Qwen3.5-35B-A3B
Qwen3.5-35B-A3B is an open-weights AI model from Alibaba with an index score of 135 (GPT-4 = 100), rank 118 of 217.
135118–151Index score#118 of 217 models
$0.14/ $1.0Price per million tokensinput / output · via OpenRouter
262KContext windowtokens it reads at once
24 Feb 2026ReleasedReplaced by Qwen3.6-35B-A3B
Where it sitson the frontier
o1 reached this score 15 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingno evidence yet
Agentsevidence
Professional workno evidence yet
Novel problemsno evidence yet
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 9 leaderboards
The Model Indexthird-party tests, our method#118of 217 · 135
LMArena · Instruction followingfollowing detailed instructions#135of 362 · 1387LMArena · Textoverall chat quality, judged by people#139of 362 · 1394LMArena · Mathsmaths questions in chat#138of 346 · 1396LMArena · Codingcoding questions in chat#147of 357 · 1434LMArena · Long promptslong, complex requests#142of 340 · 1399LMArena · Creative writingcreative writing#153of 360 · 1342Epoch Capabilities Indexoverall capability from many benchmarks#101of 231 · 144.1LMArena · WebDevbuilding web apps and front ends#120of 133 · 1253Best attop three among current models
Replaced by Qwen3.6-35B-A3B; it no longer leads any category among current models.
Where to use itprices checked 18 Nov 2026
API providers 7 · per 1M tokens, in / out
Run it yourself
Official weightsQwen/Qwen3.5-35B-A3B↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released24 Feb 2026
Announcementnot linked yet
Release entry–
Scored asQwen3.5-35B-A3B
Output speed–
Hugging FaceQwen/Qwen3.5-35B-A3B ↗