in the loop

Qwen2.5-Coder-32B
#199 of 274 scored.

AlibabaSep 18, 2024Open weights

Capabilities Index

Range 110.0–124.9

119.5

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

No independent scores yet.

Epoch AI hasn't run Qwen2.5-Coder-32B yet. Its scores show up here the morning after they do.

Everything else Epoch has for it

  • GSM8K91.1%
  • HellaSwag77.3%
  • MMLU72.1%
  • Winogrande61.6%
  • ARC AI260.7%

On the index

Around it.

  1. #196Claude InstantAnthropic120.3
  2. #197Claude 2Anthropic120.1
  3. #198Gemma 2 9BGoogle119.8
  4. #199Qwen2.5-Coder-32BAlibaba119.5
  5. #200Command R+Cohere119.3
  6. #201Claude 2.1Anthropic119.3
  7. #202Mistral NeMoMistral · $0.029 in118.7

Sources