Back to Models
qwen/qwen3-max
Not Available

Qwen3 Max

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It delivers higher accuracy in math, coding, logic, and science tasks, follows complex instructions in Chinese and English more reliably, reduces hallucinations, and produces higher-quality responses for open-ended Q&A, writing, and conversation. The model supports over 100 languages with stronger translation and commonsense reasoning, and is optimized for retrieval-augmented generation (RAG) and tool calling, though it does not include a dedicated “thinking” mode.

9/23/2025
262,144 tokens
#32 Text (Japanese)
Specifications

Modalities

Input
text
Output
text

Supported Parameters

max_tokens
presence_penalty
response_format
seed
temperature
tool_choice
tools
top_p

Max Output Tokens

32,768
Leaderboard
Text
🏆OverallELO: 1,424
#50
🇯🇵JapaneseELO: 1,381
#32
🇨🇳ChineseELO: 1,441
#73
🇰🇷KoreanELO: 1,369
#46
🇬🇧EnglishELO: 1,435
#52
frenchELO: 1,461
#33
germanELO: 1,433
#33
spanishELO: 1,406
#60
russianELO: 1,418
#50
💻CodingELO: 1,475
#42
🧮MathELO: 1,431
#38
✍️Creative WritingELO: 1,394
#56
📝Instruction FollowingELO: 1,415
#51
🌶️Hard PromptsELO: 1,449
#44
💬Multi-TurnELO: 1,445
#38