Skip to content
← All cases

clean

clean-2026000003

No perturbation: this case checks that the agent does not invent problems.

No flag expected

Statement files

These files are the untouched baseline for seed 2026000003.

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-2026000003-2-2025-08-31</MsgId>
<CreDtTm>2025-08-31T23:59:00+00:00</CreDtTm>
</GrpHdr>
<Stmt>
<Id>acct-2026000003-2</Id>
<ElctrncSeqNb>1</ElctrncSeqNb>
<CreDtTm>2025-08-31T23:59:00+00:00</CreDtTm>
<FrToDt>
<FrDtTm>2025-08-01T00:00:00+00:00</FrDtTm>
<ToDtTm>2025-08-31T23:59:59+00:00</ToDtTm>
</FrToDt>
<Acct>
<Id>
<IBAN>GB85LBEN72753349564929</IBAN>
</Id>
<Ccy>GBP</Ccy>
</Acct>
<Bal>
<Tp>
<CdOrPrtry>
<Cd>OPBD</Cd>
</CdOrPrtry>
</Tp>
<Amt Ccy="GBP">57014.64</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Dt>
<Dt>2025-08-01</Dt>
</Dt>
</Bal>
<Ntry>
<Amt Ccy="GBP">12046.81</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-02</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-02</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t020</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPO HARBOURLIGHT IT REF575443</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">1745.84</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-04</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-04</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t025</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPO IRONBRIDGE TOOLING REF227197</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">13961.28</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-06</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-06</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t007</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>TFR EASTFIELD ENERGY REF655713</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">13268.39</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-06</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-06</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t018</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO BRAMBLE LOGISTICS REF853738</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">14447.20</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-08</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-08</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t022</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO MOORLAND TELECOM REF444072</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">13805.86</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-10</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-10</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t003</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO MOORLAND TELECOM REF613623</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">12583.79</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-10</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-10</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t023</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP FENWICK &amp; PARTNERS REF381917</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">6308.84</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-11</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-11</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t005</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP IRONBRIDGE TOOLING REF422776</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">225.31</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-11</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-11</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t016</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO AURORA CONSULTING LTD REF819185</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">11516.60</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-14</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-14</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t010</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP JUNIPER PAYROLL REF879018</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">6829.28</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-15</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-15</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t008</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP IRONBRIDGE TOOLING REF556744</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">10094.39</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-16</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-16</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t002</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD GREENHOLM FOODS REF126234</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">14921.15</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-16</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-16</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t014</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>CR JUNIPER PAYROLL REF823829</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">1222.76</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-18</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-18</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t006</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>CR IRONBRIDGE TOOLING REF745744</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">2788.88</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-18</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-18</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t021</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP NORTHGATE CLEANING REF793921</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">4468.80</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-20</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-20</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t009</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD BRAMBLE LOGISTICS REF503246</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">9665.71</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-20</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-20</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t013</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPI AURORA CONSULTING LTD REF891599</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">2686.00</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-20</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-20</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t015</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPI AURORA CONSULTING LTD REF387248</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">10546.29</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-20</Dt>
