SWE-Marathon v1.1: leaderboard
Metric: Pass@1 (%). Source: www.swe-marathon.org. Saturation forecast: Around January 2027. 56 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K3 | 48.13 |
| 2 | GPT-5.6 Sol (Non-reasoning) | 5.63 |
| 3 | GPT-5.6 Terra (Non-reasoning) | 0 |
| 4 | GPT-5.6 Luna (Non-reasoning) | 0 |
Interactive version: theaggregate.ai/benchmark?slug=swe-marathon-v1-1 · How It Works · Data refreshed daily, snapshot 2026-10-09.