List your company

Data Science Agent tasks on xBench-DS

73Pass@1MIRO-30B + MIROFLOW
-2.431217.151936.73556.3181Feb 8, 2026Feb 12, 2026Feb 17, 2026Feb 21, 2026Feb 26, 2026Mar 2, 2026Mar 7, 2026

Evaluation results

MethodLinks
MIRO-30B + MIROFLOWCategory=OPEN-SOURCE2026.0373
MIRO-30B + WEDASCategory=OPEN-SOURCE2026.0372
WEBSAILOR-72BCategory=OPEN-SOURCE2026.0355
WEBSAILOR-32BCategory=OPEN-SOURCE2026.0353.3
GROK-DEEPRESEARCHCategory=CLOSED-SOURCE2026.0352
DOUBAO-DEEPTHINKCategory=CLOSED-SOURCE2026.0350
GPT-5-MINI + WEDASCategory=OPEN-SOURCE2026.0344
ASEARCHER-WEB-32BCategory=OPEN-SOURCE2026.0342.1
WEBDANCER-QWQ-32BCategory=OPEN-SOURCE2026.0338.3
GPT-5-MINI + MIROFLOWCategory=OPEN-SOURCE2026.0338
SEARCH-O1-32BCategory=OPEN-SOURCE2026.0325
WEBTHINKER-32B-RLCategory=OPEN-SOURCE2026.0324
O4-MINICategory=DIRECT INFERENCE2026.0322.3
GPT-4OCategory=DIRECT INFERENCE2026.0318
GPT-4.1Category=DIRECT INFERENCE2026.0317
QWEN-2.5-72BCategory=DIRECT INFERENCE2026.0312.7
QWQ-32BCategory=DIRECT INFERENCE2026.0310.7
QWEN-2.5-32BCategory=DIRECT INFERENCE2026.038.7
TodoEvolve + SmolagentsModel Family=GPT-5-Mini, pass@k protocol=pass@12026.020.75
TodoEvolve + SmolagentsModel Family=DeepSeek V3.2, pass@k protocol=pass@12026.020.74
TodoEvolve + SmolagentsModel Family=Kimi K2, pass@k protocol=pass@12026.020.71
Flash-SearcherModel Family=GPT-5-mini, pass@k protocol=pass@12026.020.69
Agent KBModel Family=GPT-4.1, pass@k protocol=pass@32026.020.68
Flash-SearcherModel Family=DeepSeek V3.2, pass@k protocol=pass@12026.020.68
Flash-SearcherModel Family=Kimi K2, pass@k protocol=pass@12026.020.66
Agent KBModel Family=GPT-4.1, pass@k protocol=pass@22026.020.58
Cognitive Kernel-ProModel Family=Claude-3.7 etc., pass@k protocol=pass@12026.020.56
OWL WorkforceModel Family=GPT-4o+o3-mini, pass@k protocol=pass@32026.020.55
SmolagentsModel Family=GPT-5-mini, pass@k protocol=pass@12026.020.51
Agent KBModel Family=GPT-4.1, pass@k protocol=pass@12026.020.48
OAgentsModel Family=Claude-3.7 etc., pass@k protocol=pass@12026.020.47