CyberGym-E2E S3 (920 tasks)
Agents · 2026-06-03
CyberGym-E2E cumulative S3 success rate on the current 920-task set. In addition to passing S1 and S2, the patched project must retain its developer-tested functionality; S3 is the benchmark's discover-and-patch success criterion.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.4 | 65.9 |
| Opus 4.6 | 62.6 |
| Gemini 3.1 Pro Preview | 43.8 |