Opus 5 reportedly beats GPT-5.6 Sol 30.2% to 7.8% on ARC-AGI-3

beffjezos · x · 2026-07-25

Beff Jezos says Opus 5 is far ahead on ARC-AGI-3

In a reply quoting a benchmark result, beffjezos says he wishes they knew where Fable sits on the scale at ARC Prize. The quoted claim says Opus 5 beat GPT-5.6 Sol on ARC-AGI-3, posting 30.2% vs 7.8%.

The post is short, but the implication is clear: if the benchmark holds up, the gap between top models on this task is still very large.

Related event: Anthropic Launches Claude Opus 5 with Cutting-Edge Performance at Half the Price(72 posts)→

Original post →

More from Models

Models channel →