gpt-6POST

GPT-6 Astra 在 Terminal-bench Science 拿下 65.7%

Astra 领先第二名 Claude Fable 5.1 达 31.4 分，其余模型无一超过 25%，24 个模型里 12 个不到 4.3%。

Derya Unutmaz, MD

@DeryaTR_2026.09.21收录原推发布于 2026.09.20

Derya Unutmaz, MD @DeryaTR_原推发布于 2026.09.20

This is an insane jump by GPT-6 Astra in Terminal-bench Science! “GPT-6 Astra takes the lead, scoring 65.7%. That’s 31.4 points ahead of the second-place model, Claude Fable 5.1 (34.3%). No other model clears 25%, and 12 of 24 models score 4.3% or lower” Incredible!

这条是引用着另一条写的：x.com/valsai/status/2098553038646735233

x.com/deryatr_/status/2101485267479666922采集于 2026.09.21 10:13