# Z.ai GLM 5.3 As of October 21, 2026, Z.ai GLM 5.3 ranks #15 of 213 models overall with 44.8 on the Artificial Analysis Intelligence Index. Its strongest category is agentic, where it ranks #5 of 87. Z.ai GLM 5.3 costs $0.079 per million input tokens and $1.40 per million output tokens. It was released on August 18, 2026. Page: https://llmbenchmark.ai/models/glm-5-3 Data from October 21, 2026. Every figure below names the board it was read from and the day. - Maker: Z.ai - Released: August 18, 2026 - Price per million input tokens: $0.079 - Price per million output tokens: $1.40 - Context window: 1.05M tokens - Overall rank: 15 of 213, by the Artificial Analysis Intelligence Index - Artificial Analysis Intelligence Index: 44.8 - Vibe Coding Index: 73.1 (from 2 of 4 coding benchmarks) Benchmark results (100 of 190): - LiveBench coding: 82.8% (source: LiveBench, read October 21, 2026) - LMArena WebDev: 1621 Elo (source: LMArena WebDev, read October 21, 2026) - Vals Index: 59.7% (source: Vals Index, read October 21, 2026) - GPQA Diamond: 88.1% (source: GPQA (Vals AI), read October 21, 2026) - MMLU Pro: 86.8% (source: MMLU Pro (Vals AI), read October 21, 2026) - AA Intelligence Index: 44.8 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - AA Coding Index: 74.8 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - AA Agentic Index: 53.1 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - Design Arena: websites: 1295 Elo (source: Design Arena, read October 21, 2026) - Design Arena: UI components: 1314 Elo (source: Design Arena, read October 21, 2026) - Design Arena: game dev: 1311 Elo (source: Design Arena, read October 21, 2026) - Design Arena: data viz: 1260 Elo (source: Design Arena, read October 21, 2026) - Design Arena: 3D: 1332 Elo (source: Design Arena, read October 21, 2026) - Design Arena: all code categories: 1304 Elo (source: Design Arena, read October 21, 2026) - Design Arena: SVG: 1292 Elo (source: Design Arena, read October 21, 2026) - Design Arena: ASCII art: 1213 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building mobile apps: 1194 Elo (source: Design Arena, read October 21, 2026) - Design Arena: HTML slides: 1189 Elo (source: Design Arena, read October 21, 2026) - Design Arena: PowerPoint slides: 1255 Elo (source: Design Arena, read October 21, 2026) - LiveBench reasoning: 85.8% (source: LiveBench, read October 21, 2026) - LiveBench data analysis: 70.2% (source: LiveBench, read October 21, 2026) - LiveBench research: 73.2% (source: LiveBench, read October 21, 2026) - LiveBench browser: 0.0% (source: LiveBench, read October 21, 2026) - LiveBench long agentic: 35.9% (source: LiveBench, read October 21, 2026) - LiveBench design: 77.3% (source: LiveBench, read October 21, 2026) - LiveCodeBench (Vals AI): 80.5% (source: Vals AI boards, read October 21, 2026) - SWE-bench Verified (Vals AI): 95.4% (source: Vals AI boards, read October 21, 2026) - Terminal-Bench 4 (Vals AI): 38.9% (source: Vals AI boards, read October 21, 2026) - Vibe Code Bench (Vals AI): 78.1% (source: Vals AI boards, read October 21, 2026) - Code migration (Vals AI): 44.2% (source: Vals AI boards, read October 21, 2026) - ProgramBench (Vals AI): 1.5% (source: Vals AI boards, read October 21, 2026) - SREBench (Vals AI): 9.2% (source: Vals AI boards, read October 21, 2026) - IOI (Vals AI): 68.4% (source: Vals AI boards, read October 21, 2026) - Terminal-Bench 2.1 (Vals AI): 71.5% (source: Vals AI boards, read October 21, 2026) - Vibe Code Bench 1-100 (Vals AI): 20.0% (source: Vals AI boards, read October 21, 2026) - SkillsBench (Vals AI): 47.5% (source: Vals AI boards, read October 21, 2026) - CyberBench (Vals AI): 72.1% (source: Vals AI boards, read October 21, 2026) - Finance Agent (Vals AI): 55.8% (source: Vals AI boards, read October 21, 2026) - Tax Agent Bench (Vals AI): 39.7% (source: Vals AI boards, read October 21, 2026) - Legal Research Bench (Vals AI): 49.0% (source: Vals AI boards, read October 21, 2026) - Harvey's Legal Agent Benchmark (Vals AI): 14.6% (source: Vals AI boards, read October 21, 2026) - Excel Modeling Benchmark (Vals AI): 56.3% (source: Vals AI boards, read October 21, 2026) - Terminal-Bench-Science (Vals AI): 5.7% (source: Vals AI boards, read October 21, 2026) - Public Benefits Bench (Vals AI): 68.5% (source: Vals AI boards, read October 21, 2026) - MysteryMechanism (Vals AI): 23.0% (source: Vals AI boards, read October 21, 2026) - LegalBench (Vals AI): 84.8% (source: Vals AI boards, read October 21, 2026) - TaxEval (Vals AI): 72.4% (source: Vals AI boards, read October 21, 2026) - MedCode (Vals AI): 42.9% (source: Vals AI boards, read October 21, 2026) - MedScribe (Vals AI): 88.8% (source: Vals AI boards, read October 21, 2026) - GPQA Diamond (Artificial Analysis run): 91.7% (source: Artificial Analysis, read October 21, 2026) - Humanity's Last Exam (Artificial Analysis run): 42.3% (source: Artificial Analysis, read October 21, 2026) - SciCode: 59.0% (source: Artificial Analysis, read October 21, 2026) - Long context reasoning (AA-LCR): 79.7% (source: Artificial Analysis, read October 21, 2026) - FrontierCode: 40.1% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierSWE: 30.2% (source: Epoch AI benchmarking hub, read October 21, 2026) - WeirdML: 75.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - APEX-Agents: 56.6% (source: Epoch AI benchmarking hub, read October 21, 2026) - GPQA Diamond (Epoch AI run): 90.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - Chess puzzles: 37.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - Mystery game puzzles: 33.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - OTIS Mock AIME: 91.1% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierMath, tiers 1 to 3: 68.8% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierMath, tier 4: 29.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - ProofBench: 49.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - SimpleQA Verified: 41.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - DTBench: 87.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - LMCA: 55.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - ALE-Bench: 1317.4 (source: ALE-Bench (Sakana AI), read October 21, 2026) - Vending-Bench 2: $8,164 (source: Epoch AI benchmarking hub, read October 21, 2026) - Epoch Capabilities Index: 156.0 (source: Epoch AI benchmarking hub, read October 21, 2026) - LMArena Text: 1474 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: coding: 1497 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts: 1490 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: math: 1495 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: instruction following: 1479 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: creative writing: 1458 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: English: 1482 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: non-English: 1459 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Chinese: 1532 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: German: 1488 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Japanese: 1460 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Korean: 1460 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: French: 1503 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Spanish: 1462 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Russian: 1469 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Polish: 1466 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: multi-turn: 1472 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: longer queries: 1483 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: expert: 1514 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts in English: 1496 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: software and IT: 1493 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: mathematical work: 1497 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: science: 1498 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: medicine and healthcare: 1481 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: legal and government: 1473 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: business and finance: 1459 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: writing and language: 1469 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: entertainment and media: 1447 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: React: 1641 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: HTML: 1595 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)