Agentic Evaluation on SimpleQA
84AccuracyEFFGEN
Evaluation Results
| Method | Links | |
|---|---|---|
| EFFGENModel=Qwen2.5-32B-Instruct2026.01 | 84 | |
| EFFGENModel=Gemma 3 (27B)2026.01 | 80 | |
| EFFGENModel=Qwen2.5-7B-Instruct2026.01 | 76 | |
| EFFGENModel=GPT-OSS (20B)2026.01 | 74 | |
| EFFGENModel=Qwen2.5-14B-Instruct2026.01 | 72 | |
| EFFGENModel=Gemma 3 (12B)2026.01 | 70 | |
| AutogenModel=Qwen2.5-32B-Instruct2026.01 | 70 | |
| AutoGenModel=Gemma 3 (27B)2026.01 | 66 | |
| EFFGENModel=Qwen2.5-3B-Instruct2026.01 | 58 | |
| AutogenModel=Qwen2.5-14B-Instruct2026.01 | 58 | |
| LangChainModel=Qwen2.5-32B-Instruct2026.01 | 54 | |
| EFFGENModel=Gemma 3 (4B)2026.01 | 52 | |
| SmolagentsModel=Qwen2.5-32B-Instruct2026.01 | 52 | |
| LangChainModel=Gemma 3 (27B)2026.01 | 50 | |
| AutoGenModel=GPT-OSS (20B)2026.01 | 50 | |
| SmolagentsModel=Gemma 3 (27B)2026.01 | 48 | |
| AutogenModel=Qwen2.5-7B-Instruct2026.01 | 46 | |
| SmolagentsModel=Qwen2.5-14B-Instruct2026.01 | 46 | |
| LangChainModel=Qwen2.5-14B-Instruct2026.01 | 46 | |
| AutoGenModel=Gemma 3 (12B)2026.01 | 42 | |
| EFFGENModel=Qwen2.5-1.5B-Instruct2026.01 | 40 | |
| LangChainModel=GPT-OSS (20B)2026.01 | 38 | |
| SmolagentsModel=GPT-OSS (20B)2026.01 | 34 | |
| LangChainModel=Qwen2.5-7B-Instruct2026.01 | 34 | |
| EFFGENModel=Gemma 3 (1B)2026.01 | 32 | |
| SmolagentsModel=Qwen2.5-7B-Instruct2026.01 | 32 | |
| LangChainModel=Gemma 3 (12B)2026.01 | 30 | |
| SmolagentsModel=Gemma 3 (12B)2026.01 | 28 | |
| SmolagentsModel=Qwen2.5-3B-Instruct2026.01 | 22 | |
| SmolagentsModel=Gemma 3 (4B)2026.01 | 18 | |
| SmolagentsModel=Qwen2.5-1.5B-Instruct2026.01 | 18 | |
| SmolagentsModel=Gemma 3 (1B)2026.01 | 14 | |
| AutogenModel=Qwen2.5-3B-Instruct2026.01 | 14 | |
| Raw ModelModel=Qwen2.5-32B-Instruct2026.01 | 14 | |
| AutoGenModel=Gemma 3 (4B)2026.01 | 12 | |
| Raw ModelModel=Gemma 3 (27B)2026.01 | 12 | |
| LangChainModel=Qwen2.5-1.5B-Instruct2026.01 | 12 | |
| LangChainModel=Qwen2.5-3B-Instruct2026.01 | 12 | |
| LangChainModel=Gemma 3 (1B)2026.01 | 10 | |
| LangChainModel=Gemma 3 (4B)2026.01 | 10 | |
| AutogenModel=Qwen2.5-1.5B-Instruct2026.01 | 10 | |
| AutoGenModel=Gemma 3 (1B)2026.01 | 8 | |
| Raw ModelModel=GPT-OSS (20B)2026.01 | 8 | |
| Raw ModelModel=Qwen2.5-14B-Instruct2026.01 | 8 | |
| Raw ModelModel=Gemma 3 (12B)2026.01 | 6 | |
| Raw ModelModel=Qwen2.5-7B-Instruct2026.01 | 6 | |
| Raw ModelModel=Gemma 3 (4B)2026.01 | 4 | |
| Raw ModelModel=Qwen2.5-1.5B-Instruct2026.01 | 4 | |
| Raw ModelModel=Gemma 3 (1B)2026.01 | 3 | |
| Raw ModelModel=Qwen2.5-3B-Instruct2026.01 | 2 |