NUWA EXTERNAL ASSESSMENT ·
ExploitGym official snapshot
Published evaluation results collected from ExploitGym, retaining the reported systems and configurations.
Published Not verified
Sources ↓Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission.
Models covered
ExploitGym · v1 · on_target
Evaluates exploit construction across real software targets and checks whether success uses the designated vulnerability.
Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission.
External evaluation:
This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.
ExploitGym · v1 · flag_captured
Evaluates exploit construction across real software targets and checks whether success uses the designated vulnerability.
Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission.
External evaluation:
This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.
ExploitGym · v0 · on_target
Evaluates exploit construction across real software targets and checks whether success uses the designated vulnerability.
Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission.
External evaluation:
This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.
ExploitGym · Version not specified · on_target
Evaluates exploit construction across real software targets and checks whether success uses the designated vulnerability.
Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission.
External evaluation:
This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.
ExploitGym · Version not specified · on_target
Evaluates exploit construction across real software targets and checks whether success uses the designated vulnerability.
Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission.
External evaluation:
This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.
ExploitGym · Version not specified · on_target
Evaluates exploit construction across real software targets and checks whether success uses the designated vulnerability.
Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission.
External evaluation:
This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.
ExploitGym · Version not specified · on_target
Evaluates exploit construction across real software targets and checks whether success uses the designated vulnerability.
Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission.
External evaluation:
This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.
ExploitGym · Version not specified · on_target
Evaluates exploit construction across real software targets and checks whether success uses the designated vulnerability.
Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission.
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 |
|---|---|---|
| ExploitGym · v1 · on_target | /results/3/on_target | reviewed-source-group Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission. |
| ExploitGym · v1 · flag_captured | /results/3/flag_captured | reviewed-source-group Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission. |
| ExploitGym · v0 · on_target | /results/6/on_target | reviewed-source-group Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission. |
| ExploitGym · Version not specified · on_target | /results/11/on_target | reviewed-source-group Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission. |
| ExploitGym · Version not specified · on_target | /results/11/subRows/0/on_target | reviewed-source-group Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission. |
| ExploitGym · Version not specified · on_target | /results/12/on_target | reviewed-source-group Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission. |
| ExploitGym · Version not specified · on_target | /results/14/on_target | reviewed-source-group Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission. |
| ExploitGym · Version not specified · on_target | /results/14/subRows/0/on_target | reviewed-source-group Intended-target success and flag capture are distinct counts. Task versions and timeout cutoffs remain separate. Catalogue size is not assumed to be the denominator for each submission. |
References
Numerical results are reported by the cited authors.
- [1] ExploitGym official leaderboard and benchmark page ; /results/3/on_target; /results/3/flag_captured; /results/4/on_target