# Z.ai GLM 4.5

Z.ai GLM 4.5 costs $0.60 per million input tokens and $2.20 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 61 benchmarks outside the index have a result below.

Page: https://llmbenchmark.ai/models/glm-4-5
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: $0.60
- Price per million output tokens: $2.20
- Context window: 131K tokens

Benchmark results (61 of 195):

- SWE-bench Verified: 64.2% (source: SWE-bench (swebench.com), read October 21, 2026)
- GPQA Diamond: 72.2% (source: GPQA (Vals AI), read October 21, 2026)
- AIME: 86.7% (source: AIME (Vals AI), read October 21, 2026)
- MMLU Pro: 81.2% (source: MMLU Pro (Vals AI), read October 21, 2026)
- AA Intelligence Index: 12.8 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- Design Arena: websites: 1170 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: UI components: 1144 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: game dev: 1145 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: data viz: 1159 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: 3D: 1170 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: all code categories: 1165 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: SVG: 1096 Elo (source: Design Arena, read October 21, 2026)
- LiveCodeBench (Vals AI): 67.5% (source: Vals AI boards, read October 21, 2026)
- MATH 500 (Vals AI): 94.0% (source: Vals AI boards, read October 21, 2026)
- MGSM (Vals AI): 90.8% (source: Vals AI boards, read October 21, 2026)
- LegalBench (Vals AI): 75.6% (source: Vals AI boards, read October 21, 2026)
- CorpFin (Vals AI): 61.0% (source: Vals AI boards, read October 21, 2026)
- TaxEval (Vals AI): 72.4% (source: Vals AI boards, read October 21, 2026)
- MedQA (Vals AI): 90.0% (source: Vals AI boards, read October 21, 2026)
- AA Math Index: 73.7 (source: Artificial Analysis, read October 21, 2026)
- GPQA Diamond (Artificial Analysis run): 78.2% (source: Artificial Analysis, read October 21, 2026)
- Humanity's Last Exam (Artificial Analysis run): 13.0% (source: Artificial Analysis, read October 21, 2026)
- MMLU Pro (Artificial Analysis run): 83.5% (source: Artificial Analysis, read October 21, 2026)
- LiveCodeBench (Artificial Analysis run): 73.8% (source: Artificial Analysis, read October 21, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 22.0% (source: Artificial Analysis, read October 21, 2026)
- IFBench: 44.1% (source: Artificial Analysis, read October 21, 2026)
- Long context reasoning (AA-LCR): 52.7% (source: Artificial Analysis, read October 21, 2026)
- τ²-Bench Telecom: 43.0% (source: Artificial Analysis, read October 21, 2026)
- AIME 2025 (Artificial Analysis run): 73.7% (source: Artificial Analysis, read October 21, 2026)
- WeirdML: 40.6% (source: Epoch AI benchmarking hub, read October 21, 2026)
- Creative writing (Lech Mazur): 73.4% (source: Epoch AI benchmarking hub, read October 21, 2026)
- ALE-Bench: 344.8 (source: ALE-Bench (Sakana AI), read October 21, 2026)
- LMArena Text: 1430 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: coding: 1434 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts: 1429 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: math: 1427 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: instruction following: 1404 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: creative writing: 1395 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: English: 1437 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: non-English: 1417 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Chinese: 1465 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: German: 1407 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Japanese: 1415 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Korean: 1380 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: French: 1418 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Spanish: 1454 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Russian: 1413 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Polish: 1422 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: multi-turn: 1415 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: longer queries: 1412 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: expert: 1433 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts in English: 1429 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: software and IT: 1440 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: mathematical work: 1430 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: science: 1444 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: medicine and healthcare: 1455 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: legal and government: 1438 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: business and finance: 1420 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: writing and language: 1403 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: entertainment and media: 1404 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- Kagi LLM Benchmark: 57.9% (source: Kagi LLM Benchmarking Project, read October 21, 2026)