Z.ai
GLM 5.3
GLM 5.3 is a model with open weights from Z.ai. On the Vals AI Legal Research Bench it reaches 49.04 percent all-pass, position 10 of 91, within a standard error of ±3.48 percentage points at $2.24 per task, as at 9 November 2026 [1]. It does not pass the compliance gate: No EU guarantee: AWS Bedrock: in EU regions only Global cross-region inference (processing outside the EU possible).
- Generally available
- Open weights
- 18 August 2026
- PrudentScore
- -No score: the gate is not open
- Compliance gate
- RejectedNo EU guarantee: AWS Bedrock: in EU regions only Global cross-region inference (processing outside the EU possible)
- Cost per task
- $2.24Vals AI, per completed task [1]
01
Compliance gate
Why
- No EU guarantee: AWS Bedrock: in EU regions only Global cross-region inference (processing outside the EU possible)
- Z.ai own API: "We generally provide the Services from Singapore" (privacy policy); no EU contracting party or EU processing.
The gate only opens when all three requirements are covered: processing in the EU, a contracting party in the EU or EEA, and a contractual exclusion of training on customer data. The gate tests a route, not a model name: the same model can pass through one provider and fail through another. Where a provider publishes no figure, we give no estimate.
02
Routes and EU processing
The gate tests a route (processor, region and contract), not a model name. Per route: processing in the EU, the contracting party and training on customer data.
| Processor | Region or deployment | EU processing | Source |
|---|---|---|---|
| AWS Bedrock | in EU regions only Global cross-region inference (processing outside the EU possible) | No | SourceRead 10 November 2026 |
03
Scores per benchmark
Every measurement with its source, measurement date and the day we read it. The position counts only the models measured on the same benchmark and version.
- Legal Research BenchVersion 1 · Counts towards the PrudentScore49.04%± 3.4810 of 91
Vals AI, Legal Research Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $2.24
- Harvey LAB (Vals implementation)Version 1.114.58%± 2.8611 of 36
Vals AI, Harvey LAB (Vals implementation), v1.1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $3.99
- Harvey LAB (Vals implementation)Version 1 · Counts towards the PrudentScore8.33%± 2.0027 of 80
Vals AI, Harvey LAB (Vals implementation), v1, 18 October 2026 · Source · Measured 18 October 2026 · Read 10 November 2026 · cost per task $4.30
- LegalBench (Vals leaderboard)Version 184.84%± 0.4029 of 113
Vals AI, LegalBench (Vals leaderboard), v1, 13 October 2026 · Source · Measured 13 October 2026 · Read 10 November 2026
- CaseLaw v2Not measured
- TaxEval v2Version 272.36%± 0.8860 of 108
Vals AI, TaxEval v2, v2, 1 September 2026 · Source · Measured 1 September 2026 · Read 10 November 2026
- Tax Agent BenchVersion 143.33%± 3.567 of 82
Vals AI, Tax Agent Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $1.80
- CorpFin v2Not measured
- Immigration BenchVersion 166.73%± 1.6214 of 26
Vals AI, Immigration Bench, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $0.12
- Access to JusticeVersion 173.70%± 0.715 of 23
Vals AI, Access to Justice, v1, 10 November 2026 · Source · Measured 10 November 2026 · Read 10 November 2026 · cost per task $0.46
- Public Benefits BenchVersion 1.168.54%± 1.2110 of 50
Vals AI, Public Benefits Bench, v1.1, 12 October 2026 · Source · Measured 12 October 2026 · Read 10 November 2026 · cost per task $0.95
- Vals Legal IndexVersion 174.62%± 1.846 of 36
Vals AI, Vals Legal Index, v1, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $2.68
- Vals IndexVersion 2.259.85%± 1.1114 of 35
Vals AI, Vals Index, v2.2, 9 November 2026 · Source · Measured 9 November 2026 · Read 10 November 2026 · cost per task $8.52
- Vals IndexVersion 2.153.51%± 1.3020 of 50
Vals AI, Vals Index, v2.1, 18 October 2026 · Source · Measured 18 October 2026 · Read 10 November 2026 · cost per task $7.25
- GPQA Diamond (Vals-run)Version 188.13%± 1.8535 of 109
Vals AI, GPQA Diamond (Vals-run), v1, 1 September 2026 · Source · Measured 1 September 2026 · Read 10 November 2026
- MMLU Pro (Vals-run)Version 186.77%± 0.3438 of 110
Vals AI, MMLU Pro (Vals-run), v1, 1 September 2026 · Source · Measured 1 September 2026 · Read 10 November 2026
- Artificial Analysis Intelligence IndexVersion 4.3.2 · Counts towards the PrudentScore
Artificial Analysis Intelligence Index v4.3.2: 44.8. Source: Artificial Analysis (artificialanalysis.ai), accessed 1 October 2026 [37].
Artificial Analysis, Artificial Analysis Intelligence Index, v4.3.2, 1 October 2026 · Source · Measured 1 October 2026 · Read 1 October 2026
Source: Vals AI (Legal Research Bench, Harvey LAB (Vals implementation), LegalBench (Vals leaderboard), TaxEval v2, …) · Licence: CC BY 4.0 · Adaptation: Prudai selected the models, translated the explanations, added the gate verdict and the PrudentScore and rounded figures to two decimals.
The PrudentScore is a composition by Prudai B.V. based on publicly published figures and does not represent the view or endorsement of Vals AI, Harvey or Artificial Analysis. Figures from Artificial Analysis appear in running text only, with attribution and a link, as that party's terms require [9].
04
Key facts
- Developer
- Z.ai
- Model family
- GLM
- Release date
- 18 August 2026
- Status
- Generally available
- Context window
- 1M tokens
- Max output tokens
- 128K tokens
- List price
- $1.40 input · $4.40 outputper million tokens · Read 10 November 2026
- Weights
- Open
- = not yet recorded in the register.
05
Frequently asked questions about this model
Does GLM 5.3 pass the compliance gate for legal work?
No. No EU guarantee: AWS Bedrock: in EU regions only Global cross-region inference (processing outside the EU possible) Z.ai own API: "We generally provide the Services from Singapore" (privacy policy); no EU contracting party or EU processing. The gate tests a route, not a model name; the sources are on this page.
What does GLM 5.3 cost per task?
Vals computes $2.24 per completed task on the Legal Research Bench [1]. The list price is $1.40 per million input tokens and $4.40 per million output tokens.
How does GLM 5.3 score on legal research?
49.04 percent all-pass on the Vals AI Legal Research Bench, position 10 of 91 measured models, as at 9 November 2026 [1]. That benchmark measures US law; an independent, published benchmark for Dutch legal work does not exist yet.
Related models
Claude and Anthropic, GPT and OpenAI, Gemini and Google, Grok and xAI, Kimi and Moonshot AI, Muse and Meta, Mistral, DeepSeek, GLM and Z.ai, Harvey, Vals AI and Artificial Analysis are trademarks of their respective owners. They are named for identification only and this implies no partnership, sponsorship or endorsement.
Brand marks appear for identification only and imply no partnership, sponsorship or endorsement.