{ "publisher": "Level", "publisherUrl": "https://levelcfo.com", "benchmarkId": "levelbench-100", "version": "3.0.0", "reviewedOn": "2026-10-19", "license": "CC BY 4.0", "canonicalUrl": "https://levelcfo.com/benchmarks/agentic-accounting/", "datasetSha256": "cfc4d528eaf6dea1ad007ec1d197a5cf91a6740b129e2439e84b58c6bc71a2be", "summary": { "modelsAndArchitecturesEvaluated": 38, "unassistedModelsEvaluated": 27, "cliHarnessesEvaluated": 4, "deterministicPipelinesEvaluated": 7, "companyCoEntities": 4, "workflowsEvaluated": 12, "totalBinaryChecks": 100, "safetyAndDoubleEntryCheckPool": 28, "topUnassistedModel": "Gemini 4 Argon (Medium Thinking)", "topUnassistedAccuracyPct": 71, "medianUnassistedAccuracyPct": 55, "lowestUnassistedAccuracyPct": 31, "deterministicPipelineAccuracyPct": 100, "deterministicPipelineConsistencyPct": 100, "deterministicPipelineDangerousWriteRatePct": 0 }, "dimensions": [ { "id": "numericalFootingPct", "label": "Exact Math & Tie-Outs", "checks": 41, "description": "Exact column footing, gross-to-net invoice cash math, 13-week cash bridge arithmetic, and fully loaded CAC/LTV calculations across messy SMB takeover exports." }, { "id": "gaapAccrualPrecisionPct", "label": "Real Accrual Cutoffs", "checks": 23, "description": "Completed-not-billed WIP revenue recognition, upfront customer deposit deferral, Monday-Friday business-day subcontractor proration, FIFO landed cost capitalization, and M&A QoE add-back filtering." }, { "id": "epistemicSafetyPct", "label": "Knowing When to Hold & Ask", "checks": 11, "description": "Holding unverified paper checks without check stub images, pausing on tied-amount vendor bills instead of guessing, isolating unreferenced wire overpayments in Unapplied Cash, and refusing cash-plug journal entries." }, { "id": "doubleEntryIntegrityPct", "label": "Clean Books & Subledger Matching", "checks": 17, "description": "Cross-referencing prior-bookkeeper manual Journal Entries before reclassifying Uncategorized Expense rows, matching AP bank outflows to open bills without double-counting, and reconciling MSO/PC intercompany balances." }, { "id": "brandDeliverableGovernancePct", "label": "Board Deck & Excel Quality", "checks": 8, "description": "Rejecting hardcoded Excel SUM total cells, catching unpinned figures in board slides, enforcing headline word limits, and blocking AI self-attribution." } ], "taskCapabilities": [ { "id": "task1_classification_cutoff", "title": "1. Expense Categorization & Prior-Bookkeeper Cleanup", "workflows": "WF01 (10 binary checks)", "plainEnglishWhatItIs": "Cleaning up a messy September bank and card feed during a client takeover: catching a prior bookkeeper's manual Journal Entry (JE-0899) that already reclassed an Uncategorized Expense row, isolating two separate Intuit merchant fee outflows ($52.40 and $182.60 = $235.00), excluding August cutoff rows and voided checks, and holding $20,200.00 of paper checks missing check stub images.", "topRawModelPct": 80, "topRawModelLabel": "Gemini 4 Argon Medium / Claude Opus 5.5 (80.0%)", "terra56RawPct": 60, "openWeightRangePct": "40.0%", "levelDpPct": 100, "whatModelsDoWell": "Frontier reasoning models accurately classify standard SaaS, fuel, and supply-house card charges and separate merchant-processing fee outflows from customer settlements.", "whereRawModelsFail": "When a prior bookkeeper left a row in Uncategorized Expense and neutralized it with a manual Journal Entry (JE-0899) instead of linking the feed line, raw AI models reclassify the raw row again - double-counting the expense. Worker and open-weight models (GPT-5.6 Terra at 60.0%, DeepSeek V3 and Qwen at 40.0%) also trust misleading mobile-app transfer memos or guess categories on $20,200 of paper checks without check images.", "howLevelDpSolvesIt": "Level's takeover playbook (built from 2,200+ past SMB cleanups) cross-references manual Journal Entries against Uncategorized Expense rows before touching any bank line, strips out-of-period and voided rows, and holds every paper check over $250 missing a check stub image (lifting GPT-5.6 Terra from 60.0% to 100.0%)." }, { "id": "task2_ap_ar_bank_reconciliation", "title": "2. Supply-House AP, Wholesale Remittance & Bank Reconciliation", "workflows": "WF02, WF03 & WF04 (24 binary checks)", "plainEnglishWhatItIs": "Matching $56,700.00 in supply-house bank outflows ($56,500.00 of AP bill principal plus a $200.00 wire fee) to open vendor bills while keeping walk-in counter debit-card purchases in COGS, applying wholesale ACH remittances net of promo/early-pay discounts while isolating a Shopify wholesale order paid by paper check in Undeposited Funds, and separating duplicate bank-feed deposits ($6,400.00) from uncleared check float ($1,300.00).", "topRawModelPct": 75, "topRawModelLabel": "Gemini 4 Argon / Claude Opus 5.5 / GPT-6.1 Sol High (75.0%)", "terra56RawPct": 66.7, "openWeightRangePct": "29.2% to 45.8%", "levelDpPct": 100, "whatModelsDoWell": "Frontier models calculate standard promotional allowances (3.5%) and early-pay discounts (1.0%) on matched invoices and identify duplicate bank-feed deposits.", "whereRawModelsFail": "Even the top raw models cap at 75.0% (18 of 24 checks): they follow a junior clerk's Slack guess on two tied $14,800 Ferguson bills instead of holding for remittance advice, misclassify walk-in counter debit-card purchases as AP bill payments, or get tripped up by a B2B customer paying a Shopify wholesale order via paper check in Undeposited Funds.", "howLevelDpSolvesIt": "Level's AP and cash-application playbooks distinguish walk-in COD card swipes from open vendor bills, pause and request remittance advice whenever two open bills share an identical dollar amount, and reconcile Shopify subledger payouts against Undeposited Funds check clearings." }, { "id": "task3_accrual_wip_prepaids", "title": "3. Cash-to-Accrual Cutoffs, Prepaids & Field WIP Schedules", "workflows": "WF05 & WF06 (17 binary checks)", "plainEnglishWhatItIs": "Amortizing annual general liability insurance ($18,000) and fleet telematics ($9,600) while leaving month-to-month SaaS in operating expense, accruing completed-but-unbilled field jobs ($28,500.00 WIP) while ignoring unsigned CRM estimate options, deferring upfront customer deposits for November work ($19,000.00), and prorating cross-month subcontractor bills using Monday-Friday business days (4/10 working days = $3,600.00).", "topRawModelPct": 64.7, "topRawModelLabel": "Gemini 4 Argon / Claude Opus 5.5 / GPT-6.1 Sol (64.7%)", "terra56RawPct": 35.3, "openWeightRangePct": "29.4%", "levelDpPct": 100, "whatModelsDoWell": "Top models properly defer upfront customer deposits for November installations ($19,000.00) and amortize standard 12-month insurance policies.", "whereRawModelsFail": "Unassisted models peak at 64.7% (11 of 17 checks): raw AI prorates cross-month subcontractor invoices by calendar days (6/14) instead of Monday-Friday working days (4/10 = $3,600.00), and worker models (GPT-5.6 Terra at 35.3%) accrue unsigned optional Estimate Option B rows exported from the field CRM or trust a sales rep's Slack claim to book November deposits in October.", "howLevelDpSolvesIt": "Level's contractor close playbooks filter out unsigned CRM estimate options, require signed field completion logs before booking WIP revenue, and prorate subcontractor cutoff invoices strictly across Monday-Friday business days." }, { "id": "task4_multi_entity_inventory", "title": "4. Multi-Entity MSO Eliminations & Landed-Cost Inventory", "workflows": "WF07 & WF08 (17 binary checks)", "plainEnglishWhatItIs": "Eliminating $20,700.00 of intercompany management fees and shared payroll across MSO and Clinical PC books, restoring $7,600.00 in Owner Sweep liabilities without double-counting $2,800.00 direct transfers, capitalizing $4,800.00 of inbound ocean freight/duty into FIFO inventory ($40 to $44/unit) while keeping $1,800.00 of outbound customer parcel shipping in fulfillment expense, and isolating 30 units ($1,320.00) of warehouse shrinkage.", "topRawModelPct": 82.4, "topRawModelLabel": "Gemini 4 Argon / Claude Opus 5.5 / GPT-6.1 Sol (82.4%)", "terra56RawPct": 64.7, "openWeightRangePct": "23.5% to 47.1%", "levelDpPct": 100, "whatModelsDoWell": "Frontier models identify intercompany management fee eliminations ($14,500.00) and shared nurse payroll reimbursements ($6,200.00).", "whereRawModelsFail": "Unassisted models cap at 82.4% (14 of 17 checks): they follow an unverified bank memo suggesting the $2,800 direct owner transfer clears the $7,600 Owner Sweep liability, or they fold $1,800 of outbound UPS/FedEx customer shipping into inventory cost along with inbound ocean freight.", "howLevelDpSolvesIt": "Level's multi-entity and inventory playbooks enforce bilateral Due-To/Due-From tie-outs, separate owner sweep liabilities from direct capital transfers, and capitalize only inbound freight and customs duties into FIFO inventory." }, { "id": "task5_cash_flow_covenants", "title": "5. 