List your company

Multi-Hop Question Answering on 2WikiMultihopQA (Pass@1)

82Pass@1Mem2Evolve
47.05656.12865.274.272Apr 13, 2026

Evaluation results

MethodLinks
Mem2EvolveBackbone=GPT-5-Chat2026.0482
GPT-5-Chat (Direct)Backbone=GPT-5-Chat2026.0481.8
SwarmAgenticBackbone=GPT-5-Chat2026.0480
AlitaBackbone=GPT-5-Chat2026.0477.4
DSPyBackbone=GPT-5-Chat2026.0476.4
EvoAgentBackbone=GPT-5-Chat2026.0475
AgentVerseBackbone=GPT-5-Chat2026.0474.6
GPT-5-Chat (CoT)Backbone=GPT-5-Chat2026.0474.4
AutoAgentsBackbone=GPT-5-Chat2026.0473.8
AFLOWBackbone=GPT-5-Chat2026.0472.4
DyLANBackbone=GPT-5-Chat2026.0465
GPT-5-Chat (ReAct)Backbone=GPT-5-Chat2026.0448.4