SWE-Marathon — leaderboard
Long-horizon software engineering benchmark where coding agents work on realistic repository tasks under marathon-scale time budgets, reporting pass@1 for end-to-end completed tasks.
Metric: Pass@1 (%). Source: www.swe-marathon.org. Status: saturation imminent. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 | 26 |
| 2 | Claude Fable 5 | 24 |
| 3 | Claude Opus 4.7 | 16 |
| 4 | GLM-5.2 | 13 |
| 5 | GPT-5.5 | 12 |
| 6 | Gemini 3.5 Flash | 7 |
| 7 | Gemini 3.1 Pro (Preview) | 4 |
| 8 | DeepSeek V4 Pro | 4 |
| 9 | GLM-5.1 | 1 |
| 10 | Kimi K2.6 | 0 |
| 11 | MiniMax-M2.7 | 0 |
Interactive version: theaggregate.ai/benchmark?slug=swe-marathon · How the rankings work · Data refreshed daily, snapshot 2026-07-22.