SWE-bench Verified (Fable/Mythos): leaderboard
The 'Verified' subset of SWE-bench - 500 human-validated GitHub issues ensuring correct problem statements and test coverage. This slice reports Anthropic's own runs from the Claude Fable 5 / Mythos 5 system card; small frontier-model pool.
Metric: Resolved (%). Source: www-cdn.anthropic.com. Saturation forecast: Around January 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Mythos 5 | 95.5 | #2 |
| 2 | Claude Fable 5 | 95 | #16 |
| 3 | Claude Mythos Preview | 93.9 | #4 |
| 4 | Claude Opus 4.8 | 88.6 | #37 |
| 5 | Gemini 3.1 Pro (Preview) | 80.6 | #58 |
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-verified-fable-mythos · How It Works · Data refreshed daily, snapshot 2026-10-20.