in the loop

Qwen2.5-Coder-0.5B
#271 of 274 scored.

AlibabaSep 18, 2024

Capabilities Index

Range 58.7–100.4

88.2

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

No independent scores yet.

Epoch AI hasn't run Qwen2.5-Coder-0.5B yet. Its scores show up here the morning after they do.

Everything else Epoch has for it

  • GSM8K34.5%
  • HellaSwag31.2%
  • MMLU22.7%
  • ARC AI212.5%
  • Winogrande9.6%

On the index

Around it.

  1. #268Dolly 2.0-12bDatabricks89.7
  2. #269DeepSeek Coder 6.7BDeepSeek89.6
  3. #270StarCoder 2 3BHugging Face88.8
  4. #271Qwen2.5-Coder-0.5BAlibaba88.2
  5. #272Cerebras-GPT-13BCerebras83.2
  6. #273DeepSeek Coder 1.3BDeepSeek63.6
  7. #274stablelm-tuned-alpha-7bStability AI55.8

Sources