Qwen 3.8-27B makes a striking impact on the ARC-AGI-3 Kaggle Leaderboard
GregKamradt · x · 2026-08-21
Following TUFA Labs' open-sourcing of their submission, Qwen 3.8-27B has had a striking effect on the ARC-AGI-3 Kaggle Leaderboard, demonstrating strong performance in this benchmark.
More from Models
- Ox Alpha: Free Chinese model with 1M context but high latency — bindureddy · 2026-08-21
- Legal AI startup Harvey launches first model post-trained for law on Kimi K3 — Polymarket · 2026-08-21
- Ox Alpha appears to be GLM 5.3 Flash — LinusEkenstam · 2026-08-21
- Insider confirms stealth model Ox Alpha is spectacular, resets AGI timelines — omarsar0 · 2026-08-21
- HF Report: Qwen GGUF Downloads Hit 39.6M, Dwarfing Llama's 7.5M — close_Meal6005 · 2026-08-21
- Skeptic: "Claude designed protein binders alone" was mostly just Modal credentials — charles_irl · 2026-08-21