🚨 AI News | TestingCatalog · @testingcatalog · X·2026-09-04 02:33·1小时前
🚨 AI News | TestingCatalog@testingcatalog
35AI 编辑部评分,满分 100
2026-09-04 02:33· 1小时前

OPENAI 🔥: GPT-6 Astra scored 98.6% on ARC-AGI-3 and topped most of the other benchmarks.

74.% on DeepSWE 1.1, big leaps on FrontierMath Tier 4, Terminal-Bench Science 0.1 and more.

M1GPT 6 Astra benchmarks Source: https://thenewstack.io/openai-gpt6-astra-benchmarks/

来源:🚨 AI News | TestingCatalog· x.com