PointerBench Custom Tools - Pro: leaderboard

PointerBench: 1,500 screenshot/instruction pairs, 500 per suite, with 1024×768 absolute pixel coordinates. One JSON prompt; success requires a point inside the target or box coverage ≥0.90 and precision ≥0.70. Disabled uses 512 output tokens; Low and Medium use 2,048, with a 1,024-token reasoning allowance for Medium. Outputs are unmodified; malformed, filtered and exhausted responses fail without retry. Explicit thinking settings are retained; separate Custom Tools endpoint run, distinct from the ordinary preview endpoint. Success rate (%).

Metric: Success rate (%). Source: arxiv.org. 1 models tracked.

Top models

Interactive version: theaggregate.ai/benchmark?slug=pointerbench-custom-tools-pro · How It Works · Data refreshed daily, snapshot 2026-10-25.