Unverified50% confidenceBenchmarkExact time
In the VALS AI legal evaluation, GLM-Legal took first place among open-weight models on both the Harvey Lab and Legal Bench leaderboards, with a 19.2% all-tasks-passed rate and 86.23% accuracy.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
DeepSeek Launches Search API, Zhipu's Open-Source Legal LLM Tops Charts
bilibiliAI天天酱10/18/2026
Related Entities
Related Claims
UnverifiedThe GLM-Legal model launched by Z.ai achieved a 19.2% all-pass rate on the Harvey LAB legal Agent benchmark, surpassing Claude Fable 5 and Kimi K3.78% similarUnverifiedGLM-Legal's 19.2% all-pass rate on Harvey LAB means that on most tasks the model still needs a human lawyer as a fallback.70% similarUnverifiedIn Harvey LAB-AA legal analysis, Muse Wonder achieved 13.1%, more than three times Claude Opus 5.5's 4.2%; in Vals Finance Agent V2 it ranked first with 59.1%.66% similarUnverifiedHarvey and Engram used the model to build a synthetic law firm, achieving an average score of 67 across 250 legal tasks, higher than all models evaluated in the study.66% similarUnverifiedAt 10 days, lawyers with the AI tool showed a drafting score improvement of 0.34 standard deviations (approximately a 10-percentile increase), and at 90 days the improvement expanded to 0.38 standard deviations (approximately 11 percentiles).62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1059784API
curl https://kongchang.com/api/v1/knowledge/claims/1059784MCP
get_claim(id=1059784)