ScreenSpot-Pro — With-tools condition of ScreenSpot-Pro; much higher scores than no-tools (median 87.6 vs 49.1).
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | Anthropic | 87.9 | 1 | 2026-06-01 |
| 2 | Claude Opus 4.7 | Anthropic | 87.6 | 3 | 2026-06-21 |
| 3 | Claude Opus 4.6 | Anthropic | 83.1 | 2 | 2026-06-21 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.