Back to paper
Full reasoning
May 17, 2026
cs.AI
Share this scorecard
Every score comes with the model's reasoning on the paper page.
Suggested post
"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games" scored 6.5/10 predicted impact on @kurateorg — Significance 7.0 · Novelty 7.0 · Clarity 7.0