Skip to content

QwQ-32B

AlibabaOpen weightsReasoningReleased Mar 6, 2025
Compare with Claude Opus 5.5Source scores ↗
Overall score
—
Not enough evidence to rank yet
Context window
131K
131,000 tokens
Price per 1M tokens
— in · — out
No price listed
Blended price
—
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Knowledge59.6
  2. 2Instruction following#10744.9
  3. 3Reasoning43.3
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (11)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Knowledge

GPQA65.6#85 of 117
MMLU-Redux90.0#8 of 15
MMMLU80.9#8 of 11
C-Eval88.4#7 of 10

Math

AIME 202569.5#25 of 38
MATH-50098.0#3 of 20
AIME 202479.5#9 of 19

Agentic & tool use

BFCL v366.4#4 of 5

Coding

LiveCodeBench v562.7#3 of 6

Multilingual

INCLUDE69.7#10 of 10

Instruction following

IFEval83.9#34 of 53

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price———

Arena ratings

Human-preference ratings from LMArena. Best-rated variant shown.

Text1329#228 · 25.2K votes

Open weights

From the Hugging Face repository.

Parameters
33B
Licence
apache-2.0
Downloads (30 days)
37.4K

Speed

Measured by us through OpenRouter (median of trials).

Not available on OpenRouter, so we cannot measure it yet.