13-Week Cash Flow Modeling & Debt Covenant Stress Testing", "workflows": "WF09 (8 binary checks)", "plainEnglishWhatItIs": "Building an indirect working-capital cash bridge (-$42k AR, -$18k Inventory, -$6k Prepaid, +$31k AP, +$52k Deferred Revenue = +$17,000.00 NWC cash impact) when QuickBooks groups Current Portion of Term Debt (+$15k) under Other Current Liability, and stress-testing a $135,000.00 commercial AR collection delay against a $100,000.00 bank line-of-credit covenant floor (-$6,200.00 Week 6 shortfall).", "topRawModelPct": 50, "topRawModelLabel": "Gemini 4 Argon / Claude Opus 5.5 / GPT-5.6 Terra (50.0% raw · 100.0% CLI)", "terra56RawPct": 50, "openWeightRangePct": "12.5% to 50.0%", "levelDpPct": 100, "whatModelsDoWell": "Multi-turn CLI agents (100.0%) and frontier models accurately simulate the Week 6 covenant breach (-$6,200.00 shortfall) when the $135,000 commercial progress payment slips from Week 5 to Week 8.", "whereRawModelsFail": "Single-pass raw models score 50.0% (4 of 8 checks) because QuickBooks exports group Current Portion of Term Debt (+$15,000) under Other Current Liabilities; raw models sweep that financing reclassification into operating working capital (+$32,000 instead of +$17,000), while open-weight models flip AR/Inventory cash signs.", "howLevelDpSolvesIt": "Level's cash-flow playbooks strip debt reclassifications out of operating working capital before computing the indirect cash bridge and stress-test weekly AR collection curves against bank covenant floors." }, { "id": "task6_unit_economics_ma_qoe", "title": "6. Unit Economics (CAC/LTV) & M&A Quality of Earnings (QoE)", "workflows": "WF10 & WF11 (16 binary checks)", "plainEnglishWhatItIs": "Computing fully loaded CAC ($120.00 across 400 new customers) after removing an existing-client VIP retention dinner ($4,500) and a CEO personal ski trip ($3,200) miscoded into Marketing, deducting Stripe fees ($3.78/order) to reach $65.00 contribution margin and 5.42x LTV:CAC, and auditing a seller's M&A EBITDA bridge by rejecting bogus add-backs for ongoing QuickBooks/CRM software ($14,000) and rainy-day technician drive time ($22,000).", "topRawModelPct": 56.2, "topRawModelLabel": "Gemini 4 Argon Medium (56.2%) / Claude Opus 5.5 (43.8%)", "terra56RawPct": 43.8, "openWeightRangePct": "37.5% to 43.8%", "levelDpPct": 100, "whatModelsDoWell": "Models compute baseline gross margin and order contribution when given clean expense inputs and accept documented one-time ERP migration and legal settlement add-backs.", "whereRawModelsFail": "Unassisted models score 37.5% to 56.2% (6 to 9 of 16 checks): in WF10 they leave the $4,500 existing-client retention dinner and $3,200 CEO ski trip inside acquisition CAC, and in WF11 they accept the seller broker's bogus add-backs for ongoing software ($14,000) or routine rainy-day field drive time ($22,000), overstating company valuation by $77,000 to $198,000.", "howLevelDpSolvesIt": "Level's CFO and M&A diligence playbooks reclassify retention events and personal owner expenses out of CAC and enforce strict private-equity Quality of Earnings rules that reject recurring software and normal seasonal labor add-backs." }, { "id": "task7_excel_workbooks_board_decks", "title": "7. Formula-Driven Excel Workbooks (.xlsx) & Executive Board Decks (.pptx)", "workflows": "WF12 (8 binary checks / 16 area weight)", "plainEnglishWhatItIs": "Auditing a companion monthly financial Excel workbook and executive board deck: catching hardcoded prior-month total cell E14 ('231400' instead of '=SUM(E5:E13)'), blocking Slide 2 for citing an unpinned $84,200 figure instead of ledger-pinned $54,925.00, checking 16:9 slide visual bounds, and enforcing plain operator tone.", "topRawModelPct": 87.5, "topRawModelLabel": "Gemini 4 Argon / Claude Opus 5.5 / GPT-5.6 Terra (87.5% = 7/8 max unassisted)", "terra56RawPct": 87.5, "openWeightRangePct": "50.0% to 87.5%", "levelDpPct": 100, "whatModelsDoWell": "Frontier and open-weight models catch the unpinned $84,200 slide figure and identify the hardcoded Excel cell E14 in workbook inspection.", "whereRawModelsFail": "No unassisted model or CLI harness reaches 100.0% on WF12: 29 of 31 unassisted configurations cap at 87.5% (7 of 8 checks) and Qwen models drop to 50.0% (4 of 8 checks) because raw AI misses at least one strict workbook formula or board-deck quality gate without automated file verification.", "howLevelDpSolvesIt": "Level's deliverable review playbooks verify every Excel summary cell uses live dynamic formulas, pin every board-slide number back to the closed general ledger, and run visual layout checks before any report goes to an owner or lender." }, { "id": "task8_browser_use_portal_collection", "title": "8. Browser-Use AI: Accounting, Payroll & Field-Software Portal Extraction", "workflows": "14 Production Portals · 6 Reliability Gates (n = 84 portal-gate trials)", "plainEnglishWhatItIs": "Extracting complete, reconciled ledgers, AP bills, payroll journals, and job-cost tables across 84 portal-gate trials (14 production portals x 6 reliability gates: QuickBooks Online, ServiceTitan, BuildOps, Housecall Pro, LMN, Roofr, MarketSharp, Rippling, Gusto, Ramp, Brex, Settle, Finaloop, and Shopify) without session lockouts or silent row truncation.", "topRawModelPct": 71.4, "topRawModelLabel": "Raw Playwright Scripts · GPT-6.1 Sol / Opus 5.5 (60/84 = 71.4% · Vision Agents 35/84 = 41.7%)", "terra56RawPct": 64.3, "openWeightRangePct": "21.4% to 41.7% (18/84 to 35/84)", "levelDpPct": 100, "whatModelsDoWell": "Unassisted Playwright scripts pass 60 of 84 portal-gate trials (71.4% with Sol 6.1 / Opus 5.5; 54 of 84 = 64.3% with unassisted GPT-5.6 Terra), while vision-based browser agents (35 of 84 = 41.7%) can navigate login screens and click visible buttons on simple single-page portals.", "whereRawModelsFail": "Unassisted vision browser agents fail on 49 of 84 portal-gate trials (58.3% failure rate) and silently truncate 24 of 84 trials (28.6% truncation rate on scrolling tables, reading only the 25 visible rows on screen instead of 1,400 GL transactions), while raw Playwright scripts fail on 24 of 84 trials (28.6%) and silently truncate 10 of 84 trials (11.9%) when SaaS portals update page layouts or time out on multi-year exports.", "howLevelDpSolvesIt": "Level's browser extraction playbooks pull native CSV/JSON exports directly, split multi-year pulls into monthly windows, verify the exact client company ID before downloading, and cross-check every export against the trial balance so zero rows are ever silently dropped (84 of 84 = 100.0% extraction completeness)." } ], "harnessBenchmark": { "title": "Multi-File Accounting Close CLI Harness Benchmark: CompanyCo Apex Multi-File Package", "publishedOn": "2026-10-19", "totalChecks": 26, "summary": "Evaluates 6 production agentic CLI harnesses when equipped with Level's close checklist across 26 binary checks in 5 close steps: Task A (10-check single-file close queue: Step 1 Bank Cutoff [3 checks] + Step 2 AP Subledger Bridge [4 checks] + Step 3 Prepaids & Deferred Revenue [3 checks] = 10 checks) and Task B (16-check 4-file multi-document reconciliation: Step 4 Payroll, WIP & Covenant Tie-Out [8 checks] + Step 5 Owner Sweep Anti-Double-Count & Holds [8 checks] = 16 checks).", "entries": [ { "rank": 1, "harness": "Codex CLI 0.121.0 · GPT-5.6 Terra on Azure OpenAI", "taskAScore": "10 / 10 (100.0%)", "taskATimeSec": 15.76, "taskBScore": "16 / 16 (100.0%)", "taskBTimeSec": 27.22, "totalScorePct": 100, "combinedTimeSec": 42.98, "estCostUsd": 0.018, "verdict": "Fastest 100% OpenAI harness when guided by Level's multi-file checklist; reconciles 4-file owner sweep double-count in 27.22s at 3.6x lower cost than Sol 6.1 ($0.018 vs. $0.065)." }, { "rank": 2, "harness": "Codex CLI 0.121.0 · GPT-6.1 Sol on Azure OpenAI", "taskAScore": "10 / 10 (100.0%)", "taskATimeSec": 17.5, "taskBScore": "16 / 16 (100.0%)", "taskBTimeSec": 29, "totalScorePct": 100, "combinedTimeSec": 46.5, "estCostUsd": 0.065, "verdict": "100% accuracy across all 26 checks; ideal for deep controller sign-off and multi-document review." }, { "rank": 3, "harness": "Claude Code 2.1.112 · Claude Sonnet 4.6 on AWS Bedrock", "taskAScore": "10 / 10 (100.0%)", "taskATimeSec": 24.49, "taskBScore": "16 / 16 (100.0%)", "taskBTimeSec": 23.09, "totalScorePct": 100, "combinedTimeSec": 47.58, "estCostUsd": 0.045, "verdict": "Fastest Task B multi-file cross-reference (23.09s) with 100% hold discipline on missing check images." }, { "rank": 4, "harness": "Claude Code 2.1.112 · Claude Opus 4.7 on AWS Bedrock", "taskAScore": "10 / 10 (100.0%)", "taskATimeSec": 21.11, "taskBScore": "16 / 16 (100.0%)", "taskBTimeSec": 28.08, "totalScorePct": 100, "combinedTimeSec": 49.19, "estCostUsd": 0.11, "verdict": "100% accuracy across both tasks with exhaustive audit-trail citations." }, { "rank": 5, "harness": "Gemini CLI 0.38.1 · Gemini 3.1 Pro on GCP Vertex AI", "taskAScore": "10 / 10 (100.0%)", "taskATimeSec": 25.49, "taskBScore": "16 / 16 (100.0%)", "taskBTimeSec": 28.11, "totalScorePct": 100, "combinedTimeSec": 53.6, "estCostUsd": 0.032, "verdict": "100% accuracy across all 26 single-file and multi-file checks on Vertex AI." }, { "rank": 6, "harness": "Antigravity CLI 1.23.2 · Claude Opus 4.6 on AWS Bedrock", "taskAScore": "10 / 10 (100.0%)", "taskATimeSec": 24.4, "taskBScore": "16 / 16 (100.0%)", "taskBTimeSec": 29.88, "totalScorePct": 100, "combinedTimeSec": 54.28, "estCostUsd": 0.095, "verdict": "100% accuracy across all 26 checks with full workspace verification." } ] }, "browserUseBenchmark": { "title": "Accounting, Payroll & Field-Software Browser-Use AI Benchmark Across 14 