Qwen3.8-27B tested against models 100x its size in first impressions video

arena · x · 2026-08-22

Arena released a first impressions video of the Qwen3.8-27B model with Peter Gostev. They tested it against models up to 100x larger, including DeepSeek v4, Qwen 3.8 Max, Kimi K3, GLM 5.3, Grok 4.6, GPT-5.6, and Fable. The benchmarks covered identical one-shot generation and agentic tasks, with full scores coming soon.

Original post →

More from Models

Models channel →