Execution Time Measurement on GAIA
1.6Execution Time (min)EFFGEN
Evaluation Results
| Method | Links | |
|---|---|---|
| EFFGENModel=Qwen2.5 (1.5B)2026.01 | 1.6 | |
| EFFGENModel=Qwen2.5 (3B)2026.01 | 2.5 | |
| AutoGenModel=Qwen2.5 (1.5B)2026.01 | 3.4 | |
| AutoGenModel=Qwen2.5 (7B)2026.01 | 3.8 | |
| AutoGenModel=Qwen2.5 (3B)2026.01 | 4.5 | |
| EFFGENModel=Qwen2.5 (7B)2026.01 | 4.8 | |
| EFFGENModel=Qwen2.5 (14B)2026.01 | 8.2 | |
| AutoGenModel=Qwen2.5 (14B)2026.01 | 8.4 | |
| EFFGENModel=Qwen2.5 (32B)2026.01 | 8.6 | |
| Raw ModelModel=Qwen2.5 (7B)2026.01 | 9.4 | |
| LangChainModel=Qwen2.5 (1.5B)2026.01 | 10.5 | |
| SmolagentsModel=Qwen2.5 (7B)2026.01 | 14.2 | |
| Raw ModelModel=Qwen2.5 (3B)2026.01 | 17.5 | |
| AutoGenModel=Qwen2.5 (32B)2026.01 | 18.6 | |
| LangChainModel=Qwen2.5 (7B)2026.01 | 20.5 | |
| Raw ModelModel=Qwen2.5 (1.5B)2026.01 | 23.2 | |
| LangChainModel=Qwen2.5 (14B)2026.01 | 25.4 | |
| LangChainModel=Qwen2.5 (3B)2026.01 | 27.2 | |
| Raw ModelModel=Qwen2.5 (32B)2026.01 | 28.1 | |
| Raw ModelModel=Qwen2.5 (14B)2026.01 | 28.3 | |
| SmolagentsModel=Qwen2.5 (14B)2026.01 | 29.8 | |
| SmolagentsModel=Qwen2.5 (32B)2026.01 | 34.2 | |
| SmolagentsModel=Qwen2.5 (1.5B)2026.01 | 34.6 | |
| SmolagentsModel=Qwen2.5 (3B)2026.01 | 43.9 | |
| LangChainModel=Qwen2.5 (32B)2026.01 | 74.4 |