Qwen3.8-27B
Qwen3.8-27B is an open-weights AI model from Alibaba with an index score of 155 (GPT-4 = 100), rank 59 of 217.
155139–171Index score#59 of 217 models
$0.060/ $2.2Price per million tokensinput / output · via OpenRouter
1.02MContext windowtokens it reads at once
14 Aug 2026Released3 months ago
Where it sitson the frontier
Gemini 3 Pro reached this score 9 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workevidence
Novel problemsevidence
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 10 leaderboards
The Model Indexthird-party tests, our method#59of 217 · 155
LMArena · Mathsmaths questions in chat#66of 346 · 1451LMArena · Codingcoding questions in chat#77of 357 · 1496Epoch Capabilities Indexoverall capability from many benchmarks#57of 231 · 152.7LMArena · Textoverall chat quality, judged by people#91of 362 · 1434LMArena · Instruction followingfollowing detailed instructions#94of 362 · 1419LMArena · Long promptslong, complex requests#91of 340 · 1443LMArena · WebDevbuilding web apps and front ends#37of 133 · 1590LMArena · Visionunderstanding images#53of 145 · 1243LMArena · Creative writingcreative writing#133of 360 · 1359Best attop three among current models
Not in the top three among current models on any category we track.
Where to use itprices checked 18 Nov 2026
API providers 8 of 25 · per 1M tokens, in / out
Run it yourself
Official weightsQwen/Qwen3.8-27B↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released14 Aug 2026
Announcementqwen.ai ↗
Release entryQwen3.8-27B
Scored asQwen 3.8 27B
Output speed–
Hugging FaceQwen/Qwen3.8-27B ↗