Ethan Mollick@emollick · XAI 摘要
Claude Fable 5 在 FrontierMath 基准测试（Tiers 1-4, v2）中表现优异，Tiers 1-3 得分 87%，Tier 4 得分 88%，延续了 Anthropic 模型数学能力快速提升的趋势。主推文评论道：“图形的形状越来越熟悉了。”
The shape of the graph is getting very familiar.
Claude Fable 5 scores very well on FrontierMath: Tiers 1-4 (v2), reaching 87% on Tiers 1-3 and 88% on Tier 4. This continues a streak of Anthropic models improv...