Skip to content
← All cases

column_drift

column_drift-2026100004

Column names and order change partway through the CSV.

expects column_drift

Statement files

12 highlighted lines differ from the same seed rendered without perturbations. That difference is the trap.

bnp_camt053.xmlUntouched by this perturbation
<?xml version='1.0' encoding='utf-8'?>
<Document xmlns="urn:iso:std:iso:20022:tech:xsd:camt.053.001.02">
<BkToCstmrStmt>
<GrpHdr>
<MsgId>LB-acct-2026100004-2-2025-04-30</MsgId>
<CreDtTm>2025-04-30T23:59:00+00:00</CreDtTm>
</GrpHdr>
<Stmt>
<Id>acct-2026100004-2</Id>
<ElctrncSeqNb>1</ElctrncSeqNb>
<CreDtTm>2025-04-30T23:59:00+00:00</CreDtTm>
<FrToDt>
<FrDtTm>2025-04-01T00:00:00+00:00</FrDtTm>
<ToDtTm>2025-04-30T23:59:59+00:00</ToDtTm>
</FrToDt>
<Acct>
<Id>
<IBAN>GB66LBEN19841540885057</IBAN>
</Id>
<Ccy>GBP</Ccy>
</Acct>
<Bal>
<Tp>
<CdOrPrtry>
<Cd>OPBD</Cd>
</CdOrPrtry>
</Tp>
<Amt Ccy="GBP">151264.77</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Dt>
<Dt>2025-04-01</Dt>
</Dt>
</Bal>
<Ntry>
<Amt Ccy="GBP">14744.28</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-02</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-02</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t019</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD BRAMBLE LOGISTICS REF626785</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">3466.41</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-03</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-03</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t004</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD CASTLEGATE PROPERTY REF999283</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">2535.46</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-03</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-03</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t008</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPI HARBOURLIGHT IT REF699366</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">12894.75</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-05</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-05</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t013</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD IRONBRIDGE TOOLING REF562101</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">9738.55</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-07</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-07</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t010</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD MOORLAND TELECOM REF922328</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">13613.22</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-10</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-10</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t003</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>TFR IRONBRIDGE TOOLING REF642375</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">837.76</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-10</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-10</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t014</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>TFR FENWICK &amp; PARTNERS REF967146</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">4305.01</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-11</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-11</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t005</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO JUNIPER PAYROLL REF364184</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">11389.08</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-13</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-13</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t015</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD OSPREY LEASING REF887447</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">2424.67</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-14</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-14</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t006</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>CR LARKSPUR TRAVEL REF378974</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">10194.51</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-16</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-16</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t002</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD EASTFIELD ENERGY REF760923</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">1665.35</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-17</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-17</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t009</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPI HARBOURLIGHT IT REF869130</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">3303.81</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-19</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-19</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t012</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO DELPHINIUM MEDIA REF803758</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">10856.27</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-20</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-20</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t018</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>CR LARKSPUR TRAVEL REF688788</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">9093.36</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-22</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-22</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t011</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPO DELPHINIUM MEDIA REF296506</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">1652.59</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-22</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-22</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t017</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>CR MOORLAND TELECOM REF941401</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">10234.86</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-25</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-25</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t001</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP HARBOURLIGHT IT REF293551</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">6625.88</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-27</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-27</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t007</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO KESTREL INSURANCE REF196849</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">6034.06</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-04-30</Dt>
