Public KG record
Astra
Recorded overview
An upcoming frontier model that may meet the Critical cybersecurity capability t
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: 100% on ExploitBench
- Benchmarks: 跨所列基准未见有意义的水印前后性能差异
- Benchmarks: 使用 Artificial Analysis Intelligence Index、DeepSWE v1.1、Terminal-Bench 4.0、Terminal-Bench Science 0.1 和 HealthBench Professional 评估
- Benchmarks: DeepSWE v1.1
- Benchmarks: ExploitBench
- Benchmarks: HealthBench Professional
- Benchmarks: Terminal-Bench 4.0
- Capabilities: Generate SVGs of pelicans riding bicycles at various reasoning levels.
Evidence coverage
The KG currently records 11 known information dimensions and has 8 undocumented dimensions, linked to 20 public source articles. These counts describe record coverage, not model performance or verified fit.