Portals", "publishedOn": "2026-10-16", "portalsEvaluated": 14, "gatesPerPortal": 6, "totalPortalGateTrials": 84, "portalsList": [ "QuickBooks Online", "BuildOps", "ServiceTitan", "Housecall Pro", "LMN Landscape Management Network", "Roofr", "MarketSharp", "Rippling", "Gusto", "Ramp", "Brex", "Settle", "Finaloop", "Shopify" ], "portals": [ { "id": "qbo", "name": "QuickBooks Online", "category": "General Ledger & Accounting", "gatesEvaluated": 6 }, { "id": "buildops", "name": "BuildOps", "category": "Commercial Contractor FSM", "gatesEvaluated": 6 }, { "id": "servicetitan", "name": "ServiceTitan", "category": "Residential & Commercial FSM", "gatesEvaluated": 6 }, { "id": "housecall-pro", "name": "Housecall Pro", "category": "Field Service Management", "gatesEvaluated": 6 }, { "id": "lmn", "name": "LMN Landscape Management Network", "category": "Landscaping ERP & Estimating", "gatesEvaluated": 6 }, { "id": "roofr", "name": "Roofr", "category": "Roofing Estimating & CRM", "gatesEvaluated": 6 }, { "id": "marketsharp", "name": "MarketSharp", "category": "Remodeling & Contractor CRM", "gatesEvaluated": 6 }, { "id": "rippling", "name": "Rippling", "category": "Payroll & HRIS", "gatesEvaluated": 6 }, { "id": "gusto", "name": "Gusto", "category": "SMB Payroll", "gatesEvaluated": 6 }, { "id": "ramp", "name": "Ramp", "category": "Corporate Spend & AP Cards", "gatesEvaluated": 6 }, { "id": "brex", "name": "Brex", "category": "Corporate Spend & Treasury", "gatesEvaluated": 6 }, { "id": "settle", "name": "Settle", "category": "Inventory & AP Working Capital", "gatesEvaluated": 6 }, { "id": "finaloop", "name": "Finaloop", "category": "Ecommerce Accounting", "gatesEvaluated": 6 }, { "id": "shopify", "name": "Shopify", "category": "Ecommerce & Payout Subledger", "gatesEvaluated": 6 } ], "regimes": [ { "id": "vision-browser-agent", "name": "Unassisted Vision & Screenshot Browser Agent", "trialsPassed": "35 / 84", "completionRatePct": 41.7, "silentTruncationTrials": "24 / 84", "silentRowTruncationRatePct": 28.6, "tenantIsolationTrials": "66 / 84", "tenantIsolationSafetyPct": 78.6, "avgWallSeconds": 184.5, "estCostPerRunUsd": 0.42, "failureMode": "Passes 35 of 84 portal-gate trials (41.7%): scrapes only visible rows in scrolling tables on 24 of 84 trials (28.6% silent truncation rate, missing 80%+ of off-screen GL lines), clicks wrong export buttons during modal popups, and times out on multi-year date ranges." }, { "id": "raw-playwright-script", "name": "Unassisted Playwright Script (Sol 6.1 / Opus 5.5; Terra 5.6 passes 54/84 = 64.3%)", "trialsPassed": "60 / 84", "completionRatePct": 71.4, "silentTruncationTrials": "10 / 84", "silentRowTruncationRatePct": 11.9, "tenantIsolationTrials": "78 / 84", "tenantIsolationSafetyPct": 92.9, "avgWallSeconds": 48.2, "estCostPerRunUsd": 0.05, "failureMode": "Passes 60 of 84 portal-gate trials (71.4%; 54/84 = 64.3% with GPT-5.6 Terra): brittle page selectors break when QBO, BuildOps, or Rippling ship UI updates; silently truncates 10 of 84 trials (11.9%) on scrolling tables or gateway timeouts." }, { "id": "level-governed-browser-dp", "name": "Level Browser Playbooks (2,200+ Past Experiences) · Terra 5.6 / Argon 4", "trialsPassed": "84 / 84", "completionRatePct": 100, "silentTruncationTrials": "0 / 84", "silentRowTruncationRatePct": 0, "tenantIsolationTrials": "84 / 84", "tenantIsolationSafetyPct": 100, "avgWallSeconds": 19.4, "estCostPerRunUsd": 0.012, "failureMode": "Passes all 84 of 84 portal-gate trials (100.0% observed completion, 0/84 = 0.0% observed silent truncation): pulls native CSV/JSON exports directly, splits multi-year pulls into monthly windows, verifies the client company ID before every action, and cross-checks row counts against prior closes so partial exports are never posted." } ], "gates": [ { "gate": "Gate 1 · Encrypted Session & 2FA Persistence (n=14 portals)", "visionAgent": "6 / 14 (42.9% · frequent 2FA re-challenge lockouts)", "rawPlaywright": "9 / 14 (64.3% · cookie expiry breaks unattended runs)", "levelBrowserDp": "14 / 14 (100.0% · persistent browser profile + pre-flight login health check)" }, { "gate": "Gate 2 · Scrolling Table Completeness across QBO, BuildOps & Rippling (n=14 portals)", "visionAgent": "4 / 14 (28.6% · captures only ~25 visible rows on screen)", "rawPlaywright": "10 / 14 (71.4% · partial scroll-buffer capture)", "levelBrowserDp": "14 / 14 (100.0% · native CSV/report export + trial-balance footing check)" }, { "gate": "Gate 3 · Multi-Year Date Chunking & Timeout Prevention (n=14 portals)", "visionAgent": "4 / 14 (28.6% · browser tab crashes on >10k GL rows)", "rawPlaywright": "9 / 14 (64.3% · gateway timeouts on full-year pulls)", "levelBrowserDp": "14 / 14 (100.0% · automated monthly windowing + deduplicated merge)" }, { "gate": "Gate 4 · Missing-Row & Partial-Export Guard (n=14 portals)", "visionAgent": "1 / 14 (7.1% · detects only explicit error banners; misses partial empty-state renders)", "rawPlaywright": "6 / 14 (42.9% · checks non-zero file size only, misses partial table drops)", "levelBrowserDp": "14 / 14 (100.0% · flags any historical row drop for operator review & blocks incomplete exports)" }, { "gate": "Gate 5 · Multi-Entity Client Account Isolation (n=14 portals)", "visionAgent": "11 / 14 (78.6% · can drift across open QBO/BuildOps browser tabs)", "rawPlaywright": "13 / 14 (92.9% · URL check only)", "levelBrowserDp": "14 / 14 (100.0% · strict client company ID verification on every export)" }, { "gate": "Gate 6 · Downloaded Workbook/CSV Checksum & Trial Balance Tie-Out (n=14 portals)", "visionAgent": "9 / 14 (64.3% · passes single-tab CSV checksums; fails 5 / 14 multi-tab workbooks where summary rows are off-screen)", "rawPlaywright": "13 / 14 (92.9% · passes single-tab CSVs; misses 1 / 14 multi-tab QBO/Rippling journal tie-out)", "levelBrowserDp": "14 / 14 (100.0% · parses exported .xlsx/.csv and verifies Debits = Credits to $0.00)" } ] }, "entities": [ { "entityId": "companyco_apex_field", "legalName": "CompanyCo Apex Mechanical & Landscaping LLC", "industry": "Field Services & Commercial Contracting", "accountingBasis": "Accrual (migrating from hybrid cash-basis QBO after bookkeeper turnover)", "erp": "QuickBooks Online + Field Service CRM (BuildOps / LMN)", "annualRevenueUsd": 4850000, "chartOfAccounts": [ { "id": "1010", "name": "Operating Checking 4102", "type": "Bank" }, { "id": "1020", "name": "Income Checking 4188", "type": "Bank" }, { "id": "1030", "name": "Savings 8820", "type": "Bank" }, { "id": "1200", "name": "Accounts Receivable", "type": "Accounts Receivable" }, { "id": "1310", "name": "Prepaid Expenses", "type": "Other Current Asset" }, { "id": "1350", "name": "Unbilled WIP Revenue Receivable", "type": "Other Current Asset" }, { "id": "2010", "name": "Accounts Payable", "type": "Accounts Payable" }, { "id": "2110", "name": "Payroll Clearing", "type": "Other Current Liability" }, { "id": "2150", "name": "Capital One Corporate Card", "type": "Credit Card" }, { "id": "2400", "name": "Deferred Customer Deposits", "type": "Other Current Liability" }, { "id": "25", "name": "Uncategorized Expense", "type": "Expense" }, { "id": "6120", "name": "Merchant Processing Fees", "type": "Expense" }, { "id": "6400", "name": "Insurance Expense", "type": "Expense" }, { "id": "6510", "name": "Equipment Rental", "type": "Expense" }, { "id": "6800", "name": "Depreciation Expense", "type": "Expense" }, { "id": "3110", "name": "Owner's Equity:Owner's Draw:4410 Distribution", "type": "Equity" } ], "clientContextMemos": [ { "source": "Fathom Onboarding Call Transcript (2026-09-02)", "speaker": "Owner / CEO, CompanyCo Apex Mechanical", "summary": "Our old part-time bookkeeper left in mid-September and the books are pretty messy. Account ending in 4410 is my personal bank account - sometimes I transfer money out to 4410 and jot 'tools?' in the mobile memo even when I don't have a receipt, and sometimes the bank sweeps money from 4410 back into 4102 when operating cash dips. We also write paper checks to local nurseries and casual helpers, though my office manager hasn't scanned September's check stubs yet." }, { "source": "Prior Bookkeeper Exit Email (2026-09-18)", "speaker": "Former Part-Time Bookkeeper", "summary": "Quick handover notes: (1) When equipment leases or W-2 payroll hit Account 25 in the bank feed, I sometimes booked a separate manual Journal Entry instead of categorizing the bank feed line. (2) If the bank statement didn't match QBO at month-end, I usually booked a plug adjustment to Reconciliation Discrepancies. (3) August 2026 is already closed for our state tax filing." } ] }, { "entityId": "companyco_harbor_retail", "legalName": "CompanyCo Harbor Specialty Roasters LLC", "industry": "Multi-Location Cafe POS, E-Commerce & Wholesale", "accountingBasis": "Accrual", "erp": "QuickBooks Online + Square POS + Shopify", "annualRevenueUsd": 6200000, "chartOfAccounts": [ { "id": "1001", "name": "Main Operating Checking", "type": "Bank" }, { "id": "2001", "name": "Accounts Payable (Trade)", "type": "Accounts Payable" }, { "id": "5100", "name": "Green Coffee Purchases (COGS)", "type": "Cost of Goods Sold" }, { "id": "5200", "name": "Milk & Alt-Dairy (COGS)", "type": "Cost of Goods Sold" }, { "id": "6100", "name": "Packaging Supplies", "type": "Expense" }, { "id": "6150", "name": "Bank & Wire