</BookgDt>
<ValDt>
<Dt>2025-04-30</Dt>
</ValDt>
<AcctSvcrRef>acct-2026100004-2-t016</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPI MOORLAND TELECOM REF296134</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
</Stmt>
</BkToCstmrStmt>
</Document>
hsbc_statement.xlsxUntouched by this perturbation
[sheet: Statement]
HSBC Bank plc
Business Current Account Statement
Account name: LEDGERBENCH DEMO LTD
Sort code / Account number: 42-33-29 41366294
Account reference: acct-2026100004-1
Statement period: 01 Apr 2025 to 30 Apr 2025
Currency: GBP
Opening balance: 16260.89
Date Payment type Details Paid out Paid in
01 Apr 2025 TFR LARKSPUR TRAVEL REF312489 3722.86
01 Apr 2025 SO CASTLEGATE PROPERTY REF501932 5204.87
01 Apr 2025 FPO AURORA CONSULTING LTD REF862023 3049.90
02 Apr 2025 TFR JUNIPER PAYROLL REF824772 9874.26
03 Apr 2025 CR JUNIPER PAYROLL REF385644 11476.70
05 Apr 2025 DD DELPHINIUM MEDIA REF983784 1816.18
06 Apr 2025 BP OSPREY LEASING REF613348 8549.38
06 Apr 2025 CR LARKSPUR TRAVEL REF180324 7647.10
08 Apr 2025 SO LARKSPUR TRAVEL REF368971 10586.30
09 Apr 2025 SO GREENHOLM FOODS REF277432 6699.88
09 Apr 2025 FPI JUNIPER PAYROLL REF749935 1063.08
12 Apr 2025 FPI HARBOURLIGHT IT REF937048 12854.37
12 Apr 2025 TFR IRONBRIDGE TOOLING REF580622 260.50
14 Apr 2025 DD OSPREY LEASING REF239546 6564.87
14 Apr 2025 CR DELPHINIUM MEDIA REF594696 6866.86
14 Apr 2025 DD EASTFIELD ENERGY REF862549 5802.54
15 Apr 2025 CR OSPREY LEASING REF559124 10196.13
15 Apr 2025 SO OSPREY LEASING REF273632 14616.73
19 Apr 2025 FPI MOORLAND TELECOM REF566348 6566.70
21 Apr 2025 BP DELPHINIUM MEDIA REF874406 4650.30
24 Apr 2025 BP IRONBRIDGE TOOLING REF342949 3664.58
26 Apr 2025 BP CASTLEGATE PROPERTY REF426112 5730.63
27 Apr 2025 CR CASTLEGATE PROPERTY REF794239 5203.36
27 Apr 2025 DD LARKSPUR TRAVEL REF184375 7909.73
28 Apr 2025 FPO KESTREL INSURANCE REF201345 11558.07
28 Apr 2025 TFR NORTHGATE CLEANING REF668983 313.62
29 Apr 2025 FPO KESTREL INSURANCE REF689748 8580.08
29 Apr 2025 TFR BRAMBLE LOGISTICS REF456447 3599.95
rbs_transactions.csv12 changed lines · first at line 13
"Date","Type","Description","Value","Account Name","Account Number","Ledger Ref"
"01/04/2025","BAL","OPENING BALANCE","183182.30","LEDGERBENCH DEMO LTD","81-21-49 44551244","acct-2026100004-3"
"02/04/2025","FPI","FPI KESTREL INSURANCE REF713432","669.43","LEDGERBENCH DEMO LTD","81-21-49 44551244","acct-2026100004-3"
"04/04/2025","CR","CR LARKSPUR TRAVEL REF418667","11138.75","LEDGERBENCH DEMO LTD","81-21-49 44551244","acct-2026100004-3"
"06/04/2025","DD","DD EASTFIELD ENERGY REF445151","-13422.05","LEDGERBENCH DEMO LTD","81-21-49 44551244","acct-2026100004-3"
"06/04/2025","BP","BP GREENHOLM FOODS REF110108","-5156.98","LEDGERBENCH DEMO LTD","81-21-49 44551244","acct-2026100004-3"
"08/04/2025","TFR","TFR OSPREY LEASING REF181330","1522.24","LEDGERBENCH DEMO LTD","81-21-49 44551244","acct-2026100004-3"
"10/04/2025","CR","CR LARKSPUR TRAVEL REF174145","10996.86","LEDGERBENCH DEMO LTD","81-21-49 44551244","acct-2026100004-3"
"11/04/2025","BP","BP OSPREY LEASING REF632723","-7448.34","LEDGERBENCH DEMO LTD","81-21-49 44551244","acct-2026100004-3"
"12/04/2025","DD","DD LARKSPUR TRAVEL REF755492","-2298.12","LEDGERBENCH DEMO LTD","81-21-49 44551244","acct-2026100004-3"
"13/04/2025","FPI","FPI JUNIPER PAYROLL REF969606","11274.86","LEDGERBENCH DEMO LTD","81-21-49 44551244","acct-2026100004-3"
"13/04/2025","BP","BP FENWICK & PARTNERS REF324092","-11632.94","LEDGERBENCH DEMO LTD","81-21-49 44551244","acct-2026100004-3"
"Narrative","Account Name","Transaction Type","Ledger Ref","Account Number","Amount","Posting Date"
"BP BRAMBLE LOGISTICS REF261659","LEDGERBENCH DEMO LTD","BP","acct-2026100004-3","81-21-49 44551244","-1890.28","14/04/2025"
"BP BRAMBLE LOGISTICS REF809931","LEDGERBENCH DEMO LTD","BP","acct-2026100004-3","81-21-49 44551244","-2418.53","20/04/2025"
"FPI JUNIPER PAYROLL REF176451","LEDGERBENCH DEMO LTD","FPI","acct-2026100004-3","81-21-49 44551244","3076.30","20/04/2025"
"FPO HARBOURLIGHT IT REF432189","LEDGERBENCH DEMO LTD","FPO","acct-2026100004-3","81-21-49 44551244","-1463.39","21/04/2025"
"TFR NORTHGATE CLEANING REF965734","LEDGERBENCH DEMO LTD","TFR","acct-2026100004-3","81-21-49 44551244","5765.62","21/04/2025"
"CR GREENHOLM FOODS REF155156","LEDGERBENCH DEMO LTD","CR","acct-2026100004-3","81-21-49 44551244","12686.61","21/04/2025"
"TFR NORTHGATE CLEANING REF671876","LEDGERBENCH DEMO LTD","TFR","acct-2026100004-3","81-21-49 44551244","5210.72","26/04/2025"
"SO AURORA CONSULTING LTD REF830620","LEDGERBENCH DEMO LTD","SO","acct-2026100004-3","81-21-49 44551244","-8994.84","26/04/2025"
"FPO DELPHINIUM MEDIA REF895113","LEDGERBENCH DEMO LTD","FPO","acct-2026100004-3","81-21-49 44551244","-11331.21","27/04/2025"
"FPO FENWICK & PARTNERS REF763268","LEDGERBENCH DEMO LTD","FPO","acct-2026100004-3","81-21-49 44551244","-11718.07","28/04/2025"
"FPI FENWICK & PARTNERS REF109159","LEDGERBENCH DEMO LTD","FPI","acct-2026100004-3","81-21-49 44551244","13251.14","29/04/2025"
 

Ground truth

Public here because the benchmark is open; it is the model's prompt path that can never reach these values, not human readers.

AccountClosing balance
acct-2026100004-1−£9,077.66
acct-2026100004-2£94,893.65
acct-2026100004-3£181,000.08

Recorded runs on this case

  • exactSingle prompt2 steps · 10,095 tokens · Confidence medium

    Model claude-sonnet-4-6Measured 2026-08-20Bench v1.0Run 11eaa71b2d02Commit 3d38c30

  • exactAgent with tools17 steps · 27,761 tokens · Confidence high

    Model claude-sonnet-4-6Measured 2026-08-20Bench v1.0Run f140aa1e57f4Commit 384d72d

Step through any of these on the demo page.