News Aggregation on T1 News 1.0 (test)
89.2Task Completion RateLangChain
Evaluation Results
| Method | Links | |
|---|---|---|
| LangChain2026.01 | 89.2 | |
| AgentForge2026.01 | 87.3 | |
| AutoGPT2026.01 | 78.5 | |
| Direct API2026.01 | 72 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| LangChain2026.01 | 89.2 | |
| AgentForge2026.01 | 87.3 | |
| AutoGPT2026.01 | 78.5 | |
| Direct API2026.01 | 72 |