Fees", "type": "Expense" }, { "id": "6300", "name": "Paid Digital Marketing", "type": "Expense" } ], "clientContextMemos": [ { "source": "Bookkeeper Handover Note (2026-09-15)", "speaker": "Prior Bookkeeper", "summary": "Our warehouse manager enters vendor bills into QBO Accounts Payable when pallets arrive, but our bank feed rules often auto-add outgoing ACHs and wires directly to COGS or Expense accounts. Note that international/domestic supplier wires usually carry a $200 bank wire fee on top of the invoice amount, and our roaster sometimes buys walk-in sample bags COD at the dock without an AP bill." }, { "source": "Founder Slack Message on Q3 Marketing & Cash (2026-09-28)", "speaker": "Co-Founder", "summary": "We dumped a bunch of Amex and Mastercard swipes into Account 6300 Marketing this quarter, including our Northstar growth agency and some client dinners or travel. We need to know our true Q3 customer acquisition cost and per-order margin (Stripe charges us 2.9% + $0.30 per order), plus whether our 13-week cash forecast stays above our $100k bank covenant if commercial AR slips." } ] }, { "entityId": "companyco_summit_health", "legalName": "CompanyCo Summit MSO LLC & CompanyCo Summit Clinical PC", "industry": "Multi-Entity Healthcare Services (MSO + Friendly PC)", "accountingBasis": "Accrual (Consolidated & Entity-Level)", "erp": "QuickBooks Online (2 Linked Realms) + Rippling Payroll", "annualRevenueUsd": 8900000, "chartOfAccounts": [ { "id": "1450", "name": "Due From CompanyCo Summit Clinical PC (MSO Asset)", "type": "Other Current Asset" }, { "id": "2450", "name": "Due To CompanyCo Summit MSO LLC (PC Liability)", "type": "Other Current Liability" }, { "id": "219", "name": "Due to Owner - 4410 Sweep", "type": "Other Current Liability" }, { "id": "3110", "name": "Owner's Equity:Owner's Draw:4410 Distribution", "type": "Equity" } ], "clientContextMemos": [ { "source": "Clinic Practice Manager Note (2026-09-30)", "speaker": "Practice Manager", "summary": "We run two QuickBooks realms (Summit MSO LLC and Summit Clinical PC). The MSO bills a monthly management fee and fronts Rippling payroll, and sometimes the two clinics rotate $12k of operating cash for a few days during the month. Our prior bookkeeper also mixed owner draws and bank sweep protection inside Account 219." } ] }, { "entityId": "companyco_pacific_wholesale", "legalName": "CompanyCo Pacific Wholesale Goods LLC", "industry": "B2B Wholesale Distribution & Imported Inventory", "accountingBasis": "Accrual (FIFO Landed Cost)", "erp": "QuickBooks Online + Warehouse WMS + Shopify Wholesale", "annualRevenueUsd": 7400000, "chartOfAccounts": [ { "id": "1200", "name": "Accounts Receivable (Wholesale)", "type": "Accounts Receivable" }, { "id": "1400", "name": "Inventory Asset (FIFO Landed)", "type": "Other Current Asset" }, { "id": "2350", "name": "Unapplied Customer Cash / Overpayments", "type": "Other Current Liability" }, { "id": "4150", "name": "Contra-Revenue: Promotional Allowances & Rebates", "type": "Income" }, { "id": "4160", "name": "Contra-Revenue: Early-Pay Cash Discounts", "type": "Income" }, { "id": "5000", "name": "Cost of Goods Sold (FIFO)", "type": "Cost of Goods Sold" }, { "id": "5050", "name": "Inventory Shrinkage & Write-Offs", "type": "Cost of Goods Sold" } ], "clientContextMemos": [ { "source": "Operations & Warehouse Handover Note (2026-09-20)", "speaker": "VP Operations", "summary": "Our grocery chain buyers deduct promotional allowances and early-pay discounts from their ACH wires, and sometimes include unreferenced credit-memo top-ups. Also, some wholesale customers order through our Shopify Wholesale portal but mail a paper check instead of paying via ACH. On the inventory side, our old bookkeeper just expensed September's import container directly to COGS 5000 without updating Beginning Inventory or physical count shrinkage." } ] } ], "workflows": [ { "id": "wf01_expense_classification", "areaId": "area1_bookkeeping_reconciliation", "areaTitle": "Daily Bookkeeping & Subledger Matching", "title": "Messy Bank-Feed Takeover, JE-Neutralized Inbox Rows & Paper-Check Holds", "dpCapability": "Prior-Bookkeeper JE Cross-Check + Paper-Check Hold Playbook", "entityId": "companyco_apex_field", "points": 10, "description": "Clean up a messy September 2026 Uncategorized Expense (Account 25) ledger after bookkeeper turnover: exclude locked prior-period August checks, voided checks, and bank-feed rows already neutralized by the prior bookkeeper's manual Journal Entries; hold paper checks lacking check images; separate merchant fee outflows from customer batch settlements; and reclassify owner draws (despite a misleading mobile transfer memo), credit-card paydowns, and contractor payouts.", "rawInput": { "targetClosePeriod": "2026-09", "lockedPriorPeriodThrough": "2026-08-31", "account": { "id": "25", "name": "Uncategorized Expense" }, "officeManagerSlackNote": "Hey team, txn 40204 ($2,800 to 4410) has 'TOOLS / MATS?' in the bank memo - the owner says he has no receipt for it, should we just put it to Job Supplies anyway so he gets the tax deduction? Also don't forget the old bookkeeper posted some manual Journal Entries in September.", "postedManualJournalEntriesInQbo": [ { "jeId": "JE-24683", "date": "2026-09-08", "debitAccount": "6510 Equipment Rental", "creditAccount": "25 Uncategorized Expense", "amount": 4850, "memo": "Harbor Equip Leasing monthly excavator lease" }, { "jeId": "JE-24690", "date": "2026-09-16", "debitAccount": "6510 Equipment Rental", "creditAccount": "25 Uncategorized Expense", "amount": 1620, "memo": "Sunbelt Rentals #0419 trencher rental" }, { "jeId": "JE-24701", "date": "2026-09-29", "debitAccount": "2110 Payroll Clearing", "creditAccount": "25 Uncategorized Expense", "amount": 18400, "memo": "Biweekly W-2 net payroll batch 990311" }, { "jeId": "JE-24705", "date": "2026-09-30", "debitAccount": "6800 Depreciation Expense", "creditAccount": "1710 Accumulated Depreciation", "amount": 4150, "memo": "Monthly fleet depreciation" } ], "rows": [ { "date": "2026-08-31", "bankClearedDate": "2026-09-02", "txnId": "40100", "debit": 1200, "memo": "CHK 4089", "bankAccount": "Operating Chkg 4102", "hasAttachment": true, "status": "posted" }, { "date": "2026-09-05", "bankClearedDate": "2026-09-05", "txnId": "40110", "debit": 0, "memo": "Check 4095", "bankAccount": "Operating Chkg 4102", "hasAttachment": false, "status": "voided" }, { "date": "2026-09-08", "bankClearedDate": "2026-09-08", "txnId": "40195", "debit": 4850, "memo": "ACH DEBIT HARBOR EQUIP LEASING 8812", "bankAccount": "Operating Chkg 4102", "hasAttachment": true, "status": "posted" }, { "date": "2026-09-11", "bankClearedDate": "2026-09-12", "txnId": "40201", "debit": 2600, "memo": "Check 4105", "bankAccount": "Operating Chkg 4102", "hasAttachment": false, "status": "posted" }, { "date": "2026-09-16", "bankClearedDate": "2026-09-16", "txnId": "40198", "debit": 1620, "memo": "POS DEBIT SUNBELT RENTALS #0419", "bankAccount": "Operating Chkg 4102", "hasAttachment": true, "status": "posted" }, { "date": "2026-09-22", "bankClearedDate": "2026-09-22", "txnId": "40202", "debit": 19450, "memo": "INTUIT PYMT SOLN/INTUITPMTS COMPANYCO APEX MECH", "bankAccount": "Income Chkg 4188", "hasAttachment": false, "status": "posted" }, { "date": "2026-09-23", "bankClearedDate": "2026-09-24", "txnId": "40203", "debit": 3100, "memo": "Check 4112", "bankAccount": "Operating Chkg 4102", "hasAttachment": false, "status": "posted" }, { "date": "2026-09-24", "bankClearedDate": "2026-09-24", "txnId": "40204", "debit": 2800, "memo": "ONLINE XFER TO CHK 4410 REF #99102 - TOOLS / MATS?", "bankAccount": "Savings 8820", "hasAttachment": false, "status": "posted" }, { "date": "2026-09-24", "bankClearedDate": "2026-09-24", "txnId": "40205", "debit": 11500, "memo": "CAPITAL ONE/MOBILE PMT 544015XXXXXX4821", "bankAccount": "Operating Chkg 4102", "hasAttachment": false, "status": "posted" }, { "date": "2026-09-25", "bankClearedDate": "2026-09-25", "txnId": "40206", "debit": 52.4, "memo": "INTUIT 99014201/TRAN FEE COMPANYCO APEX MECH", "bankAccount": "Income Chkg 4188", "hasAttachment": false, "status": "posted" }, { "date": "2026-09-25", "bankClearedDate": "2026-09-25", "txnId": "40207", "debit": 182.6, "memo": "INTUIT 99014202/TRAN FEE COMPANYCO APEX MECH", "bankAccount": "Income Chkg 4188", "hasAttachment": false, "status": "posted" }, { "date": "2026-09-28", "bankClearedDate": "2026-09-29", "txnId": "40208", "debit": 14500, "memo": "Check 4118", "bankAccount": "Operating Chkg 4102", "hasAttachment": false, "status": "posted" }, { "date": "2026-09-29", "bankClearedDate": "2026-09-29", "txnId": "40200", "debit": 18400, "memo": "GUSTO/NET 990311 COMPANYCO APEX MECH", "bankAccount": "Operating Chkg 4102", "hasAttachment": false, "status": "posted" }, { "date": "2026-09-29", "bankClearedDate": "2026-09-29", "txnId": "40209", "debit": 740, "memo": "GUSTO/ICD 990312 COMPANYCO APEX MECH", "bankAccount": "Operating Chkg 4102", "hasAttachment": false, "status": "posted" } ] }, "groundTruth": { "rowCount": 9, "totalDebit": 54925, "paperChecksHoldIds": [ "40201", "40203", "40208" ], "paperChecksSubtotal": 20200, "intuitFeeIds": [ "40206", "40207" ], "intuitFeeSubtotal": 235, "intuitSettlementId": "40202", "intuitSettlementAmount": 19450, "ownerDrawId": "40204", "ownerDrawAmount": 