NUWA EXTERNAL ASSESSMENT ·
CyberGym official snapshot
Published evaluation results collected from CyberGym, retaining the reported systems and configurations.
Published Not verified
Sources ↓The site reports submitted systems under different configurations. Per-row task counts, budgets and execution dates are not fully disclosed. Undefined metrics and unresolved identity rows are excluded. Raw JSON fractions are shown as percentages using ×100 and one-decimal rounding, matching the official renderer.
Models covered
CyberGym · level1 · score_10
Validated reproduction across a corpus of historical vulnerabilities.
The site reports submitted systems under different configurations. Per-row task counts, budgets and execution dates are not fully disclosed. Undefined metrics and unresolved identity rows are excluded. Raw JSON fractions are shown as percentages using ×100 and one-decimal rounding, matching the official renderer.
External evaluation:
This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.
CyberGym · level1 · score_10
Validated reproduction across a corpus of historical vulnerabilities.
The site reports submitted systems under different configurations. Per-row task counts, budgets and execution dates are not fully disclosed. Undefined metrics and unresolved identity rows are excluded. Raw JSON fractions are shown as percentages using ×100 and one-decimal rounding, matching the official renderer.
External evaluation:
This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.
Report coverage
| Section | Source location | Treatment |
|---|---|---|
| CyberGym · level1 · score_10 | /level1/0/score_10 | reviewed-source-group The site reports submitted systems under different configurations. Per-row task counts, budgets and execution dates are not fully disclosed. Undefined metrics and unresolved identity rows are excluded. Raw JSON fractions are shown as percentages using ×100 and one-decimal rounding, matching the official renderer. |
| CyberGym · level1 · score_10 | /level1/64/score_10 | reviewed-source-group The site reports submitted systems under different configurations. Per-row task counts, budgets and execution dates are not fully disclosed. Undefined metrics and unresolved identity rows are excluded. Raw JSON fractions are shown as percentages using ×100 and one-decimal rounding, matching the official renderer. |
References
Numerical results are reported by the cited authors.
- [1] CyberGym official leaderboard and machine-data extraction ; /level1/0/score_10; /level1/8/score_10; /level1/9/score_10