Public Artificial Intelligence Benchmark Records Database
ScreenSpot-Pro
Versions / Variants
| Version or Variant | Reference | Status | Records |
|---|---|---|---|
| Unspecified | screenspot-pro/default | ACTIVE | 0 |
| No tools | screenspot-pro/no-tools | ACTIVE | 1 |
| With tools | screenspot-pro/with-tools | ACTIVE | 1 |
Table may be scrolled horizontally on narrow displays.
| Record No. | Model | Benchmark | Metric | Score | Eval Date | Source | Model ID |
|---|---|---|---|---|---|---|---|
BR-002O48-014 |
Claude Opus 4.8 | ScreenSpot-Pro No tools | Overall | 82.3 | Unknown | Primary source | ANTHR-O48 |
BR-002O48-015 |
Claude Opus 4.8 | ScreenSpot-Pro With tools | Overall | 87.9 | Unknown | Primary source | ANTHR-O48 |
Showing records 1–2 of 2
Page 1 of 1