ScreenSpot-Pro (Mythos Preview Tools): leaderboard
Claude Mythos Preview system-card ScreenSpot-Pro result with Python/image tools, measuring GUI grounding in high-resolution professional screenshots.
Metric: Accuracy (%). Source: www-cdn.anthropic.com. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Mythos Preview | 92.8 | #4 |
| 2 | Claude Opus 4.6 | 83.1 | #63 |
| 3 | Claude Sonnet 4.6 | 82.4 | #90 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=screenspot-pro-mythos-preview-tools · How It Works · Data refreshed daily, snapshot 2026-10-20.