Back to Models
qwen/qwq-32b
Not Available
QwQ 32B
QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.
3/5/2025
32,768 tokens
#167 Text (Japanese)
Specifications
Modalities
Input
text
Output
text
Supported Parameters
frequency_penalty
include_reasoning
max_tokens
presence_penalty
reasoning
response_format
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_p
Max Output Tokens
32,768Leaderboard
Text
๐OverallELO: 1,336
#208๐ฏ๐ตJapaneseELO: 1,251
#167๐จ๐ณChineseELO: 1,381
#176๐ฐ๐ทKoreanELO: 1,279
#167๐ฌ๐งEnglishELO: 1,359
#202frenchELO: 1,347
#180germanELO: 1,304
#179spanishELO: 1,346
#171russianELO: 1,305
#223๐ปCodingELO: 1,384
#201๐งฎMathELO: 1,364
#173โ๏ธCreative WritingELO: 1,294
#218๐Instruction FollowingELO: 1,324
#202๐ถ๏ธHard PromptsELO: 1,357
#200๐ฌMulti-TurnELO: 1,322
#218