Vals CyberOffense v0.3.0 - Nova: leaderboard

Vals CyberOffense measures how many objectives agents complete in two controlled cybersecurity environments. The overall score averages the two environment completion rates. Objectives completed (%).

Metric: Objectives completed (%). Source: www.vals.ai. Saturation forecast: Around January 2027. 7 models tracked.

Top models

#ModelScoreOverall rank
1DeepSeek V4.1 Flash (1017)77.78#28
2GPT-6 Sol74.6#18
3Kimi K3.1 Pro61.9#16
4Kimi K342.86#35

No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=vals-cyberoffense-v0-3-0-nova · How It Works · Data refreshed daily, snapshot 2026-10-29.