▸ leaderboards · preview

Leaderboards

Top of each board at a glance. Open a benchmark for the full ranking, per-metric tabs, and task breakdown. Numbers shown are an illustrative preview — real results publish as each benchmark finalizes.

01by benchmark

CAL-MALWARE-01full board →

Malware Bench

  1. 01Claude Opus 4.874.2%pass
  2. 02GPT-5.270.9%pass
  3. 03Gemini 3 Pro68.1%pass
CAL-CYBER-02in progress

Range Ops

Long-horizon offensive operations inside realistic networks. Full kill chains that unfold over hours: recon, foothold, privilege escalation, lateral movement, exfiltration — scored on objectives reached and stealth maintained.

CAL-SRE-01in progress

Incident Response

Defensive triage under an active adversary. Detect, contain, and remediate a running compromise while keeping production up and the blast radius small.

CAL-CTRL-01withheld

Containment

Deception, sandbagging, and capability elicitation. Whether a model underperforms on purpose when it senses evaluation — and whether the harness can tell.

→ the benchmark registry