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
#163 Text (Korean)
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

32,768
Leaderboard
Text
๐Ÿ†OverallELO: 1,336
#203
๐Ÿ‡ฏ๐Ÿ‡ตJapaneseELO: 1,250
#167
๐Ÿ‡จ๐Ÿ‡ณChineseELO: 1,381
#172
๐Ÿ‡ฐ๐Ÿ‡ทKoreanELO: 1,279
#163
๐Ÿ‡ฌ๐Ÿ‡งEnglishELO: 1,359
#197
frenchELO: 1,347
#176
germanELO: 1,304
#179
spanishELO: 1,346
#168
russianELO: 1,306
#219
๐Ÿ’ปCodingELO: 1,384
#196
๐ŸงฎMathELO: 1,364
#170
โœ๏ธCreative WritingELO: 1,294
#213
๐Ÿ“Instruction FollowingELO: 1,324
#197
๐ŸŒถ๏ธHard PromptsELO: 1,357
#195
๐Ÿ’ฌMulti-TurnELO: 1,322
#213