Mathematical Reasoning on AIME 25 (Exact Match)
57Exact MatchAmem
Evaluation Results
| Method | Links | |
|---|---|---|
| AmemLLM Backbone=Gemini 2.5 Flash2025.11 | 57 | |
| ReMemLLM Backbone=Gemini 2.5 Flash2025.11 | 53 | |
| LangMemLLM Backbone=Gemini 2.5 Flash2025.11 | 50 | |
| BaselineLLM Backbone=Gemini 2.5 Flash2025.11 | 47 | |
| HistoryLLM Backbone=Gemini 2.5 Flash2025.11 | 47 | |
| SelfRAGLLM Backbone=Gemini 2.5 Flash2025.11 | 47 | |
| MemOSLLM Backbone=Gemini 2.5 Flash2025.11 | 47 | |
| Mem0LLM Backbone=Gemini 2.5 Flash2025.11 | 47 | |
| ExpRecentLLM Backbone=Gemini 2.5 Flash2025.11 | 47 | |
| ExpRAGLLM Backbone=Gemini 2.5 Flash2025.11 | 47 | |
| DC-CuLLM Backbone=Gemini 2.5 Flash2025.11 | 40 | |
| DC-RSLLM Backbone=Gemini 2.5 Flash2025.11 | 37 | |
| AWMLLM Backbone=Gemini 2.5 Flash2025.11 | 37 | |
| ReActLLM Backbone=Gemini 2.5 Flash2025.11 | 27 | |
| HistoryLLM Backbone=Claude 3.7 Sonnet2025.11 | 23 | |
| DC-CuLLM Backbone=Claude 3.7 Sonnet2025.11 | 23 | |
| MemOSLLM Backbone=Claude 3.7 Sonnet2025.11 | 20 | |
| DC-RSLLM Backbone=Claude 3.7 Sonnet2025.11 | 20 | |
| ExpRecentLLM Backbone=Claude 3.7 Sonnet2025.11 | 20 | |
| AmemLLM Backbone=Claude 3.7 Sonnet2025.11 | 17 | |
| ExpRAGLLM Backbone=Claude 3.7 Sonnet2025.11 | 17 | |
| BaselineLLM Backbone=Claude 3.7 Sonnet2025.11 | 13 | |
| Mem0LLM Backbone=Claude 3.7 Sonnet2025.11 | 13 | |
| LangMemLLM Backbone=Claude 3.7 Sonnet2025.11 | 13 | |
| ReMemLLM Backbone=Claude 3.7 Sonnet2025.11 | 13 | |
| ReActLLM Backbone=Claude 3.7 Sonnet2025.11 | 10 | |
| SelfRAGLLM Backbone=Claude 3.7 Sonnet2025.11 | 10 | |
| AWMLLM Backbone=Claude 3.7 Sonnet2025.11 | 3 |