SWE-bench Multimodal (Mythos Preview System Card): leaderboard
Claude Mythos Preview system-card run of SWE-bench Multimodal, measuring software issue resolution when visual context is part of the task.
Metric: Resolved (%). Source: www-cdn.anthropic.com. Saturation forecast: Around February 2028. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Mythos Preview | 59 | #4 |
| 2 | Claude Opus 4.6 | 27.1 | #63 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=swe-bench-multimodal-mythos-preview-system-card · How It Works · Data refreshed daily, snapshot 2026-10-20.