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.
Related event: Claude Opus 5 Sets New ARC-AGI-3 Record(15 posts)→
More from Models
- Meta's Muse Agent has built-in invite code logic, hinting at free-usage expansion — testingcatalog · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Claude is no longer available for minors as Anthropic rolls out age assurance — Muhammad523 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11