Skip to content
← All cases

clean

clean-2026000004

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 2026000004.

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-2026000004-2-2025-09-30</MsgId>
<CreDtTm>2025-09-30T23:59:00+00:00</CreDtTm>
</GrpHdr>
<Stmt>
<Id>acct-2026000004-2</Id>
<ElctrncSeqNb>1</ElctrncSeqNb>
<CreDtTm>2025-09-30T23:59:00+00:00</CreDtTm>
<FrToDt>
<FrDtTm>2025-09-01T00:00:00+00:00</FrDtTm>
<ToDtTm>2025-09-30T23:59:59+00:00</ToDtTm>
</FrToDt>
<Acct>
<Id>
<IBAN>GB30LBEN55596962187602</IBAN>
</Id>
<Ccy>GBP</Ccy>
</Acct>
<Bal>
<Tp>
<CdOrPrtry>
<Cd>OPBD</Cd>
</CdOrPrtry>
</Tp>
<Amt Ccy="GBP">42290.28</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Dt>
<Dt>2025-09-01</Dt>
</Dt>
</Bal>
<Ntry>
<Amt Ccy="GBP">8389.36</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-02</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-02</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t006</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP LARKSPUR TRAVEL REF215374</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">8640.14</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-04</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-04</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t001</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPI KESTREL INSURANCE REF911639</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">8337.78</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-04</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-04</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t012</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD BRAMBLE LOGISTICS REF971402</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">12522.67</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-08</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-08</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t025</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD OSPREY LEASING REF789537</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">665.27</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-09</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-09</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t004</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>CR AURORA CONSULTING LTD REF663238</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">11090.87</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-11</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-11</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t017</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPI GREENHOLM FOODS REF211911</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">9242.09</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-12</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-12</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t008</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP IRONBRIDGE TOOLING REF288357</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">14386.20</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-13</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-13</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t019</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD MOORLAND TELECOM REF467712</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">8851.99</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-14</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-14</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t005</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>CR NORTHGATE CLEANING REF525127</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">388.43</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-14</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-14</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t022</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPO GREENHOLM FOODS REF997451</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">14316.01</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-15</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-15</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t009</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPO GREENHOLM FOODS REF862891</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">2951.69</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-16</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-16</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t018</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD GREENHOLM FOODS REF271138</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">3935.54</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-17</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-17</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t010</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPI HARBOURLIGHT IT REF694105</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">13704.50</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-18</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-18</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t002</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO HARBOURLIGHT IT REF434145</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">6895.42</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-18</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-18</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t013</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>TFR LARKSPUR TRAVEL REF702336</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">4030.41</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-18</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-18</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t021</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>TFR HARBOURLIGHT IT REF526513</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">14303.72</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-18</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-18</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t027</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPO FENWICK &amp; PARTNERS REF881011</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">10922.86</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-20</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-20</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t007</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO MOORLAND TELECOM REF423164</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">1223.84</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-20</Dt>
