Kimi K3.1 Pro jumps 27.6 points to enter BuildingBench top six, matching DeepSeek V4.1 Flash
Lianhuiq · x · 2026-10-24
Third-party evals show Kimi K3.1 Pro leaping from 54.0 to 81.6 on BuildingBench, a 27.6-point gain that puts it in the top six for 3D reconstruction. It essentially matches DeepSeek V4.1 Flash 1017 (81.9) and joins the cluster around Sonnet 5.5 and Fable 5.1, at an estimated median cost of $12.58/task — cheaper than Sonnet and Fable, though DeepSeek remains more cost-efficient at $3.01. A demo rebuild of Melbourne's Australian Centre for Contemporary Art from photos scored 90.8, underscoring how fast open models are closing the spatial-reasoning gap.
More from Models
- Wave of Chinese Model Releases Imminent: GLM-5.5 and Qwen 4 Next Up — haider1 · 2026-10-24
- Kimi's $100 tier gives less usage than a $20 Claude sub, yet thrives in China — Linahuaa · 2026-10-24
- humans& ships collaborator model Ampersand, social product Boba, and open-sources 10% FTL decode speedup — ericzelikman · 2026-10-24
- Nat Eliason: Blind test 'OVERWHELMINGLY' picks Argon's writing, wants it to rewrite everything — nateliason · 2026-10-24
- GPT-6 Astra solves 49 of 50 research-level physics problems, catches experts' own errors — MoonL88537 · 2026-10-24
- Video: Kimi K3.1 Pro benchmarks claim wins over Opus and GPT flagship, but is it benchmaxxed? — TheAIGRID · 2026-10-24