Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ license: apache-2.0
|
|
| 12 |
|
| 13 |
## Organization Description
|
| 14 |
|
| 15 |
-
**[AutoBench](https://autobench.org/)**
|
| 16 |
|
| 17 |
Pioneering the **"Collective-LLM-as-a-Judge"** methodology, AutoBench uses massive pools of LLMs to dynamically generate tasks, execute multi-turn workflows, and granularly evaluate performance across the AI ecosystem. Today, AutoBench provides fully automated, highly correlated, and strictly un-gameable benchmarking. Furthermore, we leverage the massive synthetic execution datasets generated by our benchmarks to train next-generation **Agentic LLM Routers**, helping agent developers and enterprises optimize for both absolute quality and unit economics.
|
| 18 |
|
|
|
|
| 12 |
|
| 13 |
## Organization Description
|
| 14 |
|
| 15 |
+
**[AutoBench](https://autobench.org/)** is the premier LLM evaluation and routing infra for the Agentic Era. We are dedicated to solving the LLM evaluation crisis by moving the industry beyond static, domain-rigid, easily gameable benchmarks and building the next generation LLM-based API routers for the agentic era.
|
| 16 |
|
| 17 |
Pioneering the **"Collective-LLM-as-a-Judge"** methodology, AutoBench uses massive pools of LLMs to dynamically generate tasks, execute multi-turn workflows, and granularly evaluate performance across the AI ecosystem. Today, AutoBench provides fully automated, highly correlated, and strictly un-gameable benchmarking. Furthermore, we leverage the massive synthetic execution datasets generated by our benchmarks to train next-generation **Agentic LLM Routers**, helping agent developers and enterprises optimize for both absolute quality and unit economics.
|
| 18 |
|