Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,13 @@
|
|
| 10 |
## Introducing Athene-V2-Agent
|
| 11 |
Athene-V2-Agent is an open-source Agent LLM that surpasses the state-of-the-art in function calling and agentic capabilities.
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
💪 **Versatile Agent Capability**: Athene-V2-Agent is an agent model, capable of operating in environments with deeply nested dependencies with the environment. It is capable of reasoning and doing planning for trajectories with many tool calls necessary to answer a single query.
|
| 14 |
|
| 15 |
📊 **Performance Highlights**: Athene-V2-Agent surpasses GPT-4o in single FC tasks by 18% in function calling success rates, and by 17% in Agentic success rates.
|
|
|
|
| 10 |
## Introducing Athene-V2-Agent
|
| 11 |
Athene-V2-Agent is an open-source Agent LLM that surpasses the state-of-the-art in function calling and agentic capabilities.
|
| 12 |
|
| 13 |
+
Benchmark performance:
|
| 14 |
+
|
| 15 |
+
<p align="center" width="100%">
|
| 16 |
+
<a><img src="benchmark.jpg" alt="Benchmark" style="width: 100%; min-width: 300px; display: block; margin: auto;"></a>
|
| 17 |
+
</p>
|
| 18 |
+
|
| 19 |
+
|
| 20 |
💪 **Versatile Agent Capability**: Athene-V2-Agent is an agent model, capable of operating in environments with deeply nested dependencies with the environment. It is capable of reasoning and doing planning for trajectories with many tool calls necessary to answer a single query.
|
| 21 |
|
| 22 |
📊 **Performance Highlights**: Athene-V2-Agent surpasses GPT-4o in single FC tasks by 18% in function calling success rates, and by 17% in Agentic success rates.
|