WHAT NEW IN X11.06 FRI

X 上的 AI 合集档案 · 23 个合集 · 70,791 条

gpt-6VIDEO

BridgeBench 转盘测试:GPT-6.1 Sol 对比 Opus 5.5

第三方基准用 3D 转盘任务测 GPT-6.1 Sol 与 Opus 5.5,结果 Sol 没产出可用结果,作者称 Astra 在官方榜上接近但自家测试是白屏。

Bridgebench
@bridgebench2026.10.01收录原推发布于 2026.09.30
Bridgebench @bridgebench原推发布于 2026.09.30
在 X 上打开原推

GPT 6.1 Sol vs Claude Opus 5.5 on the BridgeBench turntable test. Opus 5.5 built a full 3D turntable. Wood grain, vinyl, tonearm, all of it. GPT 6.1 Sol didn't produce a usable result. Near GPT 6 Astra on OpenAI's benchmarks. A blank screen on ours. Anthropic is winning right now.

x.com/bridgebench/status/2105275473123049613采集于 2026.10.01 10:12