in the loop

DeepSeek-R1-Distill-Qwen-14B
#139 of 274 scored.

DeepSeekJan 20, 2025Open weights

Capabilities Index

Range 127.0–138.0

135.4

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond26.3%

    151st of 186

  • Mock AIME50.5%

    113th of 176

Everything else Epoch has for it

  • MATH level 587.1%
  • Chess Puzzles0.0%

On the index

Around it.

  1. #136Qwen3-8BAlibaba136.2
  2. #137DeepSeek-V3 (Mar 2025)DeepSeek135.9
  3. #138o1-miniOpenAI135.8
  4. #139DeepSeek-R1-Distill-Qwen-14BDeepSeek135.4
  5. #140Gemini 2.0 Flash Thinking (Jan 2025)Google135.4
  6. #141Gemini 2.0 ProGoogle135.1
  7. #142GPT-4.1 miniOpenAI · $0.40 in135.0

Sources