in the loop

Qwen 3.8 27B
#58 of 274 scored.

AlibabaAug 14, 2026Open weights

Capabilities Index

Range 147.3–151.1

149.4

Context

Takes text, image, video

1M

Input

Per 1M tokens

$0.42

Output

Per 1M tokens

$2.55

Benchmarks

No independent scores yet.

Epoch AI hasn't run Qwen 3.8 27B yet. Its scores show up here the morning after they do.

Everything else Epoch has for it

  • DTBench80.0%
  • LMCA48.7%
  • Surface Evolver Bench45.0%
  • ProofBench16.0%

On the index

Around it.

  1. #55Kimi K2.7 CodeMoonshot · $0.67 in150.0
  2. #56GLM-5.1Z.ai · $0.97 in149.8
  3. #57GPT-5.1OpenAI · $1.25 in149.6
  4. #58Qwen 3.8 27BAlibaba · $0.42 in149.4
  5. #59Qwen 3.6 Max (Preview)Alibaba149.2
  6. #60Grok 4.3 BetaxAI149.2
  7. #61DeepSeek-V4-ProDeepSeek · $0.21 in149.1

Sources