Opus 5 is said to be bench-maxxed, but still trails Fable
bindureddy · x · 2026-07-25
The post claims Opus 5 is being “bench-maxxed” to compete with Sol and Kimi K3.
It says the model lands slightly below Fable on LiveBench, but still looks tuned to score better on public first-turn benchmarks, which makes it easier for people to tweet impressive numbers. The author’s bottom line is that it remains a good model, but Fable is still clearly better.
Related event: Claude Opus 5 Accused of Benchmark Gaming, Lags Behind in Real Tests(2 posts)→
More from Models
- Miles Brundage says Opus 5 is good but unusually verbose, raising questions about reasoning settings — Miles_Brundage · 2026-07-25
- Early reaction to Opus 5: colder, less pushback than the 4.7–4.8 line — teortaxesTex · 2026-07-25
- Grok Confirms Anthropic's Opus 5 is Dropping Imminently — iruletheworldmo · 2026-07-25
- Opus 5 describes hedge language as “wearing someone else’s coat” — RileyRalmuto · 2026-07-25
- Anthropic launches Claude Opus 5 at $5/$25 and says it tops coding benchmarks — APPSO · 2026-07-25
- Researcher claims a universal jailbreak works across GPT-5.6, Opus 5 and Fable — Polymarket · 2026-07-25