概念

AA Intelligence

Q: 什么是 AA Intelligence？

评估模型智能水平的基准

Q: AA Intelligence 最近有什么新动态？

traeai 已收录 1 篇与 AA Intelligence 相关的内容。最新一篇是「WAIT… Astra crushes Fable 5.1 on every benchmark but makes 0 progress on the AA Intelligence score? > same 61 as Sol and Grok 4.6 > 51 on Agentic Index vs 59 for Grok > and then it saturates ARC-AGI-3? this is the biggest discrepancy I’ve seen a model’s evals.」，由 Hesam(@Hesamation) 发布。

别名：AA Intelligence score

评估模型智能水平的基准

已跟踪 1 条高相关材料

TraeAI 观察

如果只读 3 篇

WAIT… Astra crushes Fable 5.1 on every benchmark but makes 0 progress on the AA Intelligence score? > same 61 as Sol and Grok 4.6 > 51 on Agentic Index vs 59 for Grok > and then it saturates ARC-AGI-3? this is the biggest discrepancy I’ve seen a model’s evals.

Hesam(@Hesamation) · 7.5 分

Astra模型在多数基准测试中表现优异，但AA Intelligence得分未提升，且成本较高。

WAIT… Astra crushes Fable 5.1 on every benchmark but makes 0 progress on the AA Intelligence score? > same 61 as Sol and Grok 4.6 > 51 on Agentic Index vs 59 for Grok > and then it saturates ARC-AGI-3? this is the biggest discrepancy I’ve seen a model’s evals.

Hesam(@Hesamation)9月4日182 字 (约 1 分钟)

Astra模型在多数基准测试中表现优异，但AA Intelligence得分未提升，且成本较高。

入选理由：Astra在Fable 5.1基准中得分与Grok 4.6相同，但AA Intelligence得分未提升。

FeaturedTweet#AI模型#基准测试#成本分析#模型对比中英混合

跨材料问答 · AA Intelligence

回答基于：AA Intelligence 相关 1 条材料