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.
Related event: Qwen3.8-27B Punches Above Its Weight Against 100x Larger Models(3 posts)→
More from Models
- Yacine on LLMs: "I'm sick of how stupid these language models are. Accelerate!" — yacineMTB · 2026-10-16
- Gemini 4 Argon rolls out in Antigravity for paid AI Pro users with a separate weekly quota — GeminiApp · 2026-10-16
- GPT-4o API dies January 14 as OpenAI refuses to release weights, pushing users to Qwen — mimi10v3 · 2026-10-16
- Opus 5.5 value may end the habit of using the top model for everything — adonis_singh · 2026-10-16
- Musk says Grok Bot is growing faster than anything he's seen, with no free tier — elonmusk · 2026-10-16
- Peter Yang: Opus 5.5 Still Struggles to Hold Its Ground When Pushed Back — petergyang · 2026-10-16