Source record

GLM-5.2 — official Z.ai Hugging Face model card

Source-specific extraction of GLM-5.2 Model Card. Findings and measurements retain their original attribution.

Original source and provenance ↓ · Assessment record →

Scope and attribution

Reported by: Z.ai
Actual evaluator: Not established for every observation
Captured version: 2026-10-26
Source identity: 75f1d77e20e78286

Source transcription is not experimental replication. Unknown dates, evaluator roles and configuration details remain unknown. Source groups are not verified rankings.

Source findings

The following statements summarize the source. They are not independent NUWA experimental findings.

The complete model card is a capability and usage card with benchmark methods; it contains no dedicated safety benchmark results or frontier-risk conclusions.

README.md:1-108

Bounded to this model card and captured official page; absence here is not evidence that Z.ai has never evaluated safety.

The developer positions GLM-5.2 for long-horizon tasks, larger context and flexible coding effort.

README.md:31-37

Developer positioning only; not a validated autonomy risk finding.

NL2Repo evaluation describes rule-based and LLM-based checks against benchmark hacking.

README.md:83

No evasion rate, failure count or effectiveness measurement disclosed; not a measured model safety safeguard.

DeepSWE and ProgramBench methods describe isolated execution with internet access disabled; software benchmark resource and time budgets vary.

README.md:84-87

Controls apply to benchmark execution, not evidence of product-level misuse prevention.

The card attributes FrontierSWE to Proximal, PostTrainBench to PostTrainBench, and SWE-Marathon to Abundant AI.

README.md:90-92

These are reused externally conducted results; the card does not disclose exact model checkpoints.

The official rendered page contains a separate Agents Last Exam evaluation entry described as a leaderboard export rather than an HF-verified evaluation.

model-card-page.txt:639-645

Platform widget is separate from pinned developer README; no additional numeric observation is inherited from it.

Extraction coverage

Each entry records the treatment of the source section. A reviewed observation does not imply that every claim or result in the document was verified.

View 16 coverage entries

Section	Treatment	Location and scope
Card metadata / source identity	extracted	README.md:1-29; model-api.json $.id, $.author, $.sha, $.createdAt, $.lastModifiedOfficial zai-org repository. API SHA and raw response X-Repo-Commit agree. Repository creation/modification timestamps are not asserted as card publication/revision dates.
Introduction	qualitative	README.md:31-39Developer describes long-horizon capability, context capacity, coding and open licensing. These are not safety evaluation results. Architecture efficiency numbers are outside this bounded risk extraction.
Benchmark: Reasoning	not-relevant	README.md:45-53Generic reasoning/math/science scores; no dedicated dangerous-capability or safety evaluation is identified. No subject-task content or numerical biology comparisons extracted.
Benchmark: Coding	extracted	README.md:54-63;82-87;90-92Exact GLM-5.2 entries retained only as general software/long-horizon capability context; no inference to cyber offense, self-improvement, loss of control, or risk thresholds. Comparative model columns omitted.
Benchmark: Agentic	extracted	README.md:64-66;88-89Exact GLM-5.2 tool-use scores retained as capability context, not an autonomy risk result.
Serve GLM-5.2 Locally	not-relevant	README.md:68-77Framework compatibility / deployment links do not disclose safety testing; no setup commands executed.
Footnote	extracted	README.md:79-92Relevant harnesses, budgets, trial count, external evaluator attribution, public task count and high-level evaluation controls recorded. The NL2Repo anti-hacking measure has no measured failure rate.
Citation	qualitative	README.md:94-108References GLM-5 technical report (2602.15763); it is not a GLM-5.2 safety report. Linked sources are dependencies, not extracted or inherited evidence.
Hugging Face Evaluation results widget	not-relevant	model-card-page.txt:614-648; model-card-page.html Evaluation resultsPage includes platform evaluation entries including an Agents Last Exam leaderboard export expressly not HF-verified. Those are outside developer README and are not treated as developer risk results; duplicates of card scores are not added.
Dedicated safety evaluation	not-disclosed	Entire pinned README.md:1-108; official page model-card bodyNo safety benchmark, refusal/harmlessness result, jailbreak rate, or adversarial safety result is disclosed in this card.
Frontier risk policy / thresholds / deployment decision	not-disclosed	Entire pinned README.md:1-108; official page model-card bodyNo frontier-risk taxonomy, capability threshold, risk tier, safety case or deployment approval conclusion is disclosed.
CBRN / biological / chemical / nuclear risk	not-disclosed	Entire pinned README.md:1-108; official page model-card bodyNo dedicated CBRN dangerous-capability assessment, uplift study, or mitigation evidence is disclosed. No dangerous task content or comparisons extracted.
Cybersecurity dangerous capability	not-disclosed	Entire pinned README.md:1-108; official page model-card bodyNo offensive cyber capability or vulnerability exploitation safety assessment is disclosed. Generic coding results do not establish cyber-risk capability.
Autonomy / self-improvement / control	not-disclosed	Entire pinned README.md:1-108; official page model-card bodyNo escape, replication, persistence, resource acquisition, autonomous R&D risk threshold, or loss-of-control assessment is disclosed.
Deception / scheming / manipulation / oversight	not-disclosed	Entire pinned README.md:1-108; official page model-card bodyNo deceptive alignment, scheming, persuasion risk, sandbagging, oversight integrity, or situational-awareness evaluation is disclosed.
Product safeguards and monitoring	not-disclosed	Entire pinned README.md:1-108; official page model-card bodyNo measured product safeguards, red-team safety outcomes, post-release incident monitoring or residual-risk assessment is disclosed. Benchmark sandboxing and anti-hacking controls are narrower evaluation methods.

Unresolved source issues

This official model card discloses capability benchmarks and usage information but no dedicated safety evaluation, frontier-risk classification or deployment safety conclusion. This disclosure gap is limited to the reviewed card.

Software benchmark sandboxing and anti-hacking checks describe evaluation controls without measured product safeguard effectiveness. Externally conducted benchmark entries and a platform leaderboard widget retain their separate provenance.

Version fingerprints

document

https://huggingface.co/zai-org/GLM-5.2/raw/cf457fa734ab149ffef225f80893eb38c6ff5cdc/README.md

7ba22185651d8f69fbf6227ee718eb680fd834ec8e79ba78df6fa54896614b3d

document

https://huggingface.co/zai-org/GLM-5.2

fce38778229b2fe8d443d5af4cb0ae56ca644ada69b05f5f2b373009f5328b80

data

https://huggingface.co/api/models/zai-org/GLM-5.2

064e59e4acce4f697ea7f67ebd8aeff954cba9598ea0aaef5708429a629356e4

renderer

https://huggingface.co/zai-org/GLM-5.2

73eb98c1a6282cddb11fc787cf915d42310da6ab164807ca4fbf6dd8cd0ed932

References

[1] GLM-5.2 Model Card