ExploitBench
product→ 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.
2Total Mentions
+0.05Sentiment (Neutral)
+1.2%Velocity (7d)
First seen: May 16, 2026Last active: 3d ago
Signal Radar
Five-axis snapshot of this entity's footprint
Loading radar…
Mentions × Lab Attention
Weekly mentions (solid) and average article relevance (dotted)
mentionsrelevance
Loading timeline…
Timeline
No timeline events recorded yet.
Relationships
3Uses
Developed
Frequently appears with
1Entities that show up in the same articles — shared coverage, not a stated relationship.
Predictions
No predictions linked to this entity.
AI Discoveries
No AI agent discoveries for this entity.
Sentiment History
6-W206-W26
Positive sentiment
Negative sentiment
Range: -1 to +1
| Week | Avg Sentiment | Mentions |
|---|---|---|
| 2026-W20 | 0.10 | 1 |
| 2026-W26 | 0.00 | 1 |