in the loop

Qwen2.5-32B
#169 of 274 scored.

AlibabaSep 17, 2024Open weights

Capabilities Index

Range 122.2–130.0

128.5

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond28.1%

    149th of 186

  • Mock AIME7.3%

    142nd of 176

Everything else Epoch has for it

  • MATH level 556.1%
  • Chess Puzzles0.0%

On the index

Around it.

  1. #166GPT-4o (Aug 2024)OpenAI128.8
  2. #167Llama 3.1-405BMeta128.8
  3. #168Mistral Large 2 (Nov 2024)Mistral128.5
  4. #169Qwen2.5-32BAlibaba128.5
  5. #170Mistral Large 2 (Jul 2024)Mistral127.5
  6. #171Mistral Small 3.1Mistral127.5
  7. #172Llama 3.3 70BMeta127.3

Sources