List your company

Data Science Task Automation on xBench-DS

78ScoreMemEvolve + Flash-Searcher
45.7654.1362.570.87Dec 21, 2025

Evaluation results

MethodLinks
MemEvolve + Flash-SearcherModel Family=GPT-5-mini, pass@k=32025.1278
MemEvolve + Flash-SearcherModel Family=GPT-5-mini, pass@k=22025.1277
MemEvolve + Flash-SearcherModel Family=GPT-5-mini, pass@k=12025.1274
MemEvolve + Flash-SearcherModel Family=DeepSeek V3.2, pass@k=12025.1270
Flash-SearcherModel Family=GPT-5-mini, pass@k=12025.1269
Agent KBModel Family=GPT-4.1, pass@k=32025.1268
Flash-SearcherModel Family=DeepSeek V3.2, pass@k=12025.1268
MemEvolve + SmolAgentModel Family=GPT-5-mini, pass@k=32025.1268
MemEvolve + Flash-SearcherModel Family=Kimi K2, pass@k=12025.1268
Flash-SearcherModel Family=Kimi K2, pass@k=12025.1266
MemEvolve + SmolAgentModel Family=GPT-5-mini, pass@k=22025.1263
Agent KBModel Family=GPT-4.1, pass@k=22025.1258
MemEvolve + SmolAgentModel Family=GPT-5-mini, pass@k=12025.1257
Cognitive Kernel-ProModel Family=Claude-3.7 etc., pass@k=12025.1256
OWL WorkforceModel Family=GPT-4o+o3-mini, pass@k=32025.1255
SmolagentsModel Family=GPT-5-mini2025.1251
Agent KBModel Family=GPT-4.1, pass@k=12025.1248
OAgentsModel Family=Claude-3.7 etc.2025.1247