Individual benchmark scores plotted by date.
| Organisation | Model | Reported | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|---|
| Claude Opus 5 | 28 May 2026 | 70.57% | First-attempt success rate; default settings at 1080p with up to 500 actions; average of 5 runs; Claude Opus 4.8 grader where required | Yes | Source |
