Users joke Claude Opus 5 feels like GPT-5 as Anthropic touts SOTA scores
ChengleiSi · x · 2026-07-25
A reply thread jokes that Opus 5 feels like GPT-5, while the quoted Anthropic post says the model is now state of the art on several coding and knowledge-work evaluations.
The attached image appears to show only a tiny gap between two benchmark values, reinforcing the tone of benchmark-driven one-upmanship around frontier models.
Related event: Claude Opus 5 Sparks Debate as Anthropic Highlights SOTA(3 posts)→
More from Models
- Opus 5 Adopts Frontier-Bench as Lead Benchmark One Day Post-Launch — ajratner · 2026-07-25
- Opus 5 debuts at No. 2 on Senior SWE-bench with 32% of Fable 5’s tokens — ajratner · 2026-07-25
- NeurIPS reviewers are already asking for evals on 21B open-source MoE models — chhaviyadav_ · 2026-07-25
- Claude Opus 5 hits 30.2% on ARC-AGI-3, topping the previous 7.8% score — mhmazur · 2026-07-25
- Artificial Analysis ranks Claude Opus 5 near the top while showing a lower price point — Angaisb_ · 2026-07-25
- Claude Opus 5 appears near the top of a frontier model intelligence chart — scaling01 · 2026-07-25