Qwen3.8 27B scores 52 on Artificial Analysis
- ID
- 14995
- Status
- summarized
- Published
- 18 Aug 2026, 1:25 AM
- Fetched
- 20 Aug 2026, 2:54 AM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://artificialanalysis.ai/models/qwen3-8-27b
- Source URL
- https://hnrss.org/best
Summary
- Score
- 7.0
- Created
- 20 Aug 2026, 2:59 AM
- Tags
- Audience
- developersai_ml_learnerssaas_founders
What happened
Qwen3.8 27B, an open-weights model from Alibaba released August 2026, scores 52 on the Artificial Analysis Intelligence Index v4.1.1, ranking #1 out of 135 models in its class (small open-weights, 4B–40B). It supports text and image input, has a 256k context window, is a reasoning model, and is licensed Apache 2.0 — but is notably verbose, generating 160M output tokens versus a class median of 43M.
Why it matters
If you're self-hosting or selecting an open-weights model for a product, Qwen3.8 27B is now the top-scoring option in the small-parameter class on Artificial Analysis, and Apache 2.0 means unrestricted commercial use. The verbosity flag is the practical catch: at 160M tokens vs 43M median, inference cost and latency per task could be significantly higher than the index score alone suggests — factor output token volume into your deployment math before committing.
Discussion angle
Is a 27B model that tops the intelligence index but generates ~3.7x more output tokens than the class median actually cheaper to run than a less verbose mid-tier model? Walk through the real cost tradeoff for a Malaysian team self-hosting on rented GPU capacity.