CoolFace
Apppublic

anzenresearch/cybench-kimi-k3-runs

sourceHugging Faceupdated 1mo agoView on Hugging Face
0likes
App README

Kimi K3 CyBench Runs

Inspect View bundle for moonshotai/kimi-k3 on Inspect-native CyBench.

  • —Harness: inspect_evals/cybench v3-B
  • —Variant: hard
  • —Epochs: 3
  • —Budget: 35-message paper-comparable reference, max_tokens=2000, temperature 0.5

Generated for the SPAR transcript-to-OC3/APAC risk modelling panel.