Claude Opus 5 Exhibits Unprecedented Algebraic Reasoning on ARC-AGI-3
typewriters · x · 2026-07-25
During their analysis of Claude Opus 5, ARC Prize officials observed a new capability previously unseen from frontier models.
While tackling the previously unbeaten ARC-AGI-3 benchmark, Opus 5 demonstrated advanced logical reasoning by spontaneously converting the test layouts into algebraic notation. For instance, at step 23, the model described the scene with the equation 4center = 2×axis − 5center. By step 248, it further generalized this rule into two dimensions, formulating a universal reflection equation for both rows and columns.
Related event: Claude Opus 5 Sets New ARC-AGI-3 Record(15 posts)→
More from Models
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11