Benchmark
ScreenSpot-Pro
An evaluation benchmark for GUI element grounding tasks that measures the ability of visual-language models to precisely locate UI controls in complex desktop environments.
Timeline (last 90 days)
Oct 18
The top of MMMU_Pro is Darwin-180B-RSI with a score of 79.48; the top of ScreenSpot-Pro is meta-models/Muse-Glimmer-30B with a score of 75.4; and the first place on open-asr-leaderboard is Edge0/ARK-ASR-3B with a score of 4.76 (lower is better).
Unverified50%