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.
More from Models
- Opus 5 reportedly scores 42/42 on IMO 2026 without tools — Afinetheorem · 2026-07-25
- Elon Musk says Grok 4.6 arrives in 2 weeks and Grok 4.7 in 4 — Acceptable-Debt-294 · 2026-07-25
- Quadrillion says Anthropic’s Opus 5 is faster than Opus 4.8 on hard ML workloads — igarciacamargo · 2026-07-25
- Google is lagging behind open-weight models on most benchmarks — burny_tech · 2026-07-25
- Claude Opus 5 tops an Artificial Analysis coding-agent benchmark at 67 — Hesamation · 2026-07-25
- Side-by-side eval shows diffusion loses overall, but wins speed in agent loops — Additional-Engine402 · 2026-07-25