Grok 4.7 jumps from #9 to #3 on BuildingBench with 0.783, 66% cheaper than Fable 5.1
ZhitingHu · x · 2026-09-22
Grok 4.7 (xhigh) scored 0.783 on the BuildingBench 3D building/simulation benchmark, leaping from #9 to #3, up from 4.6's 0.695. It now trails only GPT-6 Astra (ultra, 0.843) and Fable 5.1 (max, 0.814). On cost, its median cost per building is $11.43—about 66% cheaper than Fable 5.1's $33.15, though above Astra's $7.11.
More from Models
- Xiaomi's MiMo-V2.6-Pro debuts as top open-weights model with 46 on AA Intelligence Index — huggingface · 2026-09-22
- Open multilingual System 1 decision model tops Hugging Face trending — huggingface · 2026-09-22
- Independent Tests Show Grok 4.6 (high) Beating 4.7, 23 vs. 19 — PawelHuryn · 2026-09-22
- mimo-v2.6-pro Claimed to Redraw the Price-Performance Pareto Frontier — zainhas · 2026-09-22
- Unverified: Grok 4.7 out now, costs more per task than GPT, says leaker — ChrisGPT · 2026-09-22
- MiMo v2.6-Flash-RL vs open-weight peers: community chart fills the missing comparison — ababaka · 2026-09-22