Opus 5 is shown as a new Pareto-optimal LLM with strong ARC-AGI-3 results
brandon_galang · x · 2026-07-25
A post says there is a new Pareto-optimal LLM in Opus 5.
The attached chart focuses on ARC-AGI-3 novel problem solving versus total evaluation cost. It shows Opus 5 (high) at roughly 30.2% novel problem-solving score, while Opus 4.8 (high) is shown far lower, alongside cost comparisons that frame the model as much stronger but also expensive to evaluate.
Related event: Anthropic Releases Claude Opus 5(57 posts)→
More from Models
- Hyperagent says Opus 5 is stronger, but GPT-5.6 Sol is cheaper to deploy — TawohAwa · 2026-07-25
- Qwen3.5-9B uncensored GGUF variant starts trending on Hugging Face — DavidAU · 2026-07-25
- ARC Prize says Claude Opus 5 reaches 30.2% on ARC-AGI-3 public demos — inductionheads · 2026-07-25
- Claude Opus 5 builds a Minecraft wizard tower and keeps critiquing itself — adonis_singh · 2026-07-25
- Opus 5 Builds a Wizard Tower in Minecraft, Showcasing Strong Iteration — adonis_singh · 2026-07-25
- Anthropic’s ARC-AGI-3 lead is being called meaningless as the benchmark saturates — morqon · 2026-07-25