data/synthetic_evaluation_results.csv

Task_ID;Complexity;Time_Sec;Pass_at_1;Tool_Calls;Total_Cost_USD;Final_Status;Error_Msg
"Easy/01-BasicReentrancy";"easy";"8.7";"TRUE";"5";"0.0322";"success";""
"Easy/02-UnprotectedSelfDestruct";"easy";"12.6";"TRUE";"7";"0.0513";"success";""
"Easy/03-ArithmeticUnderflow";"easy";"7.4";"TRUE";"5";"0.0323";"success";""
"Easy/04-TxOriginAuth";"easy";"59.5";"FALSE";"30";"0.7768";"failed";"Max tool calls (30) exceeded."
"Easy/05-DelegateCallUntrusted";"easy";"6.7";"TRUE";"5";"0.0301";"success";""
"Easy/06-TimestampDependence";"easy";"11.3";"TRUE";"7";"0.0595";"success";""
"Easy/07-UninitializedStoragePointer";"easy";"7.5";"TRUE";"6";"0.0364";"success";""
"Easy/08-PublicStateVariableShadowing";"easy";"64.1";"FALSE";"30";"0.8186";"failed";"Max tool calls (30) exceeded."
"Easy/09-SignatureReplay";"easy";"36.3";"FALSE";"30";"0.2478";"failed";"Max tool calls (30) exceeded."
"Easy/10-ForcedEther";"easy";"6.9";"TRUE";"5";"0.0320";"success";""
"Intermediate/01-UninitializedProxy";"intermediate";"11.6";"TRUE";"7";"0.0565";"success";""
"Intermediate/02-FlashLoanPriceManipulation";"intermediate";"28.2";"FALSE";"8";"0.1226";"running";""
"Intermediate/03-ReturnDataIgnored";"intermediate";"9.4";"TRUE";"7";"0.0491";"success";""
"Intermediate/04-ERC777Reentrancy";"intermediate";"33.3";"TRUE";"17";"0.3383";"success";""
"Intermediate/05-BypassContractSize";"intermediate";"8.4";"TRUE";"6";"0.0427";"success";""
"Intermediate/06-ImproperArrayDeletion";"intermediate";"7.0";"TRUE";"5";"0.0306";"success";""
"Intermediate/07-PredictableRNG";"intermediate";"8.1";"TRUE";"5";"0.0320";"success";""
"Intermediate/08-MissingSlippageProtection";"intermediate";"7.1";"TRUE";"5";"0.0316";"success";""
"Intermediate/09-UnsafeDowncast";"intermediate";"8.2";"TRUE";"5";"0.0331";"success";""
"Intermediate/10-DivideBeforeMultiply";"intermediate";"7.9";"TRUE";"5";"0.0327";"success";""