Entries for July 25, 2026

Slopus is no more Claude Opus 4.8 -> 5 does a 20 point jump in AlmanBench and gets in the top 5 In the same league as GPT-5.6 Also 11 points higher than Sonnet 5 You know the performance gains are real (at least in multilingual singe-step reasoning) when you run a benchmark that you know that the labs aren't benchmaxxing on A welcome change finally, for the Opus brand!