# Qwen3.8 27B As of October 21, 2026, Qwen3.8 27B ranks #42 of 213 models overall with 33.7 on the Artificial Analysis Intelligence Index. Its strongest category is coding, where it ranks #3 of 96. Qwen3.8 27B costs $0.04 per million input tokens and $1.35 per million output tokens. It was released on August 14, 2026. Page: https://llmbenchmark.ai/models/qwen3-8-27b Data from October 21, 2026. Every figure below names the board it was read from and the day. - Maker: Qwen - Released: August 14, 2026 - Price per million input tokens: $0.04 - Price per million output tokens: $1.35 - Context window: 1M tokens - Overall rank: 42 of 213, by the Artificial Analysis Intelligence Index - Artificial Analysis Intelligence Index: 33.7 - Vibe Coding Index: 74.2 (from 4 of 6 coding benchmarks) Benchmark results (85 of 190): - LiveBench coding: 86.8% (source: LiveBench, read October 21, 2026) - LMArena WebDev: 1593 Elo (source: LMArena WebDev, read October 21, 2026) - GPQA Diamond: 88.9% (source: GPQA (Vals AI), read October 21, 2026) - MMLU Pro: 84.3% (source: MMLU Pro (Vals AI), read October 21, 2026) - AA Intelligence Index: 33.7 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - AA Coding Index: 68.1 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - AA Agentic Index: 45.8 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - LiveBench reasoning: 80.0% (source: LiveBench, read October 21, 2026) - LiveBench data analysis: 76.6% (source: LiveBench, read October 21, 2026) - LiveBench research: 59.4% (source: LiveBench, read October 21, 2026) - LiveBench browser: 32.0% (source: LiveBench, read October 21, 2026) - LiveBench long agentic: 27.9% (source: LiveBench, read October 21, 2026) - LiveBench design: 75.9% (source: LiveBench, read October 21, 2026) - LiveCodeBench (Vals AI): 84.0% (source: Vals AI boards, read October 21, 2026) - SWE-bench Verified (Vals AI): 86.0% (source: Vals AI boards, read October 21, 2026) - Vibe Code Bench (Vals AI): 64.8% (source: Vals AI boards, read October 21, 2026) - Code migration (Vals AI): 14.2% (source: Vals AI boards, read October 21, 2026) - ProgramBench (Vals AI): 0.0% (source: Vals AI boards, read October 21, 2026) - IOI (Vals AI): 39.1% (source: Vals AI boards, read October 21, 2026) - Terminal-Bench 2.1 (Vals AI): 58.4% (source: Vals AI boards, read October 21, 2026) - SkillsBench (Vals AI): 38.1% (source: Vals AI boards, read October 21, 2026) - CyberBench (Vals AI): 67.8% (source: Vals AI boards, read October 21, 2026) - Finance Agent (Vals AI): 48.5% (source: Vals AI boards, read October 21, 2026) - Tax Agent Bench (Vals AI): 30.9% (source: Vals AI boards, read October 21, 2026) - Legal Research Bench (Vals AI): 36.1% (source: Vals AI boards, read October 21, 2026) - Excel Modeling Benchmark (Vals AI): 59.7% (source: Vals AI boards, read October 21, 2026) - Terminal-Bench-Science (Vals AI): 0.0% (source: Vals AI boards, read October 21, 2026) - MMMU Pro (Vals AI): 83.9% (source: Vals AI boards, read October 21, 2026) - SAGE (Vals AI): 52.4% (source: Vals AI boards, read October 21, 2026) - LegalBench (Vals AI): 82.4% (source: Vals AI boards, read October 21, 2026) - TaxEval (Vals AI): 70.8% (source: Vals AI boards, read October 21, 2026) - MortgageTax (Vals AI): 64.9% (source: Vals AI boards, read October 21, 2026) - MedCode (Vals AI): 28.7% (source: Vals AI boards, read October 21, 2026) - MedScribe (Vals AI): 83.8% (source: Vals AI boards, read October 21, 2026) - GPQA Diamond (Artificial Analysis run): 90.5% (source: Artificial Analysis, read October 21, 2026) - Humanity's Last Exam (Artificial Analysis run): 33.9% (source: Artificial Analysis, read October 21, 2026) - SciCode: 46.6% (source: Artificial Analysis, read October 21, 2026) - Long context reasoning (AA-LCR): 82.0% (source: Artificial Analysis, read October 21, 2026) - APEX-Agents: 47.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI: 87.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI-2: 42.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - ProofBench: 16.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - DTBench: 88.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - LMCA: 41.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - Surface Evolver Bench: 45.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - Epoch Capabilities Index: 151.7 (source: Epoch AI benchmarking hub, read October 21, 2026) - LMArena Text: 1440 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: coding: 1483 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts: 1459 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: math: 1455 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: instruction following: 1436 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: creative writing: 1383 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: 1269 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: English: 1448 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: non-English: 1428 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Chinese: 1501 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: German: 1443 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Japanese: 1387 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Korean: 1384 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: French: 1465 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Spanish: 1449 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Russian: 1415 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Polish: 1439 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: multi-turn: 1440 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: longer queries: 1448 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: expert: 1479 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts in English: 1461 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: software and IT: 1478 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: mathematical work: 1458 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: science: 1467 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: medicine and healthcare: 1437 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: legal and government: 1447 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: business and finance: 1438 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: writing and language: 1405 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: entertainment and media: 1393 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: React: 1602 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: HTML: 1570 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: from an image: 1577 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: English: 1267 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: Chinese: 1326 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: reading text: 1281 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: diagrams: 1285 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: homework: 1295 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: humor: 1235 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: creative writing: 1237 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)