacker News, marktechpost.com.
No prediction market is linked to this story at the moment. We match each story to Polymarket and Kalshi markets by what they ask, and show one only when it is close enough to be useful; if a market on this topic opens, it will appear here. Meanwhile, browse every market we track or see how stories and markets are matched.
Sources
Every article we clustered into this story. Headlines link to the publisher.
In this story
- Z.ai
- GLM-Legal
- Claude Fable 5
- Kimi K3
- Harvey LAB