SWE-Explore

ai model→ stable

SWE-Explore is a benchmark developed by Microsoft that isolates code search from the repair phase to evaluate AI models' retrieval capabilities independently.

1Total Mentions

-0.20Sentiment (Neutral)

+1.2%Velocity (7d)

View subgraph

First seen: Jun 14, 2026Last active: 11h ago

Signal Radar

Five-axis snapshot of this entity's footprint

live

Loading radar…

Mentions × Lab Attention

Weekly mentions (solid) and average article relevance (dotted)

mentionsrelevance

Loading timeline…

Timeline

Research MilestoneJun 14, 2026
SWE-Explore benchmark released, testing 848 bug-fixing tasks across 203 open-source projects
View source

Relationships

Developed

←
Microsoft
company1 source95% conf.

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