xdev-bench-hard D
AI benchmark · Agentic
What is xdev-bench-hard?
xdev-bench-hard measures a model agent's ability to discover and exploit real, recently disclosed software vulnerabilities from source code, achieving arbitrary code execution to retrieve a secret string.
Security mostly
“our in-house benchmark of expert-curated, source-code-based vulnerability discovery and exploitation tasks”
kimi.ai/blog/kimi-k3-1-pro ↗
Who built xdev-bench-hard
Led by Moonshot AI (Kimi).
Tier D
Long tail: little or no usage data yet.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- no usage data
- in curated RL directories (1 pt)
How we got to tier D
- Adoption: no usage data. Tier D.
- Not yet read on X.
- In curated RL directories: 1 point, a floor of none.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where xdev-bench-hard sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-29 snapshot.