hiw3c 日报精选
Hacker News Top 网页快照

两款隐秘模型刚刚出现在排行榜上,均领先于Fable 5.2。

原文标题 · Two stealth models just appeared on the leaderboard, both ahead of Fable 5.2

HN ⭐ 91 · 34 评论

来源:Hacker News Top · contralabs.com

正文为英文,可一键机器翻译(仅首次需要等待)

Deconstructing Real World Creativity.

Exploring the frontier of AI design capabilities through real client briefs from Contra’s marketplace, golden designs and model comparisons.

Leaderboard

How frontier models rank in blind head-to-head votes on real client briefs from Contra’s marketplace.

Elo rating from blind head-to-head votes

Real design projects, judged by designers and scored by rubrics

Frontier Design Benchmark is the first benchmark built on real world, high value, and complex design projects. It is judged by professional designers in the Contra Labs network, ensuring the quality of evaluation.

In the benchmark, we also built a design critique rubric and a list of AI slop patterns. The rubric scores are highly correlated with the designers’ ratings of the models (r = 0.94). These additional metrics provide explainable design quality judgement on top of pairwise preferences.

Golden Gallery

Real client briefs, each with its golden: the design set beside the models’ outputs as the bar.

Read the research

Frontier Design: Evaluating AI on Real World Design Tasks

How design jobs are set, reviewed, and evaluated

Pairwise, design rubrics, and AI slop patterns

Compare the outputs

See two AI designs for the same brief, with the model names hidden. Pick the one you think works better.

Deconstructing Real World Creativity.

Exploring the frontier of AI design capabilities through real client briefs from Contra’s marketplace, golden designs and model comparisons.

Leaderboard

How frontier models rank in blind head-to-head votes on real client briefs from Contra’s marketplace.

Real design projects, judged by designers and scored by rubrics

Frontier Design Benchmark is the first benchmark built on real world, high value, and complex design projects. It is judged by professional designers in the Contra Labs network, ensuring the quality of evaluation.

In the benchmark, we also built a design critique rubric and a list of AI slop patterns. The rubric scores are highly correlated with the designers’ ratings of the models (r = 0.94). These additional metrics provide explainable design quality judgement on top of pairwise preferences.

Golden Gallery

Real client briefs, each with its golden: the design set beside the models’ outputs as the bar.

Read the research

Frontier Design: Evaluating AI on Real World Design Tasks

How design jobs are set, reviewed, and evaluated

Pairwise, design rubrics, and AI slop patterns