other benchmark · included in ECI
FrontierSWE
FrontierSWE benchmark (score column: Score).
Results
3
Random baseline
0.0%
Score ceiling
100%
Released
2 Sep 2026
Score by model release date
Best score by organisation
Leaderboard
| # | Model | Score | Relative | Setting | Released | Run | Evidence |
|---|---|---|---|---|---|---|---|
| 1 | GLM 5.3 Open source Z.ai | 30.2% | max | 14 Aug 2026 | — | Source ↗ | |
| 2 | Kimi K3 Open source MoonshotAI | 25.9% | max | 16 Jul 2026 | — | Source ↗ | |
| 3 | Inkling (xhigh) Open source Thinking Machines | 4.1% | xhigh | 15 Jul 2026 | — | Source ↗ |
Caveats: settings (reasoning effort, agent scaffold) differ between rows and materially affect scores; the best reported setting per model is shown. Source: Epoch AI, CC BY 4.0.