in the loop

Qwen3-30B-A3B-Thinking (Jul 2025)
#120 of 274 scored.

AlibabaJul 30, 2025Open weights

Capabilities Index

Range 135.5–141.0

139.6

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond60.1%

    101st of 186

  • Mock AIME70.3%

    93rd of 176

Everything else Epoch has for it

  • DTBench48.9%
  • LMCA23.0%
  • Chess Puzzles3.2%

On the index

Around it.

  1. #117Gemini 2.5 Flash (Apr 2025)Google140.0
  2. #118gpt-oss-120bOpenAI · $0.037 in139.9
  3. #119DeepSeek-V3.1DeepSeek · $0.25 in139.9
  4. #120Qwen3-30B-A3B-Thinking (Jul 2025)Alibaba139.6
  5. #121Qwen3.5-9BAlibaba · $0.10 in139.5
  6. #122GPT-5 nanoOpenAI · $0.05 in139.4
  7. #123Qwen3-235B-A22BAlibaba139.3

Sources