Retrieval-Augmented Question Answering on DeepSearch Average
57.1SRActiveContext
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ActiveContextTaskExecutor=Gemini-3.0-flash2026.04 | 57.1 | 6.6 | |
| SynapseTaskExecutor=Gemini-3.0-flash2026.04 | 56.9 | 80.7 | |
| Full ContextTaskExecutor=Gemini-3.0-flash2026.04 | 53.9 | 46.7 | |
| Training-Free GRPOTaskExecutor=Gemini-3.0-flash2026.04 | 49 | 51.1 | |
| Gemini-3.0-flashTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04 | 42.1 | 7.8 | |
| ActiveContextTaskExecutor=Gemini-2.5-flash2026.04 | 41.5 | 7.3 | |
| SynapseTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.04 | 41 | 43.6 | |
| SynapseTaskExecutor=Gemini-2.5-flash2026.04 | 40.7 | 85.9 | |
| SynapseTaskExecutor=gpt-4o2026.04 | 39.1 | 41.9 | |
| Gemini-2.5-flashTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04 | 36.7 | 7.7 | |
| gpt-4oTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04 | 35 | 10.8 | |
| ContextCuratorTaskExecutor=gpt-4o-mini, Category=RL-Trained Curator2026.04 | 34.9 | 7.3 | |
| ActiveContextTaskExecutor=gpt-4o2026.04 | 34.7 | 7.2 | |
| Mem0TaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.04 | 34.7 | 46.6 | |
| Training-Free GRPOTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.04 | 33.7 | 35.7 | |
| Full ContextTaskExecutor=Gemini-2.5-flash2026.04 | 33.4 | 34.4 | |
| Full ContextTaskExecutor=gpt-4o2026.04 | 33.4 | 34.4 | |
| AWMTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.04 | 33.4 | 33.7 | |
| Training-Free GRPOTaskExecutor=gpt-4o2026.04 | 33 | 33.6 | |
| gpt-4o-miniTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04 | 33 | 10.2 | |
| Full ContextTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.04 | 32.7 | 33.2 | |
| Qwen2.5-7B-InstructTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04 | 30.4 | 9.9 | |
| Training-Free GRPOTaskExecutor=Gemini-2.5-flash2026.04 | 29.6 | 76.1 |