Model card
GLM-4.5-Air.
Zhipu AIopen-source
§ 02 · Benchmarks
Every benchmark GLM-4.5-Air has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | AIME 2024 | Reasoning · Mathematical Reasoning | accuracy | 89.4% | #4 | — | source ↗ |
| 02 | LiveCodeBench | Computer Code · Code Generation | pass-1 | 70.7% | #15 | — | source ↗ |
| 03 | BrowseComp | Natural Language Processing · Question Answering | accuracy | 21.3% | #16 | — | source ↗ |
| 04 | SWE-Bench Verified | Computer Code · Code Generation | accuracy | 57.6% | #21 | — | source ↗ |
| 05 | GPQA Diamond | Reasoning · Multi-step Reasoning | accuracy | 75.0% | #38 | — | source ↗ |
| 06 | HLE | Reasoning · Multi-step Reasoning | accuracy | 10.6% | #52 | — | source ↗ |
| 07 | PLCC | Natural Language Processing · Polish Cultural Competency | art-and-entertainment | 48.0% | #93 | — | source ↗ |
| 08 | PLCC | Natural Language Processing · Polish Cultural Competency | vocabulary | 47.0% | #96 | — | source ↗ |
| 09 | PLCC | Natural Language Processing · Polish Cultural Competency | average | 54.7% | #104 | — | source ↗ |
| 10 | PLCC | Natural Language Processing · Polish Cultural Competency | grammar | 52.0% | #105 | — | source ↗ |
| 11 | PLCC | Natural Language Processing · Polish Cultural Competency | geography | 64.0% | #105 | — | source ↗ |
| 12 | PLCC | Natural Language Processing · Polish Cultural Competency | history | 66.0% | #107 | — | source ↗ |
| 13 | PLCC | Natural Language Processing · Polish Cultural Competency | culture-and-tradition | 51.0% | #108 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where GLM-4.5-Air actually performs.
§ 04 · Papers
1 paper with results for GLM-4.5-Air.
- 2025-08-08· 6 results
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
§ 05 · Related models
Other Zhipu AI models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
sdadas/PLCC
7
results
pwc-dump
6
results
7 of 13 rows marked verified.