on behalf of everyone who ever smugly said "enhance" isn't a thing
i’m sorry
29% → 73% on our Chartography benchmark
great job @ClaudeDevs and fable proving everyone wrong
Our Chartography benchmark measures whether models can read professional charts.
@Anthropic's contribution to science: what if it squinted?
Nice job Fable.
Our Chartography benchmark measures whether models can read professional charts.
@AnthropicAI’s contribution to science: what if it squinted?
Nice job Fable.
on behalf of everyone who ever smugly said "enhance" isn't a thing
i’m sorry
29% → 73% on our Chartography benchmark
great job @ClaudeDevs and fable proving everyone wrong
Our Chartography benchmark measures whether models can read professional charts.
@Anthropic's contribution to science: what if it squinted?
Nice job Fable.
Our Chartography benchmark measures whether models can read professional charts.
@AnthropicAI’s contribution to science: what if it squinted?
Nice job Fable.