AI 导读
绘制 ARC-AGI 模型分数后发现,三项基准之间存在强关联。 例如,幂曲线 v2 = v1^4.53 可解释 ARC-AGI-2 分数约 98% 的变化。在 ARC-AGI-1 上得分相同的模型,在 ARC-AGI-2 上仍可能相差超过 20 个百分点。
正文
Plotting ARC-AGI model scores reveals a strong relationship across all three benchmarks.
For example, the power curve v2 = v1^4.53 explains about 98% of the variation in ARC-AGI-2 scores. Models tied on ARC-AGI-1 can still differ by over 20 percentage points on ARC-AGI-2.
来源:ARC Prize · x.com