List your company
ResearchFormerly WizWand

Mathematical Reasoning on AIME24 (Exact Match)

70Exact MatchAmem
0.3218.4136.554.59Nov 25, 2025
Updated 5mo ago

Evaluation results

MethodLinks
AmemLLM Backbone=Gemini 2.5 Flash2025.1170
HistoryLLM Backbone=Gemini 2.5 Flash2025.1160
DC-CuLLM Backbone=Gemini 2.5 Flash2025.1160
ReMemLLM Backbone=Gemini 2.5 Flash2025.1160
DC-RSLLM Backbone=Gemini 2.5 Flash2025.1153
SelfRAGLLM Backbone=Gemini 2.5 Flash2025.1150
Mem0LLM Backbone=Gemini 2.5 Flash2025.1150
AWMLLM Backbone=Gemini 2.5 Flash2025.1150
BaselineLLM Backbone=Gemini 2.5 Flash2025.1147
MemOSLLM Backbone=Gemini 2.5 Flash2025.1147
ExpRecentLLM Backbone=Gemini 2.5 Flash2025.1147
LangMemLLM Backbone=Gemini 2.5 Flash2025.1143
ExpRAGLLM Backbone=Gemini 2.5 Flash2025.1143
ReActLLM Backbone=Gemini 2.5 Flash2025.1130
AmemLLM Backbone=Claude 3.7 Sonnet2025.1127
SelfRAGLLM Backbone=Claude 3.7 Sonnet2025.1120
Mem0LLM Backbone=Claude 3.7 Sonnet2025.1120
DC-RSLLM Backbone=Claude 3.7 Sonnet2025.1120
BaselineLLM Backbone=Claude 3.7 Sonnet2025.1117
ReActLLM Backbone=Claude 3.7 Sonnet2025.1117
MemOSLLM Backbone=Claude 3.7 Sonnet2025.1117
DC-CuLLM Backbone=Claude 3.7 Sonnet2025.1117
ExpRAGLLM Backbone=Claude 3.7 Sonnet2025.1117
HistoryLLM Backbone=Claude 3.7 Sonnet2025.1113
ExpRecentLLM Backbone=Claude 3.7 Sonnet2025.1113
ReMemLLM Backbone=Claude 3.7 Sonnet2025.1113
LangMemLLM Backbone=Claude 3.7 Sonnet2025.1110
AWMLLM Backbone=Claude 3.7 Sonnet2025.113