BuildingBench: GPT-6.1 Sol scores 85.1 at 1/27 the cost of Opus 5.5's 86.8
ZhitingHu · x · 2026-10-01
EnactraAI published a BuildingBench leaderboard update showing two big quality jumps with very different price tags.
- GPT-6.1 Sol: 85.1 (up from GPT-6 Sol's 69.6), taking second place while cutting median cost per building from $1.89 to $1.70. That beats GPT-6 Astra ultra (84.3) at 76% lower cost and sits just 1.7 points behind Opus 5.5 max (86.8) at roughly 1/27 the cost
- Sonnet 5.5 max: leaps 22.5 points from 54.4 to 76.9, now fifth — but cost rises from $15.03 to $39.99 per building
More from Models
- True Positive Weekly #180: Xiaomi's MIT-licensed MiMo-V2.6, physicist-style LLM pruning, OpenHands — burkov · 2026-10-01
- Perplexity's pplx-embed-v2-context-9b-preview sets SOTA on ConTEB benchmark — perplexity_ai · 2026-10-01
- OpenAI Accuses Chinese Lab of Distillation: 16,000 Requests in 2 Days to Extract Hidden Reasoning — rohanpaul_ai · 2026-10-01
- AI Hype Cycles: The Same Crowd Bashing OpenAI Just Spent Months Bashing Anthropic — haider1 · 2026-10-01
- Player trusts Gemini on its own TTS pricing, gets billed 70p after Gemini said it would be free — Environmental_Ad3162 · 2026-10-01
- Pedro Domingos: the more agent products OpenAI ships, the faster they fail — pmddomingos · 2026-10-01