</BookgDt>
<ValDt>
<Dt>2025-08-20</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000003-2-t019</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO LARKSPUR TRAVEL REF997138</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">3924.81</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-08-20</Dt>
hsbc_statement.xlsxUntouched by this perturbation
[sheet: Statement]
HSBC Bank plc
Business Current Account Statement
Account name: LEDGERBENCH DEMO LTD
Sort code / Account number: 79-60-88 49904351
Account reference: acct-2026000003-1
Statement period: 01 Aug 2025 to 31 Aug 2025
Currency: GBP
Opening balance: 8031.09
Date Payment type Details Paid out Paid in
02 Aug 2025 DD CASTLEGATE PROPERTY REF977109 7364.92
02 Aug 2025 FPO AURORA CONSULTING LTD REF523131 4973.13
07 Aug 2025 SO LARKSPUR TRAVEL REF622659 8923.28
10 Aug 2025 FPO BRAMBLE LOGISTICS REF585381 14161.14
10 Aug 2025 CR IRONBRIDGE TOOLING REF391272 1076.44
12 Aug 2025 CR NORTHGATE CLEANING REF725114 9262.39
14 Aug 2025 TFR NORTHGATE CLEANING REF811928 10943.54
15 Aug 2025 FPO MOORLAND TELECOM REF801634 11231.03
16 Aug 2025 FPO OSPREY LEASING REF202777 3297.59
17 Aug 2025 TFR KESTREL INSURANCE REF687954 3711.61
17 Aug 2025 FPI JUNIPER PAYROLL REF878315 2747.00
17 Aug 2025 SO EASTFIELD ENERGY REF719974 14627.27
18 Aug 2025 SO EASTFIELD ENERGY REF825040 1457.38
18 Aug 2025 BP EASTFIELD ENERGY REF169741 2755.05
18 Aug 2025 FPO FENWICK & PARTNERS REF472215 12837.52
18 Aug 2025 CR LARKSPUR TRAVEL REF566477 3124.00
18 Aug 2025 FPI NORTHGATE CLEANING REF313398 4275.33
18 Aug 2025 BP AURORA CONSULTING LTD REF884105 6555.47
19 Aug 2025 DD FENWICK & PARTNERS REF413160 7087.72
20 Aug 2025 DD GREENHOLM FOODS REF154843 7179.63
20 Aug 2025 BP IRONBRIDGE TOOLING REF645782 7892.42
23 Aug 2025 TFR EASTFIELD ENERGY REF689034 1042.54
24 Aug 2025 CR IRONBRIDGE TOOLING REF329983 10959.91
29 Aug 2025 DD JUNIPER PAYROLL REF183262 2429.27
29 Aug 2025 BP LARKSPUR TRAVEL REF245828 13622.98
30 Aug 2025 BP NORTHGATE CLEANING REF922455 11290.81
31 Aug 2025 FPI HARBOURLIGHT IT REF752927 1103.43
rbs_transactions.csvUntouched by this perturbation
"Date","Type","Description","Value","Account Name","Account Number","Ledger Ref"
"01/08/2025","BAL","OPENING BALANCE","11354.24","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"01/08/2025","SO","SO EASTFIELD ENERGY REF492756","-1346.55","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"01/08/2025","FPO","FPO KESTREL INSURANCE REF368976","-8155.73","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"06/08/2025","TFR","TFR FENWICK & PARTNERS REF898895","12554.89","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"06/08/2025","CR","CR KESTREL INSURANCE REF696666","9555.34","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"07/08/2025","BP","BP IRONBRIDGE TOOLING REF722939","-12369.77","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"07/08/2025","DD","DD LARKSPUR TRAVEL REF741352","-10290.27","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"08/08/2025","DD","DD IRONBRIDGE TOOLING REF220804","-4634.33","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"08/08/2025","TFR","TFR DELPHINIUM MEDIA REF887209","8011.68","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"08/08/2025","FPO","FPO LARKSPUR TRAVEL REF251559","-6020.65","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"09/08/2025","BP","BP HARBOURLIGHT IT REF138231","-6249.92","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"10/08/2025","TFR","TFR OSPREY LEASING REF293266","2172.30","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"10/08/2025","CR","CR LARKSPUR TRAVEL REF753542","6219.00","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"11/08/2025","DD","DD LARKSPUR TRAVEL REF614705","-431.83","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"11/08/2025","FPI","FPI KESTREL INSURANCE REF590571","5603.55","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"12/08/2025","FPI","FPI FENWICK & PARTNERS REF436141","3528.60","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"14/08/2025","SO","SO KESTREL INSURANCE REF256249","-11135.19","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"18/08/2025","DD","DD IRONBRIDGE TOOLING REF208092","-6869.16","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"18/08/2025","DD","DD JUNIPER PAYROLL REF515310","-3677.92","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"19/08/2025","FPI","FPI IRONBRIDGE TOOLING REF852412","14588.76","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"24/08/2025","DD","DD FENWICK & PARTNERS REF277041","-5839.29","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"25/08/2025","FPO","FPO CASTLEGATE PROPERTY REF717559","-726.07","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"26/08/2025","FPI","FPI JUNIPER PAYROLL REF850385","4649.71","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"26/08/2025","CR","CR JUNIPER PAYROLL REF614457","8643.65","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"27/08/2025","BP","BP MOORLAND TELECOM REF100579","-3401.32","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"29/08/2025","CR","CR LARKSPUR TRAVEL REF812274","9536.23","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"30/08/2025","FPI","FPI AURORA CONSULTING LTD REF659643","13433.94","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"31/08/2025","BP","BP CASTLEGATE PROPERTY REF276249","-2986.92","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
"31/08/2025","CR","CR DELPHINIUM MEDIA REF897052","8111.24","LEDGERBENCH DEMO LTD","42-74-75 69680461","acct-2026000003-3"
 

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-2026000003-1−£81,409.33
acct-2026000003-2−£16,714.98
acct-2026000003-3£33,828.21

Recorded runs on this case

  • exactSingle prompt2 steps · 11,896 tokens · Confidence high

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

  • exactAgent with tools20 steps · 44,270 tokens · Confidence high

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

Step through any of these on the demo page.