in the loop

QwQ-32B
#130 of 274 scored.

AlibabaMar 5, 2025Open weights

Capabilities Index

Range 132.9–141.6

137.6

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond53.8%

    111th of 186

  • Mock AIME59.1%

    106th of 176

Everything else Epoch has for it

  • Fiction.LiveBench83.3%
  • Lech Mazur Writing80.2%
  • Aider polyglot20.9%
  • Chess Puzzles0.0%

On the index

Around it.

  1. #127Grok 3xAI138.3
  2. #128Qwen3-14BAlibaba · $0.10 in138.2
  3. #129gpt-oss-20bOpenAI · $0.018 in137.8
  4. #130QwQ-32BAlibaba137.6
  5. #131DeepSeek-R1-Distill-Qwen-32BDeepSeek137.4
  6. #132Qwen3-30B-A3B-Instruct (Jul 2025)Alibaba137.4
  7. #133GPT-4.1OpenAI · $2.00 in136.8

Sources