models · Zhipu AI
Catalogued from llm-stats Open LLM Leaderboard at Quarantine — unverified, pending attestation.
| Method | closed-weights |
|---|
| Publisher | Zhipu AI |
|---|---|
| Origin | Recorded as a covered nation under 10 U.S.C. § 4872(f) — the PRC, Russia, Iran or North Korea. The registry did not record which. |
| Licence | unknown |
| Context window | 202,752 tokens |
| Modality | text+image+video->text |
| Pulls recorded here | 6 |
| GPQA Diamond | 80.9 |
|---|---|
| IFBench | 61.1 |
| Humanity's Last Exam | 17.1 |
Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.
Registry record as of 2026-09-28. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.