List your company

Web-based Question Answering on WebWalkerQA

81.18Success RateMemEvolve + Flash-Searcher
51.196858.980966.76574.5491Dec 21, 2025

Evaluation results

MethodLinks
MemEvolve + Flash-SearcherModel Family=GPT-5-mini, pass@k=32025.1281.18
MemEvolve + Flash-SearcherModel Family=GPT-5-mini, pass@k=22025.1279.41
MemEvolve + Flash-SearcherModel Family=GPT-5-mini, pass@k=12025.1274.71
Agent KBModel Family=GPT-4.1, pass@k=32025.1273.53
MemEvolve + Flash-SearcherModel Family=DeepSeek V3.2, pass@k=12025.1272.35
Flash-SearcherModel Family=GPT-5-mini, pass@k=12025.1271.18
MemEvolve + SmolAgentModel Family=GPT-5-mini, pass@k=32025.1271.18
Flash-SearcherModel Family=DeepSeek V3.2, pass@k=12025.1269.41
MemEvolve + Flash-SearcherModel Family=Kimi K2, pass@k=12025.1269.41
Agent KBModel Family=GPT-4.1, pass@k=22025.1268.82
MemEvolve + SmolAgentModel Family=GPT-5-mini, pass@k=22025.1267.06
MemEvolve + SmolAgentModel Family=GPT-5-mini, pass@k=12025.1261.18
Cognitive Kernel-ProModel Family=Claude-3.7 etc., pass@k=12025.1260.64
Agent KBModel Family=GPT-4.1, pass@k=12025.1260.59
SmolagentsModel Family=GPT-5-mini2025.1258.82
OAgentsModel Family=Claude-3.7 etc.2025.1258.23
OWL WorkforceModel Family=GPT-4o+o3-mini, pass@k=32025.1257.64
Flash-SearcherModel Family=Kimi K2, pass@k=12025.1252.35