Claude Opus 5 hits 30.2% on ARC-AGI-3, topping the previous 7.8% score
mhmazur · x · 2026-07-25
Claude Opus 5 has reportedly set a new SOTA on ARC-AGI-3.
- ARC Prize says Anthropic’s Opus 5 reached 30.2% on ARC-AGI-3.
- The previous best score was 7.8%, set by GPT-5.6 Sol (Max).
- ARC Prize also says Opus 5 showed novel behavior that helped it solve environments no model had beaten before, even outperforming Fable in its analysis.
More from Models
- Critic says Gemini 3.5 Pro is already too late to compete — teortaxesTex · 2026-07-25
- Claude Opus 5 is now available in GitHub Copilot and Microsoft Foundry — DanWahlin · 2026-07-25
- 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
- Early Claude Opus 5 feedback says it matches Fable 5 on short tasks, but gets less complete on long ones — ZeroStateReflex · 2026-07-25