Roboflow Vision Evals
Roboflow · Image comprehension, counting, OCR and image information extraction
Across e/accUnder observation
Evidence budgetNot scored
Upstream data timeUnverified
Last successful syncCollection not started
What it measures and how
Six tasks share a budget. Distinguish strict accuracy from model-judge scores. Half-ranges from three runs are not 95% intervals.
How this evidence is used
Under observation: the new board’s data API is rate-limited. The older open-source repository lacks this round’s new models; old data is not presented as the new board.
Limitations and attribution
Under observation: the new board’s data API is rate-limited. The older open-source repository lacks this round’s new models; old data is not presented as the new board.
Data license: Leaderboard data usage terms remain to be confirmed.
Results are published by Roboflow. Raw scores and the e/acc consensus index use different scales and cannot be added directly.