# GLM-Legal: Z.ai's Legal Model, Benchmarks Checked, Price

> Z.ai's GLM-Legal scores 19.2% on Harvey's legal agent benchmark. We checked it against the Vals leaderboard: sixth place, at $0.15 per task.

- Author: Nitish Garg, Founder & CEO, CellCog
- Published: 2026-10-12
- Canonical (HTML): https://cellcog.ai/blog/glm-legal/
- Section: Guides / Choosing a platform
- Publisher: CellCog (https://cellcog.ai), the AI employee platform. Blog index for agents: https://cellcog.ai/blog/llms.txt

## Key points

- Z.ai released GLM-Legal on October 12, 2026: a legal model built on GLM-5.3-Flash, trained for contract review, evidence analysis and compliance.
- Its 19.2% all-pass rate on Harvey's Legal Agent Benchmark matches the Vals AI leaderboard (19.17%), where it ranks sixth behind four Muse Spark models and Gemini 4 Argon.
- Its edge is cost: $0.15 per Harvey LAB test on Vals, against $10.55 for Gemini 4 Argon and $26.16 for GPT-6 Astra.
- The trade is time: an average Harvey LAB run took 1 hour 12 minutes, against 24 minutes for the leader, Muse Spark 1.2.
- Z.ai trained the model and its agent harness together with reinforcement learning across tens of thousands of legal environments.
- Access is by application only; Z.ai has published no GLM-Legal price. It is coming to Z.ai's AutoClaw desktop agent.

## At a glance

- **What is GLM-Legal?** Z.ai's legal model, released October 12, 2026 and built on GLM-5.3-Flash, trained for agentic legal work such as contract review, evidence analysis and compliance.
- **How good is GLM-Legal on Harvey LAB?** 19.17% task pass rate on the Vals AI leaderboard, sixth of the models listed; Muse Spark 1.2 leads at 25.42% and Gemini 4 Argon has 19.58%.
- **How much does GLM-Legal cost?** Z.ai has published no price. On the Vals leaderboard a Harvey LAB test cost $0.15, run at GLM-5.3-Flash's $0.075 input and $0.25 output per million tokens.

**Z.ai released GLM-Legal on October 12, 2026, a legal model built on GLM-5.3-Flash and trained for contract review, evidence analysis and compliance work.** Its [launch post](https://x.com/Zai_org/status/2109678174468534511) at 16:10 UTC says it "matches frontier models on mainstream legal benchmarks", and its [tech blog](https://z.ai/blog/glm-legal) puts the headline number at a 19.2% all-pass rate on Harvey's Legal Agent Benchmark (LAB). Access is by application for now: "Apply for API access", with Z.ai's AutoClaw desktop agent to follow.

We checked the number against the independent leaderboard. It holds, and it tells a more useful story than Z.ai's chart does.

## The number, checked

Harvey LAB gives an agent a partner-style instruction and a folder of client documents, and a task counts as passed only when every rubric criterion passes. [Vals AI runs the held-out set](https://www.vals.ai/benchmarks/hlab) and updated its leaderboard on October 12 with GLM Legal on it.

*Table: Z.ai's chart vs the Vals AI leaderboard, Harvey LAB task pass rate (October 12, 2026)*

| Model | Z.ai's chart | Vals AI leaderboard | Vals rank |
|---|---|---|---|
| GLM-Legal | 19.2% | 19.17% | 6 |
| Kimi K3 | 12.9% | 12.92% | 10 |
| Claude Fable 5 | 11.3% | 11.25% | 14 |
| GLM-5.3-Flash | 6.7% | 6.67% | 29 |
| GPT-6 Astra | 5.4% | 5.42% | 32 |
| Muse Spark 1.2 | not shown | 25.42% | 1 |
| Gemini 4 Argon | not shown | 19.58% | 5 |

Every number on Z.ai's chart matches Vals to the rounding. What the chart leaves out is the five models above it: Meta's Muse Spark 1.2, 1.3 Max, 1.3 and 1.1 (25.42% down to 20.00%) and Google's Gemini 4 Argon at 19.58%. GLM-Legal is sixth, within the leaderboard's roughly 2.5-point error bars of Argon. The gain over its base model is real: 19.17% against 6.67% for GLM-5.3-Flash, the 12.5 points Z.ai claims.

## Where it wins: cost per task

On the same leaderboard GLM Legal cost $0.15 per test against $10.55 for Gemini 4 Argon, its nearest neighbour by score, and $2.09 for the leader. Vals ran it at $0.075 in and $0.25 out per million tokens, GLM-5.3-Flash's rate; Z.ai has not published a GLM-Legal price. The trade is time: an average run took 1 hour 12 minutes, against 24 minutes for Muse Spark 1.2.

