# Z.ai GLM 4.5 Air

Z.ai GLM 4.5 Air costs $0.20 per million input tokens and $1.10 per million output tokens, as of October 21, 2026. None of the 6 coding benchmarks behind the index has measured it, so it has no coding index, but 48 benchmarks outside the index have a result below.

Page: https://llmbenchmark.ai/models/glm-4-5-air
Data from October 21, 2026. Every figure below names the board it was read from and the day.

- Maker: Z.ai
- Released: July 25, 2025
- Price per million input tokens: $0.20
- Price per million output tokens: $1.10
- Context window: 131K tokens

Benchmark results (48 of 195):

- AA Intelligence Index: 11.1 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- Design Arena: websites: 1146 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: UI components: 1123 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: game dev: 1094 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: data viz: 1186 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: 3D: 1123 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: all code categories: 1137 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: SVG: 1071 Elo (source: Design Arena, read October 21, 2026)
- AA Math Index: 80.7 (source: Artificial Analysis, read October 21, 2026)
- GPQA Diamond (Artificial Analysis run): 73.3% (source: Artificial Analysis, read October 21, 2026)
- Humanity's Last Exam (Artificial Analysis run): 7.0% (source: Artificial Analysis, read October 21, 2026)
- MMLU Pro (Artificial Analysis run): 81.5% (source: Artificial Analysis, read October 21, 2026)
- LiveCodeBench (Artificial Analysis run): 68.4% (source: Artificial Analysis, read October 21, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 20.5% (source: Artificial Analysis, read October 21, 2026)
- IFBench: 37.6% (source: Artificial Analysis, read October 21, 2026)
- Long context reasoning (AA-LCR): 46.7% (source: Artificial Analysis, read October 21, 2026)
- τ²-Bench Telecom: 46.5% (source: Artificial Analysis, read October 21, 2026)
- AIME 2025 (Artificial Analysis run): 80.7% (source: Artificial Analysis, read October 21, 2026)
- GSO-Bench: 2.9% (source: Epoch AI benchmarking hub, read October 21, 2026)
- LMArena Text: 1384 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: coding: 1397 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts: 1379 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: math: 1396 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: instruction following: 1354 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: creative writing: 1343 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: English: 1397 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: non-English: 1366 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Chinese: 1426 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: German: 1377 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Japanese: 1348 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Korean: 1308 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: French: 1400 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Spanish: 1385 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Russian: 1373 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Polish: 1368 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: multi-turn: 1371 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: longer queries: 1366 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: expert: 1370 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts in English: 1388 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: software and IT: 1401 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: mathematical work: 1396 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: science: 1407 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: medicine and healthcare: 1402 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: legal and government: 1382 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: business and finance: 1371 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: writing and language: 1354 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: entertainment and media: 1339 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- Kagi LLM Benchmark: 43.0% (source: Kagi LLM Benchmarking Project, read October 21, 2026)