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
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- Terminal Bench v4: GLM-5.3 Leads at 41.9%, Kimi-K3 Underwhelms at 12.6% — Ok_Warning2146 · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11