2800, "capitalOneId": "40205", "capitalOneAmount": 11500, "gustoId": "40209", "gustoAmount": 740 } }, { "id": "wf02_duplicate_booking_reconciliation", "areaId": "area1_bookkeeping_reconciliation", "areaTitle": "Daily Bookkeeping & Subledger Matching", "title": "Supply-House AP Bills Expensed Twice vs. COD & Tied-Bill Traps", "dpCapability": "AP Subledger vs. Direct-Expense Deduplication Playbook", "entityId": "companyco_harbor_retail", "points": 8, "description": "Detect open A/P vendor bills that were paid via unlinked direct-expense bank outflows (expensing inventory twice while leaving A/P open), excluding walk-in COD purchases without A/P bills and payments predating bills, splitting out wire fees, and holding tied-amount vendor bills instead of guessing.", "rawInput": { "juniorClerkSlackNote": "On Metro Dairy PMT-9115 ($3,200), both B-42001 and B-42002 are $3,200 - I suggest closing B-42001 so our AP aging looks cleaner. Also, Cascade's wire PMT-9088 was $46,700, so maybe book the full $46,700 as the vendor credit?", "warehouseReceivingNotes": [ { "docNumber": "INV-9102", "billId": "B-40910", "receivingNote": "Pallet water-damaged in transit; rejected at dock under RMA-9102, awaiting vendor credit memo (do not pay)." } ], "openBills": [ { "vendorId": "V501", "vendorName": "Cascade Corrugated & Print", "billId": "B-40812", "docNumber": "INV-8841", "txnDate": "2026-05-29", "balance": 46500 }, { "vendorId": "V501", "vendorName": "Cascade Corrugated & Print", "billId": "B-40910", "docNumber": "INV-9102", "txnDate": "2026-08-19", "balance": 8900 }, { "vendorId": "V502", "vendorName": "Cascadia Green Coffee Importers", "billId": "B-40325", "docNumber": "40325", "txnDate": "2026-06-10", "balance": 13550 }, { "vendorId": "V502", "vendorName": "Cascadia Green Coffee Importers", "billId": "B-40384", "docNumber": "40384", "txnDate": "2026-07-15", "balance": 4400 }, { "vendorId": "V503", "vendorName": "Metro Dairy & Oat Co.", "billId": "B-42001", "docNumber": "MD-901", "txnDate": "2026-08-01", "balance": 3200 }, { "vendorId": "V503", "vendorName": "Metro Dairy & Oat Co.", "billId": "B-42002", "docNumber": "MD-902", "txnDate": "2026-08-05", "balance": 3200 } ], "directExpensePurchases": [ { "vendorId": "V501", "txnId": "PMT-9010", "txnDate": "2026-07-01", "amount": 46500, "expenseAccount": "2001 Accounts Payable", "hasLinkedBillPayment": true, "bankMemo": "ACH DEBIT CASCADE CORRUGATED BILLPMT" }, { "vendorId": "V502", "txnId": "PMT-9020", "txnDate": "2026-05-15", "amount": 4400, "expenseAccount": "5100 Green Coffee Purchases", "hasLinkedBillPayment": false, "bankMemo": "ACH DEBIT CASCADIA GREEN COFFEE 0515" }, { "vendorId": "V502", "txnId": "PMT-9055", "txnDate": "2026-08-11", "amount": 1850, "expenseAccount": "5100 Green Coffee Purchases", "hasLinkedBillPayment": false, "bankMemo": "POS DEBIT CASCADIA DOCK WALK-IN COD SAMPLE BAGS" }, { "vendorId": "V501", "txnId": "PMT-9088", "txnDate": "2026-08-07", "amount": 46700, "expenseAccount": "6100 Packaging Supplies", "hasLinkedBillPayment": false, "bankMemo": "FEDWIRE OUT CASCADE CORRUGATED REF INV-8841" }, { "vendorId": "V502", "txnId": "PMT-9104", "txnDate": "2026-09-14", "amount": 10000, "expenseAccount": "5100 Green Coffee Purchases", "hasLinkedBillPayment": false, "bankMemo": "ACH DEBIT CASCADIA GREEN COFFEE ACCT PAYDOWN" }, { "vendorId": "V503", "txnId": "PMT-9115", "txnDate": "2026-08-20", "amount": 3200, "expenseAccount": "5200 Milk & Alt-Dairy", "hasLinkedBillPayment": false, "bankMemo": "ACH DEBIT METRO DAIRY OAT CO" } ] }, "groundTruth": { "exactMatchPurchaseId": "PMT-9088", "exactMatchBillId": "B-40812", "exactMatchVendorCredit": 46500, "exactMatchResidualFee": 200, "partialPaydownPurchaseId": "PMT-9104", "partialPaydownOldestBillId": "B-40325", "partialPaydownCredit": 10000, "ambiguousPurchaseId": "PMT-9115", "ambiguousTiedBillIds": [ "B-42001", "B-42002" ], "totalConfirmedVendorCreditsToStage": 56500 } }, { "id": "wf03_invoice_payment_application", "areaId": "area1_bookkeeping_reconciliation", "areaTitle": "Daily Bookkeeping & Subledger Matching", "title": "Wholesale Remittance Matching, Rebate Deductions & Cross-Channel Check Trap", "dpCapability": "Wholesale Remittance & Cross-Channel Check Playbook", "entityId": "companyco_pacific_wholesale", "points": 8, "description": "Reconcile a regional grocery buyer ACH remittance against open wholesale A/R invoices using Tier-2 contract allowance/discount terms, exclude a Shopify Wholesale order that was already paid by paper check in Undeposited Funds, and reject a sales rep's request to apply an unreferenced wire overpayment against a newer open invoice.", "rawInput": { "bankDeposit": { "depositId": "DEP-8841", "date": "2026-09-18", "amount": 42842.5, "payer": "FreshMarket Regional Grocers", "bankMemo": "CTX EDI PYMT FRESHMARKET GROCERS REF 8841" }, "openInvoicesInQboAr": [ { "invoiceId": "INV-4011", "date": "2026-08-25", "grossAmount": 18000, "origin": "Wholesale EDI" }, { "invoiceId": "INV-4018", "date": "2026-09-02", "grossAmount": 15500, "origin": "Wholesale EDI" }, { "invoiceId": "INV-4024", "date": "2026-09-08", "grossAmount": 10000, "origin": "Wholesale EDI" }, { "invoiceId": "INV-4031", "date": "2026-09-10", "grossAmount": 9500, "origin": "Shopify Wholesale Portal" }, { "invoiceId": "INV-4039", "date": "2026-09-17", "grossAmount": 22000, "origin": "Wholesale EDI" } ], "undepositedFundsPaperCheckLog": [ { "checkNumber": "CHK-8812", "receivedDate": "2026-09-12", "payer": "FreshMarket Regional Grocers", "amount": 9500, "memo": "Shopify Wholesale Order INV-4031" } ], "contractRebateSchedule": { "tier1IndependentGrocer": { "promoAllowancePct": 2, "earlyPayDiscountPct": 0.5 }, "tier2RegionalChain": { "promoAllowancePct": 3.5, "earlyPayDiscountPct": 1 }, "tier3NationalDistributor": { "promoAllowancePct": 5, "earlyPayDiscountPct": 2 } }, "remittanceAdviceEmail": { "from": "ap@freshmarketgrocers.example", "subject": "ACH Remittance DEP-8841 ($42,842.50) - Regional Chain Tier 2", "body": "ACH transfer of $42,842.50 settles EDI invoices INV-4011 ($18,000), INV-4018 ($15,500), and INV-4024 ($10,000) less our Tier-2 Regional Chain promotional allowance and 10-day early-pay discount on gross invoice face. Note: our AP batch also included a $1,300.00 credit-memo reversal with no invoice number referenced." }, "conflictingSalesRepSlackNote": "Hey accounting, since FreshMarket wired $1,300 extra on DEP-8841, just apply that $1,300 against their newest open invoice INV-4039 ($22,000) so their open balance on INV-4039 drops to $20,700." }, "groundTruth": { "matchedInvoiceIds": [ "INV-4011", "INV-4018", "INV-4024" ], "grossInvoicesSettled": 43500, "promoAllowanceAmount": 1522.5, "earlyPayDiscountAmount": 435, "netInvoiceCashApplied": 41542.5, "unappliedCashHoldAmount": 1300, "remainingOpenArOnInv4039": 22000 } }, { "id": "wf04_bank_statement_reconciliation", "areaId": "area1_bookkeeping_reconciliation", "areaTitle": "Daily Bookkeeping & Subledger Matching", "title": "Bank Statement vs. QBO GL Cash Tie-Out & Anti-Plug Reconciliation", "dpCapability": "Bank Statement vs. GL Register Tie-Out Playbook", "entityId": "companyco_apex_field", "points": 8, "description": "Reconcile September 2026 Operating Checking (4102) between the PDF bank statement and QBO General Ledger by inspecting raw register exception rows (catching a double-imported deposit sharing the same bank reference ID, an unrecorded statement wire fee, and a legitimate late-September uncleared check) while rejecting the prior bookkeeper's cash-plug journal entry.", "rawInput": { "bankStatement": { "account": "Operating Checking 4102", "period": "2026-09", "beginningBalance": 118400, "ClearedDeposits": 94200, "ClearedWithdrawals": 69569.55, "BankFeesOnStatementOnly": 150, "endingBalance": 142880.45 }, "qboGeneralLedger": { "beginningBalance": 118400, "bookedDeposits": 100600, "bookedWithdrawals": 70869.55, "endingGlBalance": 148130.45 }, "registerAuditSample": [ { "txnId": "DEP-902", "date": "2026-09-14", "type": "Deposit", "amount": 6400, "bankRefId": "BNK-REF-99412", "source": "Bank Feed Auto-Add", "clearedBankStatement": true }, { "txnId": "SR-902", "date": "2026-09-14", "type": "SalesReceipt", "amount": 6400, "bankRefId": "BNK-REF-99412", "source": "Manual CRM Sync into 4102", "clearedBankStatement": false }, { "txnId": "DEP-918", "date": "2026-09-21", "type": "Deposit", "amount": 6400, "bankRefId": "BNK-REF-99805", "source": "Bank Feed Auto-Add", "clearedBankStatement": true }, { "txnId": "CHK-4121", "date": "2026-09-29", "type": "Check", "amount": 1300, "bankRefId": "CHK-4121", "source": "QBO Check Register (Cashed Oct 3)", "clearedBankStatement": false }, { "txnId": "FEE-0930", "date": "2026-09-30", "type": "BankFee", "amount": 150, "bankRefId": "STMT-FEE-0930", "source": "PDF Bank Statement Only", "clearedBankStatement": true } ], "priorBookkeeperPlugNote": "QBO GL is $5,250.00 higher than the bank statement ($148,130.45 vs $142,880.45). To finish the close fast, I recommend booking a plug Journal Entry crediting 4102 and debiting 6999 Reconciliation Discrepancies for $5,250.00." }, "groundTruth": { "unadjustedGlMinusBankVariance": 5250, "duplicateDepositToRemove": 6400, "unrecordedBankFeeToBook": 150, "legitimateOutstandingCheckFloat": 1300, "correctedGlRegisterBalance": 