Subgraph Atlas · centered on entity

ExploitBench

product2 mentions· velocity: stable

CMU's ExploitBench is an AI benchmark for automated vulnerability exploitation, where Claude Mythos scored 9.9/16 on V8 exploits versus GPT-5.5's 5.5, but cost $36,428 per run — 12 times more.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.

0 nodes · 0 edges · loading…

companypersonai_modelproductresearch_labbenchmarkframework

drag to move · scroll to zoom · click a node

Top connections

GPT-3.5ai model

24 mentions

→ Center atlas here

Claude Mythosai model

17 mentions

→ Center atlas here

Carnegie Mellon Universityorganization

10 mentions

→ Center atlas here

How to read this: the white-ringed node is ExploitBench. Surrounding nodes are direct relationships; the second ring is what those neighbors connect to. Edge thickness scales with source-article evidence. Click any node and choose Center graph here to walk the graph.