Reported 90% on ARC-AGI-2 at $3.12/task with 32% cost reduction
eyishazyer · x · 2026-09-02
A reposted discussion claims a model scored 90% on ARC-AGI-2 at $3.12 per task, alongside a 32% cost reduction — cited as evidence of a strong reasoning gain and improved efficiency. The specific model isn't named in the excerpt, so the claim warrants verification.
More from Models
- Claude Fable 5.1 prompting guide: 16 official tips and an agent migration checklist — xiaohu · 2026-09-02
- Leaked Gemini 3.8 Flash benchmarks claim wins over Opus 5 on Terminal Bench 2.1 — kimmonismus · 2026-09-02
- Gemini 3.8 Flash reportedly delivers ~Opus 5 performance at much lower cost — inductionheads · 2026-09-02
- Tester Claims Fable 5.1 Excels at Long-Horizon Tasks, Finance and Consulting 'Wiped Out' — felpix_ · 2026-09-02
- Technical assessment of Qwen3.8-27B ahead of Max's Arena debut — arena · 2026-09-02
- Qwen3.8-Max-0902 lands in LMArena, plus a technical video review of Qwen3.8-27B — arena · 2026-09-02