List your company

Tool-use Reasoning on ToolBench

88API Success RateExpRAG
60.9667.987582.02Nov 25, 2025

Evaluation results

MethodLinks
ExpRAGLLM Backbone=Claude 3.7 Sonnet2025.118872
ReMemLLM Backbone=Claude 3.7 Sonnet2025.118771
ExpRAGLLM Backbone=Gemini 2.5 Flash2025.118773
ReMemLLM Backbone=Gemini 2.5 Flash2025.118571
ExpRecentLLM Backbone=Claude 3.7 Sonnet2025.118266
ExpRecentLLM Backbone=Gemini 2.5 Flash2025.117866
AmemLLM Backbone=Claude 3.7 Sonnet2025.117763
SelfRAGLLM Backbone=Claude 3.7 Sonnet2025.117763
LangMemLLM Backbone=Claude 3.7 Sonnet2025.117763
DC-CuLLM Backbone=Claude 3.7 Sonnet2025.117762
DC-RSLLM Backbone=Claude 3.7 Sonnet2025.117762
BaselineLLM Backbone=Claude 3.7 Sonnet2025.117662
HistoryLLM Backbone=Claude 3.7 Sonnet2025.117661
ReActLLM Backbone=Claude 3.7 Sonnet2025.117661
MemOSLLM Backbone=Claude 3.7 Sonnet2025.117662
Mem0LLM Backbone=Claude 3.7 Sonnet2025.117661
AWMLLM Backbone=Claude 3.7 Sonnet2025.117662
AmemLLM Backbone=Gemini 2.5 Flash2025.117260
SelfRAGLLM Backbone=Gemini 2.5 Flash2025.117261
BaselineLLM Backbone=Gemini 2.5 Flash2025.117161
MemOSLLM Backbone=Gemini 2.5 Flash2025.117161
Mem0LLM Backbone=Gemini 2.5 Flash2025.117161
AWMLLM Backbone=Gemini 2.5 Flash2025.117159
DC-CuLLM Backbone=Gemini 2.5 Flash2025.117059
LangMemLLM Backbone=Gemini 2.5 Flash2025.116857
DC-RSLLM Backbone=Gemini 2.5 Flash2025.116857
ReActLLM Backbone=Gemini 2.5 Flash2025.116457
HistoryLLM Backbone=Gemini 2.5 Flash2025.116254