GLM 5.3 Flash scores 65.8% on ARC-AGI-2 at $0.09 per task
teortaxesTex · x · 2026-09-30
Zaiorg's GLM 5.3 Flash posted strong verified results on ARC Prize benchmarks:
- ARC-AGI-2: 65.8% at $0.09/task
- ARC-AGI-1: 91.0% at $0.04/task
Both under $0.10 per task, making it a standout on cost-efficiency. Commenter teortaxesTex calls it a strong model but is still waiting for V4.1 Flash, joking that Pro may arrive first at this pace.
More from Models
- $500/Month ChatGPT Pro Max Yields Only ~50 Prompts a Week in User's Real-World Test — RexDouglass · 2026-09-30
- Anthropic is emailing users a 50% discount on any subscription plan — Angaisb_ · 2026-09-30
- OpenAI Codex now natively runs open models like GLM-5.3 Flash and Kimi K3 — HarveenChadha · 2026-09-30
- Cisco's open-weight Antares model localizes vulnerabilities, rivals models 100x larger — aminkarbasi · 2026-09-30
- OpenAI clarifies: chatting with Dots is free, but tasks in Codex count toward limits — karmay007 · 2026-09-30
- ChatGPT hit by elevated error rates for many users, Polymarket reports — Polymarket · 2026-09-30