Claude Opus 5.5 tops VoxelBench, GPT-6 Sol ranks third
legit_api · x · 2026-09-24
VoxelBench updates: Claude Opus 5.5 takes the #1 spot, described simply as "wonderful," while GPT-6 Sol ranks third, improving over 5.6. The top-3 race remains fierce.
Note: the model names are unusual and unverified; treat with caution pending official announcements.
Related event: "Claude Opus 5.5" Tops VoxelBench — But It's Just a Meme(2 posts)→
More from Models
- Anthropic's new Opus 5.5 playbook: stop saying "think carefully" and hand over whole tasks — udmrzn · 2026-09-24
- Early Opus 5.5 Impressions: Major Gains in Writing Tone, Layout and iOS Design — doodlestein · 2026-09-24
- METR says it used an undisclosed 'additional source' to understand Anthropic's AI R&D, buried in the Opus 5.5 system card — coherence · 2026-09-24
- Not every AI task needs an LLM: 'decide' may become a standard model call — bigdata · 2026-09-24
- Gemma 4 now runs fully offline in the Antigravity SDK on local GPUs, zero API costs — DynamicWebPaige · 2026-09-24
- Claude's terminal model picker used to be simpler, and this meme says why — ColleenMBrady · 2026-09-24