Benchmark Leaderboards
Loading leaderboardsβ¦
Loading leaderboardsβ¦
Track which models hold the current SOTA on the benchmarks the field actually uses. Click a column header to sort; the leading row is highlighted.
AI2 Diagrams β science-diagram question answering over grade-school diagrams (arrows, labels, structures). Tests structured visual comprehension. Accuracy as scored by the OpenVLM Leaderboard.
Metric: Accuracy β higher is better Β· Source β