# Qwen3.5 397B A17B As of October 21, 2026, Qwen3.5 397B A17B ranks #48 of 123 models overall with 57.1 ±13.8 on the LLMBenchmark Index. Qwen3.5 397B A17B ranks #54 of 122 in reasoning, its strongest category. Qwen3.5 397B A17B costs $0.39 per million input tokens and $2.34 per million output tokens. Qwen3.5 397B A17B was released on February 16, 2026. Page: https://llmbenchmark.ai/models/qwen3-5-397b-a17b Data from October 21, 2026. Every figure below names the board it was read from and the day. - Maker: Qwen - Released: February 16, 2026 - Price per million input tokens: $0.39 - Price per million output tokens: $2.34 - Context window: 262K tokens - Overall rank: 48 of 123, by the LLMBenchmark Index - LLMBenchmark Index: 57.1 ±13.8 (90% margin, from 4 of 7 inputs) - Artificial Analysis Intelligence Index: 21.4 - Vibe Coding Index: not enough data (one index benchmark; at least two are needed to rank) Benchmark results (65 of 195): - LMArena WebDev: 1400 Elo (source: LMArena WebDev, read October 21, 2026) - AA Intelligence Index: 21.4 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - Design Arena: websites: 1191 Elo (source: Design Arena, read October 21, 2026) - Design Arena: UI components: 1163 Elo (source: Design Arena, read October 21, 2026) - Design Arena: game dev: 1140 Elo (source: Design Arena, read October 21, 2026) - Design Arena: data viz: 1175 Elo (source: Design Arena, read October 21, 2026) - Design Arena: 3D: 1161 Elo (source: Design Arena, read October 21, 2026) - Design Arena: all code categories: 1180 Elo (source: Design Arena, read October 21, 2026) - Design Arena: SVG: 1140 Elo (source: Design Arena, read October 21, 2026) - GPQA Diamond (Artificial Analysis run): 89.3% (source: Artificial Analysis, read October 21, 2026) - Humanity's Last Exam (Artificial Analysis run): 29.0% (source: Artificial Analysis, read October 21, 2026) - SciCode: 44.8% (source: Artificial Analysis, read October 21, 2026) - Terminal-Bench Hard (Artificial Analysis run): 40.9% (source: Artificial Analysis, read October 21, 2026) - IFBench: 78.8% (source: Artificial Analysis, read October 21, 2026) - Long context reasoning (AA-LCR): 77.3% (source: Artificial Analysis, read October 21, 2026) - τ²-Bench Telecom: 95.6% (source: Artificial Analysis, read October 21, 2026) - APEX-Agents: 24.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - GPQA Diamond (Epoch AI run): 86.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - Mystery game puzzles: 18.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - OTIS Mock AIME: 88.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierMath, tiers 1 to 3: 31.2% (source: Epoch AI benchmarking hub, read October 21, 2026) - DTBench: 87.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - LMCA: 37.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - ALE-Bench: 621.9 (source: ALE-Bench (Sakana AI), read October 21, 2026) - Epoch Capabilities Index: 146.8 (source: Epoch AI benchmarking hub, read October 21, 2026) - LMArena Text: 1437 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: coding: 1464 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts: 1448 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: math: 1453 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: instruction following: 1424 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: creative writing: 1402 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: 1262 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: English: 1443 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: 1498 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: German: 1445 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Japanese: 1429 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: 1462 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Spanish: 1441 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Russian: 1430 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Polish: 1447 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: 1441 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: expert: 1462 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts in English: 1450 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: software and IT: 1463 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: mathematical work: 1454 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: 1455 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: legal and government: 1441 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: business and finance: 1435 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: writing and language: 1415 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: entertainment and media: 1399 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: React: 1388 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: HTML: 1410 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: English: 1268 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: Chinese: 1314 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: reading text: 1271 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: diagrams: 1277 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: homework: 1292 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: humor: 1262 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: captioning: 1230 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: recognizing things: 1265 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: creative writing: 1260 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)