VERIFIEDOct 142026
Is GLM 4.5 Air state of the art?
Yes.Yes on Math (best per dollar). Not the overall leader.
As of Oct 14, 2026, GLM 4.5 Air from Zhipu AI. Yes on Math (best per dollar). Not the overall leader. Ranked #30 in Math.
General LLMNot SOTA · #141#141 · 0dGeneral LLM · paretoNot SOTA · #183#183 · 0dReasoningNot SOTA · #140#140 · 0dReasoning · paretoNot SOTA · #182#182 · 0dMathNot SOTA · #30#30 · 0dMath · paretoPareto#30 · 0dCodingNot SOTA · #137#137 · 0dLong contextNot SOTA · #137#137 · 0dLong context · paretoNot SOTA · #179#179 · 0dFactualityNot SOTA · #109#109 · 0d
Why
The ruling, in plain English
Ranked #141 in General LLM.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text (style-controlled, overall) glm-4.5-air | 1373.118763406586 1368.9–1377.4 | 2026-10-08 | INDEP. | snap_368d64825bf4 |
| LMArena Text (style-controlled, hard prompts) glm-4.5-air | 1390.8051502779456 1385.3–1396.3 | 2026-10-08 | INDEP. | snap_368d64825bf4 |
| Humanity's Last Exam GLM-4.5-Air | 0.0812 0.1–0.1 | 2025-07-20 | INDEP. | snap_fee7890b5dd0 |
| LMArena Text (style-controlled, coding) glm-4.5-air | 1426.8896817255625 1419.2–1434.6 | 2026-10-08 | INDEP. | snap_368d64825bf4 |
| LMArena Text (style-controlled, longer query) glm-4.5-air | 1379.6066044071754 1372.1–1387.1 | 2026-10-08 | INDEP. | snap_368d64825bf4 |
| LMArena Text factuality glm-4.5-air | 1394.2166395465438 1387.4–1401.0 | 2026-10-08 | INDEP. | snap_f051faf18005 |
Reign history
Where it sits in the succession
No closed or open crown interval includes this model.
Honest about the gaps
Where it is not the crown
| Category | This model | Why |
|---|---|---|
| General LLM | Not SOTA · #141 | Ranked #141 in General LLM. |
| Reasoning | Not SOTA · #140 | Ranked #140 in Reasoning. |
| Math | Not SOTA · #30 | Ranked #30 in Math. |
| Coding | Not SOTA · #137 | Ranked #137 in Coding. |
| Long context | Not SOTA · #137 | Ranked #137 in Long context. |
| Factuality | Not SOTA · #109 | Ranked #109 in Factuality. |