</BookgDt>
<ValDt>
<Dt>2025-09-20</Dt>
</ValDt>
<AcctSvcrRef>acct-2026000004-2-t024</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO NORTHGATE CLEANING REF632909</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">14501.90</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-09-21</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: 51-46-75 11798741
Account reference: acct-2026000004-1
Statement period: 01 Sep 2025 to 30 Sep 2025
Currency: GBP
Opening balance: 41771.10
Date Payment type Details Paid out Paid in
01 Sep 2025 FPI NORTHGATE CLEANING REF383682 7054.13
02 Sep 2025 FPO EASTFIELD ENERGY REF916893 13818.09
03 Sep 2025 FPI GREENHOLM FOODS REF743446 4431.82
03 Sep 2025 DD AURORA CONSULTING LTD REF362090 2884.80
04 Sep 2025 FPO DELPHINIUM MEDIA REF889950 2299.51
04 Sep 2025 TFR AURORA CONSULTING LTD REF582241 11187.68
05 Sep 2025 FPI MOORLAND TELECOM REF190643 1207.11
05 Sep 2025 TFR BRAMBLE LOGISTICS REF541569 10814.88
05 Sep 2025 FPI GREENHOLM FOODS REF681186 2780.00
08 Sep 2025 FPI LARKSPUR TRAVEL REF186639 14125.05
08 Sep 2025 FPO EASTFIELD ENERGY REF289038 6606.24
08 Sep 2025 BP LARKSPUR TRAVEL REF967410 1000.78
09 Sep 2025 TFR MOORLAND TELECOM REF482046 4004.78
11 Sep 2025 FPI AURORA CONSULTING LTD REF322713 8539.90
12 Sep 2025 DD BRAMBLE LOGISTICS REF140975 4011.09
13 Sep 2025 DD DELPHINIUM MEDIA REF438211 2535.29
15 Sep 2025 FPI GREENHOLM FOODS REF345111 3168.84
16 Sep 2025 DD GREENHOLM FOODS REF496309 13966.37
16 Sep 2025 FPO KESTREL INSURANCE REF404698 2924.10
17 Sep 2025 CR IRONBRIDGE TOOLING REF749761 1153.90
18 Sep 2025 CR GREENHOLM FOODS REF324299 3472.50
20 Sep 2025 DD JUNIPER PAYROLL REF183410 453.37
20 Sep 2025 FPI GREENHOLM FOODS REF582646 9265.05
22 Sep 2025 FPI BRAMBLE LOGISTICS REF197313 1150.75
24 Sep 2025 SO AURORA CONSULTING LTD REF920228 14989.91
24 Sep 2025 FPI FENWICK & PARTNERS REF327978 13843.12
24 Sep 2025 FPO JUNIPER PAYROLL REF845213 10613.28
26 Sep 2025 TFR GREENHOLM FOODS REF152061 13088.60
30 Sep 2025 BP EASTFIELD ENERGY REF892098 10160.57
rbs_transactions.csvUntouched by this perturbation
"Date","Type","Description","Value","Account Name","Account Number","Ledger Ref"
"01/09/2025","BAL","OPENING BALANCE","59995.65","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"01/09/2025","FPI","FPI AURORA CONSULTING LTD REF623833","12074.92","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"03/09/2025","FPI","FPI MOORLAND TELECOM REF364472","4010.05","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"05/09/2025","BP","BP HARBOURLIGHT IT REF783390","-11202.52","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"05/09/2025","SO","SO OSPREY LEASING REF576386","-809.61","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"07/09/2025","DD","DD GREENHOLM FOODS REF162794","-1899.80","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"07/09/2025","FPO","FPO DELPHINIUM MEDIA REF856056","-1136.98","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"08/09/2025","DD","DD IRONBRIDGE TOOLING REF627399","-8494.07","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"12/09/2025","FPI","FPI GREENHOLM FOODS REF174094","9206.59","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"15/09/2025","CR","CR GREENHOLM FOODS REF388950","8697.90","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"15/09/2025","DD","DD JUNIPER PAYROLL REF209977","-7127.58","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"16/09/2025","BP","BP CASTLEGATE PROPERTY REF996133","-12620.00","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"17/09/2025","BP","BP GREENHOLM FOODS REF638757","-6156.72","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"19/09/2025","TFR","TFR FENWICK & PARTNERS REF804571","13537.55","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"19/09/2025","BP","BP EASTFIELD ENERGY REF824213","-7572.13","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"19/09/2025","CR","CR BRAMBLE LOGISTICS REF139294","11474.10","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"20/09/2025","FPI","FPI MOORLAND TELECOM REF879754","14715.04","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"22/09/2025","DD","DD OSPREY LEASING REF296605","-9667.35","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"26/09/2025","FPI","FPI EASTFIELD ENERGY REF154353","14158.12","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"27/09/2025","CR","CR CASTLEGATE PROPERTY REF548579","12806.64","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"27/09/2025","FPO","FPO HARBOURLIGHT IT REF924805","-2356.52","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"28/09/2025","BP","BP IRONBRIDGE TOOLING REF939533","-3811.52","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"28/09/2025","TFR","TFR DELPHINIUM MEDIA REF687144","10654.50","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
"30/09/2025","FPO","FPO AURORA CONSULTING LTD REF190053","-9672.04","LEDGERBENCH DEMO LTD","87-65-62 16451022","acct-2026000004-3"
 

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-2026000004-1£64,795.81
acct-2026000004-2−£11,268.25
acct-2026000004-3£88,804.22

Recorded runs on this case

  • wrongSingle prompt2 steps · 12,200 tokens · Confidence high

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

  • exactAgent with tools17 steps · 31,210 tokens · Confidence high

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

Step through any of these on the demo page.