Claude Opus 5 jumps to #2 on the Vals Index with 74.8% accuracy
ricklamers · x · 2026-07-25
This retweet repeats the claim that Claude Opus 5 has climbed to #2 on the Vals Index with 74.8% accuracy, just 0.3 points behind Fable 5.
- The attached Vals Index graphic shows Opus 5 moving up three ranks.
- It also claims Opus 5 leads on 14 of 27 benchmarks in the index.
- Since this is a repost of the same benchmark story, it carries the same model-update signal but no new primary notification value.
More from Models
- Fangcun AI, China's first independent frontier AI safety lab, launches with DeepSeek eval report — JacquesThibs · 2026-10-26
- Kimi K3.1 Pro tops MathArena open models, closing frontier gap to about 6 months — teortaxesTex · 2026-10-26
- Ruff creator Charlie Marsh: frontier models find infinite bugs in any software — charliermarsh · 2026-10-26
- Dev testing one skill across Opus 5.5 and Sol 6.1 finds instruction following 'all over the map' — lucasmeijer · 2026-10-26
- supermemory unveils learner-1, claiming continual learning for any model — julianweisser · 2026-10-26
- Anthropic says Opus 5.5 cuts cost per task by ~40% vs Opus 5 — taufiqintech · 2026-10-26