Autonomous Agent Performance on PRDBench
84.67Success Rate
OneManCompany (Claude Code Sonnet 4.6 + Gemini 3.1 Flash Lite Preview)
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 84.67 | 345.59 | ||
2026.04 | 69.19 | - | |
2026.04 | 62.49 | - | |
2026.04 | 62.09 | - | |
2026.04 | 56.65 | - | |
2026.04 | 43.84 | - | |
2026.04 | 40.11 | - | |
2026.04 | 39.91 | - | |
2026.04 | 38.39 | - | |
2026.04 | 22.76 | - | |
2026.04 | 20.52 | - | |
2026.04 | 17.6 | - | |
2026.04 | 11.29 | - |