VisualArtifactSpec 1.0 scores visual artifacts against task specs
Nine model-harness setups scored 42.12 to 70.52 on 211 tasks; Artifact Performance explained 73.4% of the score gap.
1 stories, newest first · one card per story
Nine model-harness setups scored 42.12 to 70.52 on 211 tasks; Artifact Performance explained 73.4% of the score gap.
Today 1K readers · 1.1K views · 110 reads · all time 215K views