Data◆Article · 3:45 — 4:20
Qwen 3.8 27B achieves DeepSeek V4-Pro/GPT-5.6 Luna-level performance on the Artificial Analysis Intelligence Index, marking the first time a local model has reached that capability tier.
Qwen 3.8 27B benchmarks show it competing with frontier models like DeepSeek V4 and GPT-5.6 Luna Max, signaling a significant compression of the local-to-frontier performance gap. ✦ AI generated
AINews · Latent Space · 2026-08-17 · original ↗
The strongest signal here was @cline's note that Qwen3.8-27B now scores at DeepSeek V4-Pro / GPT-5.6 Luna territory on the Artificial Analysis Intelligence Index, described as the first time a local model has reached that capability tier. Ollama immediately positioned deployment paths for local users, and anecdotal reports like @rishdotblog's suggest the model is already practical for long-context local coding setups.
Read full article ↗excerpt · fair-use quotation
- ·Scores at DeepSeek V4-Pro / GPT-5.6 Luna tier
- ·First local model to reach this capability level
- ·Benchmarked on Artificial Analysis Intelligence Index
- ·Local-to-frontier performance gap compressing rapidly
- ·Ollama positioned immediate deployment paths
- ·Already practical for long-context local coding
- ·Anecdotal reports confirm real-world usability
- ·27B parameters enable efficient local inference
Around this claim
In practice · 2
Kimi K3 shows open weight models can stand toe-to-toe with proprietary frontier ones.Simon Willison · Simon Willison's Weblog · conf 80%Leading open weight models now trail closed frontier models on cybersecurity capability by only 4-7 months, down from the 6-10 month gap measured through most of 2025.UK AI Security Institute (AISI) · Import AI · conf 75%