# Z.ai GLM 4.7 As of October 21, 2026, Z.ai GLM 4.7 ranks #49 of 123 models overall with 56.9 ±10.2 on the LLMBenchmark Index. GLM 4.7 ranks #40 of 108 in math, its strongest category. Z.ai GLM 4.7 costs $0.60 per million input tokens and $2.20 per million output tokens. GLM 4.7 was released on December 22, 2025. Page: https://llmbenchmark.ai/models/glm-4-7 Data from October 21, 2026. Every figure below names the board it was read from and the day. - Maker: Z.ai - Released: December 22, 2025 - Price per million input tokens: $0.60 - Price per million output tokens: $2.20 - Context window: 205K tokens - Overall rank: 49 of 123, by the LLMBenchmark Index - LLMBenchmark Index: 56.9 ±10.2 (90% margin, from 6 of 7 inputs) - Artificial Analysis Intelligence Index: 22.2 - Vibe Coding Index: 55.1 (from 2 of 6 coding benchmarks) Benchmark results (81 of 195): - LMArena WebDev: 1435 Elo (source: LMArena WebDev, read October 21, 2026) - GPQA Diamond: 80.0% (source: GPQA (Vals AI), read October 21, 2026) - AIME: 93.3% (source: AIME (Vals AI), read October 21, 2026) - MMLU Pro: 82.7% (source: MMLU Pro (Vals AI), read October 21, 2026) - AA Intelligence Index: 22.2 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - AA Coding Index: 45.3 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - Design Arena: websites: 1226 Elo (source: Design Arena, read October 21, 2026) - Design Arena: UI components: 1199 Elo (source: Design Arena, read October 21, 2026) - Design Arena: game dev: 1189 Elo (source: Design Arena, read October 21, 2026) - Design Arena: data viz: 1195 Elo (source: Design Arena, read October 21, 2026) - Design Arena: 3D: 1191 Elo (source: Design Arena, read October 21, 2026) - Design Arena: all code categories: 1217 Elo (source: Design Arena, read October 21, 2026) - Design Arena: SVG: 1143 Elo (source: Design Arena, read October 21, 2026) - Design Arena: ASCII art: 1165 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building full-stack apps: 1050 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building mobile apps: 1105 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building Android apps: 1112 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building Godot games: 1058 Elo (source: Design Arena, read October 21, 2026) - LiveCodeBench (Vals AI): 82.2% (source: Vals AI boards, read October 21, 2026) - SWE-bench Verified (Vals AI): 69.4% (source: Vals AI boards, read October 21, 2026) - MGSM (Vals AI): 88.2% (source: Vals AI boards, read October 21, 2026) - LegalBench (Vals AI): 83.4% (source: Vals AI boards, read October 21, 2026) - CaseLaw (Vals AI): 54.9% (source: Vals AI boards, read October 21, 2026) - CorpFin (Vals AI): 46.4% (source: Vals AI boards, read October 21, 2026) - TaxEval (Vals AI): 68.8% (source: Vals AI boards, read October 21, 2026) - MedQA (Vals AI): 93.7% (source: Vals AI boards, read October 21, 2026) - MedCode (Vals AI): 32.8% (source: Vals AI boards, read October 21, 2026) - MedScribe (Vals AI): 68.6% (source: Vals AI boards, read October 21, 2026) - AA Math Index: 95.0 (source: Artificial Analysis, read October 21, 2026) - GPQA Diamond (Artificial Analysis run): 85.9% (source: Artificial Analysis, read October 21, 2026) - Humanity's Last Exam (Artificial Analysis run): 27.4% (source: Artificial Analysis, read October 21, 2026) - MMLU Pro (Artificial Analysis run): 85.6% (source: Artificial Analysis, read October 21, 2026) - LiveCodeBench (Artificial Analysis run): 89.4% (source: Artificial Analysis, read October 21, 2026) - Terminal-Bench Hard (Artificial Analysis run): 31.8% (source: Artificial Analysis, read October 21, 2026) - IFBench: 67.9% (source: Artificial Analysis, read October 21, 2026) - Long context reasoning (AA-LCR): 71.0% (source: Artificial Analysis, read October 21, 2026) - τ²-Bench Telecom: 95.9% (source: Artificial Analysis, read October 21, 2026) - AIME 2025 (Artificial Analysis run): 95.0% (source: Artificial Analysis, read October 21, 2026) - Terminal-Bench: 33.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - GPQA Diamond (Epoch AI run): 83.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - SimpleBench: 47.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - Chess puzzles: 21.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - OTIS Mock AIME: 83.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - ProofBench: 6.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - SimpleQA Verified: 32.2% (source: Epoch AI benchmarking hub, read October 21, 2026) - CL-bench: 15.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - CL-bench Life: 10.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - ALE-Bench: 399.5 (source: ALE-Bench (Sakana AI), read October 21, 2026) - Vending-Bench 2: $2,377 (source: Epoch AI benchmarking hub, read October 21, 2026) - Epoch Capabilities Index: 143.6 (source: Epoch AI benchmarking hub, read October 21, 2026) - LMArena Text: 1435 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: coding: 1454 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts: 1443 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: math: 1424 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: instruction following: 1412 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: creative writing: 1401 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: English: 1453 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: 1495 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: German: 1426 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Japanese: 1439 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Korean: 1399 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: French: 1432 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Spanish: 1434 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Russian: 1423 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Polish: 1435 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: multi-turn: 1446 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: longer queries: 1432 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: expert: 1424 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts in English: 1452 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: software and IT: 1453 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: mathematical work: 1411 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: science: 1457 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: medicine and healthcare: 1469 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: legal and government: 1444 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: business and finance: 1429 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: writing and language: 1411 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: entertainment and media: 1400 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: React: 1420 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: HTML: 1447 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - BrowseComp-Plus: 64.7% (source: BrowseComp-Plus, read October 21, 2026)