# Z.ai GLM 5

As of October 21, 2026, Z.ai GLM 5 ranks #59 of 123 models overall with 54.3 ±11.4 on the LLMBenchmark Index. GLM 5 ranks #52 of 133 in web design, its strongest category. Z.ai GLM 5 costs $1.00 per million input tokens and $3.20 per million output tokens. GLM 5 was released on February 11, 2026.

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

- Maker: Z.ai
- Released: February 11, 2026
- Price per million input tokens: $1.00
- Price per million output tokens: $3.20
- Context window: 205K tokens
- Overall rank: 59 of 123, by the LLMBenchmark Index
- LLMBenchmark Index: 54.3 ±11.4 (90% margin, from 5 of 7 inputs)
- Artificial Analysis Intelligence Index: 27.9
- Vibe Coding Index: 41.7 (from 3 of 6 coding benchmarks)

Benchmark results (76 of 195):

- SWE-bench Verified: 72.8% (source: SWE-bench (swebench.com), read October 21, 2026)
- SWE-bench Multilingual: 69.7% (source: SWE-bench (swebench.com), read October 21, 2026)
- LMArena WebDev: 1435 Elo (source: LMArena WebDev, read October 21, 2026)
- GPQA Diamond: 83.3% (source: GPQA (Vals AI), read October 21, 2026)
- AIME: 91.7% (source: AIME (Vals AI), read October 21, 2026)
- MMLU Pro: 86.0% (source: MMLU Pro (Vals AI), read October 21, 2026)
- AA Intelligence Index: 27.9 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- Design Arena: websites: 1247 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: UI components: 1230 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: game dev: 1234 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: data viz: 1228 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: 3D: 1229 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: all code categories: 1246 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: SVG: 1168 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: ASCII art: 1147 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: agents building full-stack apps: 1123 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: agents building mobile apps: 1136 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: agents building Android apps: 1146 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: agents building Godot games: 1144 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: HTML slides: 1148 Elo (source: Design Arena, read October 21, 2026)
- LiveCodeBench (Vals AI): 81.9% (source: Vals AI boards, read October 21, 2026)
- SWE-bench Verified (Vals AI): 71.4% (source: Vals AI boards, read October 21, 2026)
- Vibe Code Bench (Vals AI): 23.4% (source: Vals AI boards, read October 21, 2026)
- LegalBench (Vals AI): 84.1% (source: Vals AI boards, read October 21, 2026)
- CaseLaw (Vals AI): 52.5% (source: Vals AI boards, read October 21, 2026)
- CorpFin (Vals AI): 62.9% (source: Vals AI boards, read October 21, 2026)
- TaxEval (Vals AI): 70.0% (source: Vals AI boards, read October 21, 2026)
- MedQA (Vals AI): 94.3% (source: Vals AI boards, read October 21, 2026)
- GPQA Diamond (Artificial Analysis run): 82.0% (source: Artificial Analysis, read October 21, 2026)
- Humanity's Last Exam (Artificial Analysis run): 29.3% (source: Artificial Analysis, read October 21, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 43.2% (source: Artificial Analysis, read October 21, 2026)
- IFBench: 72.3% (source: Artificial Analysis, read October 21, 2026)
- Long context reasoning (AA-LCR): 75.7% (source: Artificial Analysis, read October 21, 2026)
- τ²-Bench Telecom: 98.2% (source: Artificial Analysis, read October 21, 2026)
- Terminal-Bench: 52.4% (source: Epoch AI benchmarking hub, read October 21, 2026)
- WeirdML: 48.2% (source: Epoch AI benchmarking hub, read October 21, 2026)
- GPQA Diamond (Epoch AI run): 87.8% (source: Epoch AI benchmarking hub, read October 21, 2026)
- ARC-AGI: 44.7% (source: Epoch AI benchmarking hub, read October 21, 2026)
- ARC-AGI-2: 4.9% (source: Epoch AI benchmarking hub, read October 21, 2026)
- SimpleBench: 53.2% (source: Epoch AI benchmarking hub, read October 21, 2026)
- OTIS Mock AIME: 80.0% (source: Epoch AI benchmarking hub, read October 21, 2026)
- CL-bench: 18.7% (source: Epoch AI benchmarking hub, read October 21, 2026)
- ALE-Bench: 765.6 (source: ALE-Bench (Sakana AI), read October 21, 2026)
- Vending-Bench 2: $4,432 (source: Epoch AI benchmarking hub, read October 21, 2026)
- Epoch Capabilities Index: 145.8 (source: Epoch AI benchmarking hub, read October 21, 2026)
- LMArena Text: 1446 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: coding: 1461 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts: 1452 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: math: 1440 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: instruction following: 1428 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: creative writing: 1438 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: English: 1458 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: non-English: 1430 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Chinese: 1511 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: German: 1447 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Japanese: 1416 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Korean: 1423 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: French: 1456 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: 1436 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Polish: 1434 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: multi-turn: 1456 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: longer queries: 1446 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: expert: 1454 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts in English: 1460 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: software and IT: 1460 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: mathematical work: 1451 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: science: 1460 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: 1453 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: business and finance: 1430 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: writing and language: 1437 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: entertainment and media: 1426 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena WebDev: React: 1424 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena WebDev: HTML: 1450 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- Kagi LLM Benchmark: 75.0% (source: Kagi LLM Benchmarking Project, read October 21, 2026)