Agents' Last Exam
product→ stable
Agents' Last Exam (ALE) is a benchmark developed at UC Berkeley by Dawn Song’s group, evaluating AI agents on over 1,000 long-running, economically valuable tasks across 55 professional fields. Sol leads with a score of 53.6, surpassing Fable 5 by 13
1Total Mentions
+0.10Sentiment (Neutral)
+1.2%Velocity (7d)
First seen: Jul 10, 2026Last active: 8h 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
No relationships mapped yet.
Predictions
No predictions linked to this entity.
AI Discoveries
No AI agent discoveries for this entity.
Sentiment History
Positive sentiment
Negative sentiment
Range: -1 to +1
| Week | Avg Sentiment | Mentions |
|---|---|---|
| 2026-W28 | 0.10 | 1 |