List your company

Science Question Answering on GPQA (Exact Match)

70Exact MatchExpRAG
2.419.9537.555.05Nov 25, 2025

Evaluation results

MethodLinks
ExpRAGLLM Backbone=Claude 3.7 Sonnet2025.1170
ReMemLLM Backbone=Claude 3.7 Sonnet2025.1167
DC-RSLLM Backbone=Claude 3.7 Sonnet2025.1162
ExpRecentLLM Backbone=Claude 3.7 Sonnet2025.1161
SelfRAGLLM Backbone=Claude 3.7 Sonnet2025.1158
Mem0LLM Backbone=Claude 3.7 Sonnet2025.1158
ReActLLM Backbone=Claude 3.7 Sonnet2025.1157
DC-CuLLM Backbone=Claude 3.7 Sonnet2025.1157
HistoryLLM Backbone=Claude 3.7 Sonnet2025.1156
BaselineLLM Backbone=Claude 3.7 Sonnet2025.1155
MemOSLLM Backbone=Claude 3.7 Sonnet2025.1155
AmemLLM Backbone=Claude 3.7 Sonnet2025.1154
LangMemLLM Backbone=Claude 3.7 Sonnet2025.1153
AWMLLM Backbone=Claude 3.7 Sonnet2025.1153
LangMemLLM Backbone=Gemini 2.5 Flash2025.1153
AmemLLM Backbone=Gemini 2.5 Flash2025.1152
ReMemLLM Backbone=Gemini 2.5 Flash2025.1151
MemOSLLM Backbone=Gemini 2.5 Flash2025.1150
AWMLLM Backbone=Gemini 2.5 Flash2025.1149
BaselineLLM Backbone=Gemini 2.5 Flash2025.1148
DC-CuLLM Backbone=Gemini 2.5 Flash2025.1148
DC-RSLLM Backbone=Gemini 2.5 Flash2025.1148
SelfRAGLLM Backbone=Gemini 2.5 Flash2025.1146
Mem0LLM Backbone=Gemini 2.5 Flash2025.1145
HistoryLLM Backbone=Gemini 2.5 Flash2025.1143
ExpRecentLLM Backbone=Gemini 2.5 Flash2025.1142
ExpRAGLLM Backbone=Gemini 2.5 Flash2025.1142
ReActLLM Backbone=Gemini 2.5 Flash2025.115