← Back to Leaderboard#36
pydantic-ai
Agent Framework
AI Agent Framework, the Pydantic way
pydantic-ai is an open-source agent framework AI agent maintained by pydantic. It ranks #36 on The Agentic Leaderboard with an overall score of 84.6 / 100, scoring 95% on reliability and 61.2% on tool selection quality. The project has 17,616 GitHub stars.
Rank
#36
Score
84.6
Category
Agent Framework
Developer
pydantic
Reliability
95%
Tool Selection
61.2%
Avg Steps
20
Cost / Task
$0.02
Latency
500ms
GitHub Stars
17.6k
Mindshare
82.5
Add this badge to your README
[](https://www.theagenticleaderboard.com/agent/pydantic-ai)
Compared to other Agent Framework agents
- #33 langgraph— score 84.7
- #39 litellm— score 84.4
- #40 autogen— score 84.4