in the loop

Qwen3-8B
#136 of 274 scored.

AlibabaApr 28, 2025Open weights

Capabilities Index

Range 130.1–138.2

136.2

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond42.3%

    121st of 186

  • Mock AIME56.1%

    109th of 176

Everything else Epoch has for it

  • Fiction.LiveBench62.1%
  • DTBench32.9%
  • LMCA10.4%
  • Chess Puzzles0.0%

On the index

Around it.

  1. #133GPT-4.1OpenAI · $2.00 in136.8
  2. #134GPT-4.5OpenAI136.7
  3. #135Qwen3-30B-A3BAlibaba · $0.12 in136.2
  4. #136Qwen3-8BAlibaba136.2
  5. #137DeepSeek-V3 (Mar 2025)DeepSeek135.9
  6. #138o1-miniOpenAI135.8
  7. #139DeepSeek-R1-Distill-Qwen-14BDeepSeek135.4

Sources