in the loop

Qwen2.5-Coder-3B
#233 of 274 scored.

AlibabaSep 18, 2024

Capabilities Index

Range 94.2–115.7

107.7

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

No independent scores yet.

Epoch AI hasn't run Qwen2.5-Coder-3B yet. Its scores show up here the morning after they do.

Everything else Epoch has for it

  • GSM8K75.7%
  • HellaSwag61.2%
  • ARC AI237.2%
  • Winogrande34.8%

On the index

Around it.

  1. #230DeepSeek-Coder-V2-Lite-BaseDeepSeek108.9
  2. #231PaLM 2-MGoogle108.3
  3. #232Phi-2Microsoft107.9
  4. #233Qwen2.5-Coder-3BAlibaba107.7
  5. #234Nemotron-4 15BNvidia107.7
  6. #235Yi-9B01.AI107.6
  7. #236LLaMA-33BMeta107.4

Sources