List your company

Deep Search on Deep Search Tasks (test)

91.3Pass@1SALE w/o memory
6.12428.23750.3572.463Feb 2, 2026

Evaluation results

MethodLinks
SALE w/o memoryTask complexity (tau(t))=<= 0.12026.0291.30.24
SALETask complexity (tau(t))=<= 0.12026.0291.30.22
SALETask complexity (tau(t))=<= 0.52026.0288.50.22
Best single agentTask complexity (tau(t))=<= 0.12026.0287.50.36
Best single agentTask complexity (tau(t))=<= 0.52026.0287.50.36
SALE w/o memoryTask complexity (tau(t))=<= 0.52026.0287.50.24
TO-RouterTask complexity (tau(t))=<= 0.12026.0286.30.28
FrugalGPTTask complexity (tau(t))=<= 0.12026.0286.30.47
WTPTask complexity (tau(t))=<= 0.52026.0286.30.33
CARROTTask complexity (tau(t))=<= 0.52026.0286.30.28
TO-RouterTask complexity (tau(t))=<= 0.52026.0286.30.32
CARROTTask complexity (tau(t))=<= 0.12026.02850.27
WTPTask complexity (tau(t))=<= 0.12026.0283.80.32
FrugalGPTTask complexity (tau(t))=<= 0.52026.0281.30.48
SALETask complexity (tau(t))=<= 2.52026.0273.50.23
SALE w/o memoryTask complexity (tau(t))=<= 2.52026.0272.50.25
Best single agentTask complexity (tau(t))=<= 2.52026.0268.80.36
WTPTask complexity (tau(t))=<= 2.52026.0267.50.31
TO-RouterTask complexity (tau(t))=<= 2.52026.0267.50.34
SALETask complexity (tau(t))=All2026.0267.30.21
SALE w/o memoryTask complexity (tau(t))=All2026.0266.40.24
CARROTTask complexity (tau(t))=<= 2.52026.0266.30.29
FrugalGPTTask complexity (tau(t))=<= 2.52026.0266.30.53
Best single agentTask complexity (tau(t))=All2026.0263.80.36
TO-RouterTask complexity (tau(t))=All2026.02630.33
WTPTask complexity (tau(t))=All2026.0262.40.32
CARROTTask complexity (tau(t))=All2026.0261.30.28
FrugalGPTTask complexity (tau(t))=All2026.02610.51
SALETask complexity (tau(t))=<= 12.52026.0237.10.17
SALE w/o memoryTask complexity (tau(t))=<= 12.52026.0235.40.19
WTPTask complexity (tau(t))=<= 12.52026.0234.20.32
Best single agentTask complexity (tau(t))=<= 12.52026.0232.90.36
TO-RouterTask complexity (tau(t))=<= 12.52026.0232.90.36
FrugalGPTTask complexity (tau(t))=<= 12.52026.0230.50.5
CARROTTask complexity (tau(t))=<= 12.52026.0229.30.29
SALETask complexity (tau(t))=<= 602026.0216.30.23
SALE w/o memoryTask complexity (tau(t))=<= 602026.0215.60.26
Best single agentTask complexity (tau(t))=<= 602026.0212.50.36
TO-RouterTask complexity (tau(t))=<= 602026.0212.50.36
FrugalGPTTask complexity (tau(t))=<= 602026.0212.50.6
WTPTask complexity (tau(t))=<= 602026.029.40.31
CARROTTask complexity (tau(t))=<= 602026.029.40.32