Science Question Answering on GPQA (Exact Match)
70Exact MatchExpRAG
Evaluation Results
| Method | Links | |
|---|---|---|
| ExpRAGLLM Backbone=Claude 3.7 Sonnet2025.11 | 70 | |
| ReMemLLM Backbone=Claude 3.7 Sonnet2025.11 | 67 | |
| DC-RSLLM Backbone=Claude 3.7 Sonnet2025.11 | 62 | |
| ExpRecentLLM Backbone=Claude 3.7 Sonnet2025.11 | 61 | |
| SelfRAGLLM Backbone=Claude 3.7 Sonnet2025.11 | 58 | |
| Mem0LLM Backbone=Claude 3.7 Sonnet2025.11 | 58 | |
| ReActLLM Backbone=Claude 3.7 Sonnet2025.11 | 57 | |
| DC-CuLLM Backbone=Claude 3.7 Sonnet2025.11 | 57 | |
| HistoryLLM Backbone=Claude 3.7 Sonnet2025.11 | 56 | |
| BaselineLLM Backbone=Claude 3.7 Sonnet2025.11 | 55 | |
| MemOSLLM Backbone=Claude 3.7 Sonnet2025.11 | 55 | |
| AmemLLM Backbone=Claude 3.7 Sonnet2025.11 | 54 | |
| LangMemLLM Backbone=Claude 3.7 Sonnet2025.11 | 53 | |
| AWMLLM Backbone=Claude 3.7 Sonnet2025.11 | 53 | |
| LangMemLLM Backbone=Gemini 2.5 Flash2025.11 | 53 | |
| AmemLLM Backbone=Gemini 2.5 Flash2025.11 | 52 | |
| ReMemLLM Backbone=Gemini 2.5 Flash2025.11 | 51 | |
| MemOSLLM Backbone=Gemini 2.5 Flash2025.11 | 50 | |
| AWMLLM Backbone=Gemini 2.5 Flash2025.11 | 49 | |
| BaselineLLM Backbone=Gemini 2.5 Flash2025.11 | 48 | |
| DC-CuLLM Backbone=Gemini 2.5 Flash2025.11 | 48 | |
| DC-RSLLM Backbone=Gemini 2.5 Flash2025.11 | 48 | |
| SelfRAGLLM Backbone=Gemini 2.5 Flash2025.11 | 46 | |
| Mem0LLM Backbone=Gemini 2.5 Flash2025.11 | 45 | |
| HistoryLLM Backbone=Gemini 2.5 Flash2025.11 | 43 | |
| ExpRecentLLM Backbone=Gemini 2.5 Flash2025.11 | 42 | |
| ExpRAGLLM Backbone=Gemini 2.5 Flash2025.11 | 42 | |
| ReActLLM Backbone=Gemini 2.5 Flash2025.11 | 5 |