## The other two benchmarks

Z.ai's blog says GLM-Legal matches "frontier closed-source models on LegalBench and PLawBench". Its own chart puts it at 86.2 on LegalBench against 88.6 for Claude Fable 5 and 87.1 for GPT-6 Astra, and 77.3 on PLawBench (Chinese legal practice) against Fable 5's 77.7. Close, not ahead. Those two are Z.ai's runs; we found no independent scores yet.

On Artificial Analysis's [LAB-AA v1.1](https://artificialanalysis.ai/evaluations/harvey-lab-aa), a private 120-task version that fails any deliverable with a material hallucination, GLM-Legal is not listed yet; its base models are.

## How Z.ai built it

The blog describes two stages on top of GLM-5.3-Flash: legal mid-training on a larger corpus, then reinforcement learning "across tens of thousands of realistic legal environments" in which the agent harness and the model were changed together: "Harness architecture and model training iterate in lockstep." The examples it shows are agent work, not chat: tracked-change edits to a services contract, a contradiction map across 40 dispute documents, a pre-launch privacy checklist for three countries.

That is the same direction as OpenAI's [Astra for Law](https://cellcog.ai/blog/astra-for-law/) in September, which wrapped GPT-6 Astra in a legal search index and instructions, sold first to selected firms. Two labs, one month, the same bet: the value in legal AI sits in the configuration around the model.

## Where CellCog sits

Our conflict, declared: we build CellCog, where businesses hire AI employees, and every CellCog tier runs on Claude Opus 5.5, which scores 3.75% on the same Vals leaderboard. We do not route to GLM-Legal. An AI employee doing legal operations reads, drafts and organises; it is an assistant to a lawyer, never counsel.

## What we are watching

- A published GLM-Legal price and general API access.
- Independent LegalBench and LAB-AA scores.
- GLM-Legal arriving in AutoClaw.

## Update log

- October 12, 2026: page opened, from Z.ai's post and blog and the Vals AI leaderboard updated the same day.

## Sources

- Z.ai, [GLM-Legal: Advancing Agentic Legal Intelligence](https://z.ai/blog/glm-legal), October 12, 2026; [announcement on X](https://x.com/Zai_org/status/2109678174468534511), 16:10 UTC.
- Vals AI, [Harvey's Legal Agent Benchmark leaderboard](https://www.vals.ai/benchmarks/hlab), updated October 12, 2026.
- Artificial Analysis, [Harvey LAB-AA v1.1](https://artificialanalysis.ai/evaluations/harvey-lab-aa).
- Harvey, [Introducing Harvey's Legal Agent Benchmark](https://www.harvey.ai/blog/introducing-harveys-legal-agent-benchmark), May 6, 2026.

## FAQ

**Is GLM-Legal better than GPT-6 Astra and Claude?**

On Harvey LAB, yes: 19.17% against 5.42% for GPT-6 Astra and 11.25% for Claude Fable 5. On LegalBench, Z.ai's own chart has it slightly behind both.

**Is GLM-Legal open-weight?**

Z.ai has not released weights; access is through an application for the API.

**How is it different from Astra for Law?**

Astra for Law wraps GPT-6 Astra in a legal search index for selected firms; GLM-Legal is a smaller model trained with its agent harness for legal tasks.

**What is Harvey LAB?**

Harvey's Legal Agent Benchmark: an agent gets a partner-style instruction and client documents, and a task passes only if every rubric criterion passes.

**Does CellCog use GLM-Legal?**

No. Every CellCog tier runs on Claude Opus 5.5; we cover GLM-Legal as a model for legal work.

## Related

- [Astra for Law: OpenAI's Legal Model, Benchmarks, Access](https://cellcog.ai/blog/astra-for-law/index.md)
- [GLM-5.3-Flash: Is It Still Free? Price After the Promo](https://cellcog.ai/blog/glm-5-3-flash/index.md)
- [GLM 5.3 for AI Agents: Release Date, Weights, What It Means](https://cellcog.ai/blog/glm-5-3-for-ai-agents/index.md)
- [Best AI Agent Harnesses: October 2026 Rankings](https://cellcog.ai/blog/best-ai-agent-harnesses/index.md)

## The AI employee for this read

[AI Legal Assistant](https://cellcog.ai/ai-employees/ai-legal-assistant): I built this page. For what it covers, hire a legal assistant: it tracks the contracts, drafts the first pass and routes what needs a lawyer.

---

Markdown alternate of https://cellcog.ai/blog/glm-legal/. Try CellCog free, no credit card needed: https://cellcog.ai/signup