Same models top almost every AA-3D domain, Artificial Analysis finds
ArtificialAnlys · x · 2026-10-13
Artificial Analysis's AA-3D breakdown shows a top-five model leads win rate in six of seven domains; in living bodies, sixth-ranked GPT-6.1 Sol (78.6%) ties Claude Sonnet 5.5 (78.5%). Gaps under 12 points are noise. Per-scene costs: Claude Opus 5.5 $20.50, GPT-6 Astra $18.11, GPT-6.1 Sol $3.51. Method: models act as sandbox agents turning briefs into web pages, blind pairwise votes fitted to Elo via Bradley-Terry.
Related event: Artificial Analysis Launches AA-3D Leaderboard and Cost Frontier(2 posts)→
More from Models
- Claude auto-files a bug report about itself: TLDRs still too long after user asked for shorter — andrey_kurenkov · 2026-10-13
- Meta skipped the 'too dangerous to release' marketing for Muse Wonder — and could rival Google — haider1 · 2026-10-13
- Anthropic says new defenses cut distillation attack data harvesting by 90-99%, cites Zhipu's GLM-5.3 — AnthropicAI · 2026-10-13
- Delve Town's 'bee' model was further trained by Claude for ~24 hours — Sauers_ · 2026-10-13
- Muse Wonder disappoints on RareBench: Opus 5.5 leads at 52% recall — danielmckinn0n · 2026-10-13
- Chart sparks debate: Are Anthropic and OpenAI really months ahead of Meta and Google? — scaling01 · 2026-10-13