# Z.ai GLM 5.2

As of October 22, 2026, Z.ai GLM 5.2 ranks #33 of 123 models overall with 62.5 ±7.1 on the LLMBenchmark Index. GLM 5.2 ranks #26 of 133 in web design, its strongest category. Z.ai GLM 5.2 costs $1.40 per million input tokens and $4.40 per million output tokens. GLM 5.2 was released on June 16, 2026.

Page: https://llmbenchmark.ai/models/glm-5-2
Data from October 22, 2026. Every figure below names the board it was read from and the day.

- Maker: Z.ai
- Released: June 16, 2026
- Price per million input tokens: $1.40
- Price per million output tokens: $4.40
- Context window: 1.05M tokens
- Overall rank: 33 of 123, by the LLMBenchmark Index
- LLMBenchmark Index: 62.5 ±7.1 (90% margin, from 6 of 7 inputs)
- Artificial Analysis Intelligence Index: 33.7
- Vibe Coding Index: 61.1 (from 4 of 6 coding benchmarks)

Benchmark results (98 of 195):

- LMArena WebDev: 1604 Elo (source: LMArena WebDev, read October 22, 2026)
- GPQA Diamond: 85.6% (source: GPQA (Vals AI), read October 22, 2026)
- MMLU Pro: 86.7% (source: MMLU Pro (Vals AI), read October 22, 2026)
- AA Intelligence Index: 33.7 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Coding Index: 68.8 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Agentic Index: 38.4 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- Design Arena: websites: 1285 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: UI components: 1294 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: game dev: 1268 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: data viz: 1285 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: 3D: 1287 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: all code categories: 1287 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: SVG: 1213 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: ASCII art: 1191 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: agents building web apps: 1222 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: agents building full-stack apps: 1241 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: agents building mobile apps: 1159 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: agents building Android apps: 1178 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: agents building Godot games: 1142 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: agents building games: 1206 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: HTML slides: 1125 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: PowerPoint slides: 1170 Elo (source: Design Arena, read October 22, 2026)
- LiveCodeBench (Vals AI): 69.5% (source: Vals AI boards, read October 22, 2026)
- SWE-bench Verified (Vals AI): 82.8% (source: Vals AI boards, read October 22, 2026)
- Vibe Code Bench (Vals AI): 64.0% (source: Vals AI boards, read October 22, 2026)
- Code migration (Vals AI): 37.9% (source: Vals AI boards, read October 22, 2026)
- ProgramBench (Vals AI): 0.5% (source: Vals AI boards, read October 22, 2026)
- SREBench (Vals AI): 0.0% (source: Vals AI boards, read October 22, 2026)
- Terminal-Bench 2.1 (Vals AI): 67.8% (source: Vals AI boards, read October 22, 2026)
- SkillsBench (Vals AI): 45.1% (source: Vals AI boards, read October 22, 2026)
- Finance Agent (Vals AI): 49.7% (source: Vals AI boards, read October 22, 2026)
- Legal Research Bench (Vals AI): 31.3% (source: Vals AI boards, read October 22, 2026)
- Excel Modeling Benchmark (Vals AI): 61.5% (source: Vals AI boards, read October 22, 2026)
- LegalBench (Vals AI): 84.1% (source: Vals AI boards, read October 22, 2026)
- CorpFin (Vals AI): 66.1% (source: Vals AI boards, read October 22, 2026)
- TaxEval (Vals AI): 73.3% (source: Vals AI boards, read October 22, 2026)
- MedCode (Vals AI): 40.8% (source: Vals AI boards, read October 22, 2026)
- MedScribe (Vals AI): 83.5% (source: Vals AI boards, read October 22, 2026)
- GPQA Diamond (Artificial Analysis run): 89.5% (source: Artificial Analysis, read October 22, 2026)
- Humanity's Last Exam (Artificial Analysis run): 41.1% (source: Artificial Analysis, read October 22, 2026)
- SciCode: 51.2% (source: Artificial Analysis, read October 22, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 50.8% (source: Artificial Analysis, read October 22, 2026)
- IFBench: 73.3% (source: Artificial Analysis, read October 22, 2026)
- Long context reasoning (AA-LCR): 78.3% (source: Artificial Analysis, read October 22, 2026)
- τ²-Bench Telecom: 99.1% (source: Artificial Analysis, read October 22, 2026)
- FrontierCode: 24.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- WeirdML: 70.1% (source: Epoch AI benchmarking hub, read October 22, 2026)
- APEX-Agents: 45.2% (source: Epoch AI benchmarking hub, read October 22, 2026)
- PostTrainBench: 31.7% (source: Epoch AI benchmarking hub, read October 22, 2026)
- GPQA Diamond (Epoch AI run): 91.9% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ARC-AGI: 77.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ARC-AGI-2: 22.8% (source: Epoch AI benchmarking hub, read October 22, 2026)
- SimpleBench: 58.8% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Chess puzzles: 22.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Mystery game puzzles: 19.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- EBR-bench: 9.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- OTIS Mock AIME: 86.4% (source: Epoch AI benchmarking hub, read October 22, 2026)
- FrontierMath, tiers 1 to 3: 59.2% (source: Epoch AI benchmarking hub, read October 22, 2026)
- FrontierMath, tier 4: 29.3% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ProofBench: 35.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- SimpleQA Verified: 34.2% (source: Epoch AI benchmarking hub, read October 22, 2026)
- DTBench: 93.6% (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMCA: 45.8% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Surface Evolver Bench: 55.6% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ALE-Bench: 1047.0 (source: ALE-Bench (Sakana AI), read October 22, 2026)
- Vending-Bench 2: $8,314 (source: Epoch AI benchmarking hub, read October 22, 2026)
- Epoch Capabilities Index: 151.9 (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMArena Text: 1470 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: coding: 1487 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts: 1481 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: math: 1483 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: instruction following: 1466 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: creative writing: 1463 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: English: 1475 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: non-English: 1459 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Chinese: 1522 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: German: 1470 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Japanese: 1450 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Korean: 1440 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: French: 1479 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Spanish: 1478 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Russian: 1468 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Polish: 1456 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: multi-turn: 1469 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: longer queries: 1480 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: expert: 1487 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts in English: 1481 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: software and IT: 1486 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: mathematical work: 1489 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: science: 1489 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: medicine and healthcare: 1475 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: legal and government: 1486 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: business and finance: 1451 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: writing and language: 1463 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: entertainment and media: 1450 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena WebDev: React: 1617 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena WebDev: HTML: 1565 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- Kagi LLM Benchmark: 62.6% (source: Kagi LLM Benchmarking Project, read October 22, 2026)