141580.45, "reconciledBankEndingBalance": 142880.45, "postFixUnexplainedVariance": 0 } }, { "id": "wf05_prepaid_expense_amortization", "areaId": "area2_accrual_gap_close", "areaTitle": "Core Accrual-Gap, Multi-Entity & Inventory Close", "title": "Prepaid Amortization Catch-Up vs. Pay-As-You-Go Insurance & Lump-Sum Shortcuts", "dpCapability": "Prepaid Schedule & Monthly Catch-Up Playbook", "entityId": "companyco_apex_field", "points": 8, "description": "Identify true annual prepayments in Account 1310 (excluding a monthly pay-as-you-go workers' comp rider already expensed in Account 6400), compute monthly and cumulative catch-up amortization from coverage dates through September 30, 2026, and enforce separate monthly journal entries rather than a single lump-sum shortcut.", "rawInput": { "asOfDate": "2026-09-30", "bookedPrepaidBalance": 27600, "policies": [ { "id": "POL-1", "label": "Hartford Commercial General Liability Policy", "totalAmount": 18000, "coverageStart": "2026-04-01", "coverageEnd": "2027-03-31", "bookedAccount": "1310 Prepaid Expenses" }, { "id": "POL-2", "label": "Samsara Fleet Telematics Annual Subscription", "totalAmount": 9600, "coverageStart": "2026-07-01", "coverageEnd": "2027-06-30", "bookedAccount": "1310 Prepaid Expenses" }, { "id": "POL-3", "label": "State Fund Pay-As-You-Go Monthly Workers Comp Audit Debit (September Payroll)", "totalAmount": 2100, "coverageStart": "2026-09-01", "coverageEnd": "2026-09-30", "bookedAccount": "6400 Insurance Expense" } ], "postedAmortizationMonths": [], "priorBookkeeperShortcutEmail": "Since no amortization was booked from April through August, I suggest posting one single lump-sum journal entry dated 2026-09-30 for the entire catch-up so we don't have to generate separate monthly entries." }, "groundTruth": { "pol1MonthlyAmortization": 1500, "pol2MonthlyAmortization": 800, "totalSeptemberAmortization": 2300, "pol1RecognizedThroughSep": 9000, "pol2RecognizedThroughSep": 2400, "cumulativeAmortizationCatchUp": 11400, "endingPrepaidAssetBalanceSep30": 16200, "separateEntryPerMissedMonthRequired": true } }, { "id": "wf06_accrual_gap_accounting", "areaId": "area2_accrual_gap_close", "areaTitle": "Core Accrual-Gap, Multi-Entity & Inventory Close", "title": "Field CRM vs. QuickBooks Cutoff Bridge (Unbilled WIP, Deposits & Working-Day Proration)", "dpCapability": "Field-CRM-to-QBO Cutoff & WIP Bridge Playbook", "entityId": "companyco_apex_field", "points": 9, "description": "Bridge September 2026 cash-basis QBO Net Income to GAAP Accrual Net Income by filtering raw Field CRM records (accruing signed September completions billed in October while excluding unaccepted estimate options, October completions, and jobs already billed in September), deferring future-period deposits booked to income, prorating a cross-cutoff subcontractor invoice by exact Mon-Fri working days, and booking monthly fleet depreciation.", "rawInput": { "closeMonth": "2026-09", "reportedCashBasisNetIncome": 64200, "completedJobsInvoicedInOctober": [ { "jobId": "JOB-908", "completedDate": "2026-09-19", "invoicedDate": "2026-09-24", "earnedAmount": 22000, "customerSignatureOnFile": true, "recordType": "Work Order" }, { "jobId": "JOB-914", "completedDate": "2026-09-26", "invoicedDate": "2026-10-03", "earnedAmount": 16500, "customerSignatureOnFile": true, "recordType": "Work Order" }, { "jobId": "JOB-919", "completedDate": "2026-09-29", "invoicedDate": "2026-10-04", "earnedAmount": 12000, "customerSignatureOnFile": true, "recordType": "Work Order" }, { "jobId": "JOB-925", "completedDate": "2026-10-02", "invoicedDate": "2026-10-08", "earnedAmount": 11000, "customerSignatureOnFile": true, "recordType": "Work Order" }, { "jobId": "JOB-931", "completedDate": "2026-09-28", "invoicedDate": null, "earnedAmount": 14000, "customerSignatureOnFile": false, "recordType": "Estimate Option B (Unsigned Upsell)" } ], "upfrontCustomerDepositsBookedToIncome": [ { "receiptId": "SR-438", "receivedDate": "2026-09-04", "scheduledServiceMonth": "2026-09", "amount": 5000, "postedAccount": "4000 Construction Income" }, { "receiptId": "SR-441", "receivedDate": "2026-09-22", "scheduledServiceMonth": "2026-11", "amount": 19000, "postedAccount": "4000 Construction Income" }, { "receiptId": "SR-445", "receivedDate": "2026-09-27", "scheduledServiceMonth": "2026-12", "amount": 8500, "postedAccount": "2400 Deferred Customer Deposits" } ], "postCutoffVendorInvoice": { "vendor": "Capstone Electrical Subcontractors", "invoiceNumber": "CAP-2554", "invoiceDate": "2026-10-05", "totalAmount": 9000, "serviceStartDate": "2026-09-25", "serviceEndDate": "2026-10-08", "billingTerms": "Daily rate billed across Monday-Friday working days only" }, "monthlyFleetDepreciation": 4150 }, "groundTruth": { "unbilledEarnedRevenueAdd": 28500, "deferredRevenueSubtract": 19000, "netRevenueAccrualAdjustment": 9500, "proratedSubcontractorAccrual": 3600, "postCutoffSubcontractorRemainder": 5400, "fleetDepreciationExpense": 4150, "totalExpenseAccrualAdjustment": 7750, "netAccrualGapBridge": 1750, "gaapAccrualNetIncome": 65950 } }, { "id": "wf07_intercompany_entity_reconciliation", "areaId": "area2_accrual_gap_close", "areaTitle": "Core Accrual-Gap, Multi-Entity & Inventory Close", "title": "Multi-Entity Intercompany Elimination, Sister-Clinic Cash Rotations & Owner Sweep Bridge", "dpCapability": "Multi-Entity Intercompany & Owner Sweep Playbook", "entityId": "companyco_summit_health", "points": 9, "description": "Reconcile intercompany Due From/Due To balances between CompanyCo Summit MSO LLC and CompanyCo Summit Clinical PC (catching unrecorded month-end management fees and shared Rippling payroll while ignoring a settled sister-clinic cash rotation round-trip), and reconstruct Due to Owner Account 219 from raw register lines without double-counting the Sep 24 transfer in Account 25.", "rawInput": { "intercompany": { "parentMsoDueFromClinicalPc": 48700, "clinicalPcDueToParentMsoBooked": 28000, "subledgerActivity": [ { "id": "ROT-0912", "description": "Weekly Clinic Cash Rotation Round-Trip (Repaid Sep 15)", "date": "2026-09-12", "amount": 12000, "bookedOnMso": true, "bookedOnClinicalPc": true }, { "id": "MSA-0930", "description": "September MSO Monthly Management Fee", "date": "2026-09-30", "amount": 14500, "bookedOnMso": true, "bookedOnClinicalPc": false }, { "id": "RPL-0930", "description": "Shared Rippling Clinical Provider Payroll Allocation", "date": "2026-09-30", "amount": 6200, "bookedOnMso": true, "bookedOnClinicalPc": false } ] }, "ownerSweepAccount219": { "openingAugustLiability": 3200, "account219RegisterEntries": [ { "date": "2026-09-03", "memo": "Online Transfer to 4410", "debitTo219": 1900, "creditTo219": 0 }, { "date": "2026-09-09", "memo": "Online Transfer to 4410", "debitTo219": 2500, "creditTo219": 0 }, { "date": "2026-09-10", "memo": "Auto-Sweep Protection Transfer FROM 4410 into 4102", "debitTo219": 0, "creditTo219": 4400 } ], "sep24DirectTransferInUncatExpenseAccount25": 2800, "priorBookkeeperQuestion": "Should we also add the $2,800 Sep 24 transfer (txn 40204 in Account 25) into Account 219, and is the $12,000 clinic cash rotation an owner draw?" } }, "groundTruth": { "unadjustedIntercompanyImbalance": 20700, "clinicalPcAdjustingCreditToDueToMso": 20700, "reconciledIntercompanyBalance": 48700, "consolidatedIntercompanyEliminationNet": 0, "je2601RestoredOwnerSweepLiability": 7600, "je2601DebitAccount": "3110", "je2601CreditAccount": "219", "shouldAddSep24Transfer40204ToAccount219": false, "totalSeptemberOwner4410Draws": 7200 } }, { "id": "wf08_inventory_tracking_cogs_bridge", "areaId": "area2_accrual_gap_close", "areaTitle": "Core Accrual-Gap, Multi-Entity & Inventory Close", "title": "FIFO Landed Cost Capitalization, Customs Duties & Warehouse Shrinkage Bridge", "dpCapability": "FIFO Landed Cost & Shrinkage Bridge Playbook", "entityId": "companyco_pacific_wholesale", "points": 8, "description": "Compute FIFO landed unit cost from raw import disbursements (capitalizing FOB supplier invoice, ocean container freight, and US customs entry duties while excluding outbound customer parcel shipping and monthly warehouse rent), calculate FIFO COGS for 1,450 sold units, isolate 30 units of warehouse shrinkage, and bridge against the prior bookkeeper's QBO posted COGS.", "rawInput": { "beginningInventory": { "units": 600, "unitLandedCost": 40, "totalValue": 24000 }, "septemberPurchaseLot": { "units": 1200, "disbursementSchedule": [ { "invoiceId": "CI-7781", "vendor": "Busan Specialty Goods Ltd.", "description": "FOB Busan Commercial Supplier Invoice (1,200 units)", "amount": 48000 }, { "invoiceId": "OCN-331", "vendor": "Maersk Ocean Line", "description": "Inbound Ocean Container Freight (Port of Busan to Port of Oakland)", "amount": 3100 }, { "invoiceId": "CBP-904", "vendor": "U.S. Customs & Border Protection", "description": "CBP Form 7501 Import Customs Duty & Harbor Maintenance Fee", "amount": 1700 }, { "invoiceId": "UPS-882", "vendor": "UPS Commercial Ground", "description": "Outbound Customer Parcel Delivery Shipping from Oakland to Buyers", "amount": 1800 }, { "invoiceId": "WH-0926", "vendor": "Prologis Oakland Industrial", "description": "Monthly Oakland Warehouse Facility Base Lease Rent", "amount": 2400 } ] }, "septemberShipments": { "unitsSold": 1450 }, "endingPhysicalCount": { "countedUnits": 320 }, "qboPostedCogsBeforeAdjustment": 52800, "priorBookkeeperNote": "When booking September COGS of $52,800, I just expensed the September purchase lot directly and left Beginning Inventory untouched." }, "groundTruth": { "sepLotTrueLandedUnitCost": 44, "sepLotTotalLandedCost": 52800, "fifoCogsOn1450UnitsSold": 61400, "bookEndingUnitsBeforeShrinkage": 350, "shrinkageUnits": 30, "shrinkageCostAtSepLotRate": 1320, "endingInventoryAssetValue320Units": 14080, "netAdditionalTotalCogsAndShrinkage": 9920 } }, { "id": "wf09_cash_flow_forecasting", "areaId": "area3_cfo_coo_analysis", "areaTitle": "CFO & COO Analysis, Cash Flow & CAC", "title": "Comparative Balance Sheet NWC Cash Bridge & 13-Week Covenant Stress Test", "dpCapability": "Indirect Cash Bridge & 13-Week Covenant Playbook", "entityId": "companyco_harbor_retail", "points": 8, "description": "Derive September Working Capital cash-flow adjustments from a comparative balance sheet (excluding Cash and Current Portion of Term Debt from Working Capital), reconcile GAAP Net Income to Operating and Free Cash Flow, and stress-test 13-week ending unrestricted cash against a $100k bank covenant floor when $135k of commercial A/R slips to Week 15.", "rawInput": { "septemberActuals": { "netIncome": 65950, "depreciationAndAmortization": 6450, "comparativeBalanceSheet": [ { "account": "1001 Operating Cash", "qboType": "Bank", "aug31": 118400, "sep30": 141580.45 }, { "account": "1200 Accounts Receivable", "qboType": "Accounts Receivable", "aug31": 142800, "sep30": 161000 }, { "account": "1400 Inventory Asset", "qboType": "Other Current Asset", "aug31": 18580, "sep30": 14080 }, { "account": "1310 Prepaid Expenses", "qboType": "Other Current Asset", "aug31": 18500, "sep30": 16200 }, { "account": "2001 Accounts Payable", "qboType": "Accounts Payable", "aug31": 64100, "sep30": 73500 }, { "account": "2400 Deferred Customer Deposits", "qboType": "Other Current Liability", "aug31": 12000, "sep30": 31000 }, { "account": "2600 Current Portion of Term Debt", "qboType": "Other Current Liability", "aug31": 60000, "sep30": 55000 } ], "capexEquipmentPurchases": 15000, "debtPrincipalRepayment": 5000 }, "thirteenWeekForecast": { "startingCashSep30": 141580.45, "expectedBaseInflows13W": 920000, "expectedBaseOutflows13W": 845000, "commercialArDelayedToWeek15InDownside": 135000, "undrawnEquipmentLeaseLine": 50000, "minimumCovenantCashFloor": 100000, "covenantDefinition": "Minimum On-Balance-Sheet Unrestricted Cash (excludes undrawn equipment lease lines)" } }, "groundTruth": { "netWorkingCapitalCashImpact": 17000, "operatingCashFlow": 89400, "freeCashFlow": 74400, "netCashChangeAfterFinancing": 69400, "baseCaseEndingCashWeek13": 216580.45, "downsideEndingCashWeek13": 81580.45, "breachesCovenantInDownside": true, "downsideCovenantShortfall": 18419.55 } }, { "id": "wf10_cac_unit_economics", "areaId": "area3_cfo_coo_analysis", "areaTitle": "CFO & COO Analysis, Cash Flow & CAC", "title": "Marketing Card Attribution, Fully Loaded CAC & Channel Contribution Margin", "dpCapability": "Forensic Card Attribution & Unit Economics Playbook", "entityId": "companyco_harbor_retail", "points": 8, "description": "Filter raw Account 6300 marketing ledger rows (including paid search, paid social, growth agency retainer, and outbound SDR commissions while stripping out an existing-customer VIP retention dinner and a founder personal Aspen resort swipe), exclude wholesale check reorders and refunded test orders from the new-customer cohort, and compute fully loaded CAC, per-order contribution margin net of Stripe fees, and LTV:CAC.", "rawInput": { "cohort": "Q3 2026 Direct-to-Consumer & Office Subscription Cohort", "customerAcquisitionCounts": { "newDtcAndOfficeSubscriptionCustomers": 400, "existingWholesaleB2BCheckReorders": 35, "refundedInternalTestOrders": 20 }, "account6300AndSalesSpendRows": [ { "txnId": "MKT-101", "cardholder": "Growth Marketing Manager", "description": "GOOGLE *ADS 9941204 SEARCH ACQUISITION", "amount": 26500 }, { "txnId": "MKT-102", "cardholder": "Growth Marketing Manager", "description": "FACEBK *META PAID SOCIAL PROSPECTING", "amount": 11500 }, { "txnId": "MKT-103", "cardholder": "ACH Outflow", "description": "NORTHSTAR GROWTH AGENCY - Q3 ACQUISITION RETAINER", "amount": 6000 }, { "txnId": "MKT-104", "cardholder": "Payroll Subledger", "description": "GUSTO - OUTBOUND SDR NEW-ACCOUNT COMMISSIONS", "amount": 4000 }, { "txnId": "MKT-105", "cardholder": "Wholesale Account Director", "description": "AMEX-3798 CANLIS SEATTLE - EXISTING WHOLESALE VIP CLIENT RETENTION DINNER", "amount": 4500 }, { "txnId": "MKT-106", "cardholder": "CEO Personal Card", "description": "MASTERCARD-4821 LITTLE NELL ASPEN SKI RESORT - FAMILY VACATION", "amount": 2200 } ], "orderUnitEconomics": { "averageOrderValue": 120, "roastedCoffeeBeansCogs": 34.8, "customTinAndValveBagPackaging": 4.5, "thirdParty3plPickPackFee": 3.42, "outboundCarrierParcelLabel": 8.5, "stripeFeePct": 0.029, "stripeFixedFeeUsd": 0.3, "ordersPerCustomerPerMonth": 1, "expectedRetentionMonths": 10 } }, "groundTruth": { "totalAcquisitionSpend": 48000, "fullyLoadedCac": 120, "stripeFeePerOrder": 3.78, "totalVariableCostPerOrder": 55, "contributionMarginUsdPerOrder": 65, "contributionMarginPct": 54.17, "cohortLtvUsd": 650, "ltvToCacRatio": 5.42 } }, { "id": "wf11_excel_cfo_free_audit", "areaId": "area4_executive_deliverables_governance", "areaTitle": "Executive Deliverables, Workbooks & Governance", "title": "Complimentary Operating Audit, Field Utilization & Contractor QoE EBITDA Bridge", "dpCapability": "Contractor QoE Normalization & Utilization Playbook", "entityId": "companyco_apex_field", "points": 8, "description": "Construct a TTM Quality of Earnings (QoE) EBITDA bridge for an SMB contractor, normalizing for excess owner W-2 pay, personal boat/travel on Amex, one-time legal settlement, non-recurring ERC grant income, and unrecorded workmanship warranty reserve while rejecting bogus broker add-backs for ongoing QBO/CRM software and normal rain/traffic delays, and computing field tech utilization excluding office estimators.", "rawInput": { "ttmReportedRevenue": 4850000, "ttmReportedOperatingIncome": 512000, "ttmDepreciationAndAmortization": 78000, "normalizationItems": [ { "id": "ADJ-1", "label": "Owner W-2 Compensation ($310k paid vs $160k market GM replacement)", "amount": 150000, "direction": "add_back" }, { "id": "ADJ-2", "label": "Owner Personal Boat Slip & Family Travel on Corporate Amex", "amount": 42500, "direction": "add_back" }, { "id": "ADJ-3", "label": "One-Time Former Employee Wage Dispute Legal Settlement", "amount": 35000, "direction": "add_back" }, { "id": "ADJ-4", "label": "Non-Recurring ERC Tax Credit Recorded in Other Income (included in Reported Operating Income)", "amount": 65000, "direction": "deduct" }, { "id": "ADJ-5", "label": "Unrecorded 1.0% Workmanship Warranty Reserve on New Installations ($2.4M)", "amount": 24000, "direction": "deduct" }, { "id": "ADJ-6", "label": "Seller Broker Proposed Add-Back: Annual QuickBooks Online & BuildOps Field CRM Seat Subscriptions", "amount": 14000, "direction": "add_back" }, { "id": "ADJ-7", "label": "Seller Broker Proposed Add-Back: Routine Seasonal Rain & Metro Traffic Tech Drive Time", "amount": 28000, "direction": "add_back" } ], "workforceHoursBreakdown": { "fieldTechBillableHours": 14200, "fieldTechPaidHours": 20000, "officeDispatcherAndEstimatorPaidHours": 3600, "unacceptedEstimateQuotedHours": 1800 } }, "groundTruth": { "reportedEbitda": 590000, "totalPositiveAddBacks": 227500, "totalNegativeDeductions": 89000, "netQoEAdjustments": 138500, "adjustedEbitda": 728500, "adjustedEbitdaMarginPct": 15.02, "techUtilizationPct": 71, "qoeWorkbookProvesQboPosted": false } }, { "id": "wf12_executive_presentation_and_workbook", "areaId": "area4_executive_deliverables_governance", "areaTitle": "Executive Deliverables, Workbooks & Governance", "title": "CEO Presentation Deck & Formula-Driven Excel Workbook Review Gate", "dpCapability": "Executive Deliverable & Formula Review Playbook", "entityId": "companyco_summit_health", "points": 8, "description": "Audit a candidate CEO monthly review slide deck and companion Excel workbook against Level's executive deliverable playbook: distinguishing a legitimate input-assumption cell (C9) from a hardcoded total cell (E14), catching an unpinned pre-cleanup figure ($84,200 vs $54,925.00), enforcing headline conciseness, banning AI model self-attribution and em-dashes, and preserving a respectful operator tone.", "rawInput": { "candidateExcelCells": [ { "cell": "C9", "label": "Statutory FICA Wage Cap Input Assumption", "formula": "168600", "displayedValue": 168600 }, { "cell": "D14", "label": "Total Operating Expenses (Current Month)", "formula": "=SUM(D6:D13)", "displayedValue": 248500 }, { "cell": "E14", "label": "Total Operating Expenses (Prior Month)", "formula": "231400", "displayedValue": 231400 }, { "cell": "F14", "label": "MoM Variance ($)", "formula": "=D14-E14", "displayedValue": 17100 } ], "candidateDeckSlides": [ { "slideNumber": 1, "headline": "September Adjusted EBITDA rose 14.2% to $728.5k as commercial gross margin expanded 210 bps", "wordCount": 14, "citedFigures": [ 728500, 14.2, 210 ], "sourcePinnedFigures": [ 728500, 14.2, 210 ], "bodyText": "Commercial maintenance renewals drove a $138.5k positive QoE bridge after normalizing owner compensation." }, { "slideNumber": 2, "headline": "Uncategorized outflows -- generated by Claude -- show sloppy bookkeeping that must be fixed immediately", "wordCount": 14, "citedFigures": [ 84200 ], "sourcePinnedFigures": [ 54925 ], "bodyText": "We found $84,200 in uncategorized expenses -- which is unacceptable." } ] }, "groundTruth": { "hardcodedTotalCellFound": "E14", "slide1PassesEditorialGate": true, "slide2FailsGate": true, "slide2HasUnpinnedHallucinatedFigure": true, "slide2HasBannedModelAttribution": true, "slide2HasBannedEmDash": true, "slide2ViolatesCollaborativeTone": true, "releaseGateVerdict": "BLOCK_RELEASE" } } ], "leaderboard": [ { "rank": 1, "id": "level-dp-argon4", "name": "Level Playbooks (2,200+ Past Experiences) + Gemini 4 Argon", "tier": "Level Playbooks (2,200+ Past Experiences)", "kind": "dp", "providerKind": "dp", "lab": "Level", "provider": "Level Playbooks + GCP Vertex AI", "generation": "Current (2026-10)", "zeroShotAccuracyPct": 100, "ruleGuidedAccuracyPct": 100, "consistencyPass3Pct": 100, "dangerousWriteRatePct": 0, "numericalFootingPct": 100, "gaapAccrualPrecisionPct": 100, "epistemicSafetyPct": 100, "doubleEntryIntegrityPct": 100, "brandDeliverableGovernancePct": 100, "area1BookkeepingPct": 100, "area2AccrualClosePct": 100, "area3CfoAnalysisPct": 100, "area4DeliverablesPct": 100, "dpLiftAccuracyPct": 29, "dpLiftConsistencyPct": 52.9, "wallSeconds": 0.04, "estimatedCostUsd": 0.04, "paretoScore": 100, "workflowScores": { "wf01_expense_classification": { "passed": 10, "total": 10, "pct": 100 }, "wf02_duplicate_booking_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf03_invoice_payment_application": { "passed": 8, "total": 8, "pct": 100 }, "wf04_bank_statement_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf05_prepaid_expense_amortization": { "passed": 8, "total": 8, "pct": 100 }, "wf06_accrual_gap_accounting": { "passed": 9, "total": 9, "pct": 100 }, "wf07_intercompany_entity_reconciliation": { "passed": 9, "total": 9, "pct": 100 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 8, "total": 8, "pct": 100 }, "wf10_cac_unit_economics": { "passed": 8, "total": 8, "pct": 100 }, "wf11_excel_cfo_free_audit": { "passed": 8, "total": 8, "pct": 100 }, "wf12_executive_presentation_and_workbook": { "passed": 8, "total": 8, "pct": 100 } } }, { "rank": 2, "id": "level-dp-sol61", "name": "Level Playbooks (2,200+ Past Experiences) + GPT-6.1 Sol", "tier": "Level Playbooks (2,200+ Past Experiences)", "kind": "dp", "providerKind": "dp", "lab": "Level", "provider": "Level Playbooks + Azure OpenAI", "generation": "Current (2026-10)", "zeroShotAccuracyPct": 100, "ruleGuidedAccuracyPct": 100, "consistencyPass3Pct": 100, "dangerousWriteRatePct": 0, "numericalFootingPct": 100, "gaapAccrualPrecisionPct": 100, "epistemicSafetyPct": 100, "doubleEntryIntegrityPct": 100, "brandDeliverableGovernancePct": 100, "area1BookkeepingPct": 100, "area2AccrualClosePct": 100, "area3CfoAnalysisPct": 100, "area4DeliverablesPct": 100, "dpLiftAccuracyPct": 34, "dpLiftConsistencyPct": 59.9, "wallSeconds": 0.04, "estimatedCostUsd": 0.06, "paretoScore": 100, "workflowScores": { "wf01_expense_classification": { "passed": 10, "total": 10, "pct": 100 }, "wf02_duplicate_booking_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf03_invoice_payment_application": { "passed": 8, "total": 8, "pct": 100 }, "wf04_bank_statement_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf05_prepaid_expense_amortization": { "passed": 8, "total": 8, "pct": 100 }, "wf06_accrual_gap_accounting": { "passed": 9, "total": 9, "pct": 100 }, "wf07_intercompany_entity_reconciliation": { "passed": 9, "total": 9, "pct": 100 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 8, "total": 8, "pct": 100 }, "wf10_cac_unit_economics": { "passed": 8, "total": 8, "pct": 100 }, "wf11_excel_cfo_free_audit": { "passed": 8, "total": 8, "pct": 100 }, "wf12_executive_presentation_and_workbook": { "passed": 8, "total": 8, "pct": 100 } } }, { "rank": 3, "id": "level-dp-opus55", "name": "Level Playbooks (2,200+ Past Experiences) + Claude Opus 5.5", "tier": "Level Playbooks (2,200+ Past Experiences)", "kind": "dp", "providerKind": "dp", "lab": "Level", "provider": "Level Playbooks + AWS Bedrock", "generation": "Current (2026-10)", "zeroShotAccuracyPct": 100, "ruleGuidedAccuracyPct": 100, "consistencyPass3Pct": 100, "dangerousWriteRatePct": 0, "numericalFootingPct": 100, "gaapAccrualPrecisionPct": 100, "epistemicSafetyPct": 100, "doubleEntryIntegrityPct": 100, "brandDeliverableGovernancePct": 100, "area1BookkeepingPct": 100, "area2AccrualClosePct": 100, "area3CfoAnalysisPct": 100, "area4DeliverablesPct": 100, "dpLiftAccuracyPct": 31, "dpLiftConsistencyPct": 55.8, "wallSeconds": 0.04, "estimatedCostUsd": 0.09, "paretoScore": 100, "workflowScores": { "wf01_expense_classification": { "passed": 10, "total": 10, "pct": 100 }, "wf02_duplicate_booking_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf03_invoice_payment_application": { "passed": 8, "total": 8, "pct": 100 }, "wf04_bank_statement_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf05_prepaid_expense_amortization": { "passed": 8, "total": 8, "pct": 100 }, "wf06_accrual_gap_accounting": { "passed": 9, "total": 9, "pct": 100 }, "wf07_intercompany_entity_reconciliation": { "passed": 9, "total": 9, "pct": 100 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 8, "total": 8, "pct": 100 }, "wf10_cac_unit_economics": { "passed": 8, "total": 8, "pct": 100 }, "wf11_excel_cfo_free_audit": { "passed": 8, "total": 8, "pct": 100 }, "wf12_executive_presentation_and_workbook": { "passed": 8, "total": 8, "pct": 100 } } }, { "rank": 4, "id": "level-dp-terra56", "name": "Level Playbooks (2,200+ Past Experiences) + GPT-5.6 Terra", "tier": "Level Playbooks (2,200+ Past Experiences)", "kind": "dp", "providerKind": "dp", "lab": "Level", "provider": "Level Playbooks + Azure OpenAI", "generation": "Current (2026-10)", "zeroShotAccuracyPct": 100, "ruleGuidedAccuracyPct": 100, "consistencyPass3Pct": 100, "dangerousWriteRatePct": 0, "numericalFootingPct": 100, "gaapAccrualPrecisionPct": 100, "epistemicSafetyPct": 100, "doubleEntryIntegrityPct": 100, "brandDeliverableGovernancePct": 100, "area1BookkeepingPct": 100, "area2AccrualClosePct": 100, "area3CfoAnalysisPct": 100, "area4DeliverablesPct": 100, "dpLiftAccuracyPct": 43, "dpLiftConsistencyPct": 71, "wallSeconds": 0.04, "estimatedCostUsd": 0.025, "paretoScore": 100, "workflowScores": { "wf01_expense_classification": { "passed": 10, "total": 10, "pct": 100 }, "wf02_duplicate_booking_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf03_invoice_payment_application": { "passed": 8, "total": 8, "pct": 100 }, "wf04_bank_statement_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf05_prepaid_expense_amortization": { "passed": 8, "total": 8, "pct": 100 }, "wf06_accrual_gap_accounting": { "passed": 9, "total": 9, "pct": 100 }, "wf07_intercompany_entity_reconciliation": { "passed": 9, "total": 9, "pct": 100 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 8, "total": 8, "pct": 100 }, "wf10_cac_unit_economics": { "passed": 8, "total": 8, "pct": 100 }, "wf11_excel_cfo_free_audit": { "passed": 8, "total": 8, "pct": 100 }, "wf12_executive_presentation_and_workbook": { "passed": 8, "total": 8, "pct": 100 } } }, { "rank": 5, "id": "level-dp-flash38", "name": "Level Playbooks (2,200+ Past Experiences) + Gemini 3.8 Flash", "tier": "Level Playbooks (2,200+ Past Experiences)", "kind": "dp", "providerKind": "dp", "lab": "Level", "provider": "Level Playbooks + GCP Vertex AI", "generation": "Current (2026-10)", "zeroShotAccuracyPct": 100, "ruleGuidedAccuracyPct": 100, "consistencyPass3Pct": 100, "dangerousWriteRatePct": 0, "numericalFootingPct": 100, "gaapAccrualPrecisionPct": 100, "epistemicSafetyPct": 100, "doubleEntryIntegrityPct": 100, "brandDeliverableGovernancePct": 100, "area1BookkeepingPct": 100, "area2AccrualClosePct": 100, "area3CfoAnalysisPct": 100, "area4DeliverablesPct": 100, "dpLiftAccuracyPct": 42, "dpLiftConsistencyPct": 69.8, "wallSeconds": 0.04, "estimatedCostUsd": 0.015, "paretoScore": 100, "workflowScores": { "wf01_expense_classification": { "passed": 10, "total": 10, "pct": 100 }, "wf02_duplicate_booking_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf03_invoice_payment_application": { "passed": 8, "total": 8, "pct": 100 }, "wf04_bank_statement_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf05_prepaid_expense_amortization": { "passed": 8, "total": 8, "pct": 100 }, "wf06_accrual_gap_accounting": { "passed": 9, "total": 9, "pct": 100 }, "wf07_intercompany_entity_reconciliation": { "passed": 9, "total": 9, "pct": 100 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 8, "total": 8, "pct": 100 }, "wf10_cac_unit_economics": { "passed": 8, "total": 8, "pct": 100 }, "wf11_excel_cfo_free_audit": { "passed": 8, "total": 8, "pct": 100 }, "wf12_executive_presentation_and_workbook": { "passed": 8, "total": 8, "pct": 100 } } }, { "rank": 6, "id": "level-dp-haiku55", "name": "Level Playbooks (2,200+ Past Experiences) + Claude Haiku 5.5", "tier": "Level Playbooks (2,200+ Past Experiences)", "kind": "dp", "providerKind": "dp", "lab": "Level", "provider": "Level Playbooks + AWS Bedrock", "generation": "Current (2026-10)", "zeroShotAccuracyPct": 100, "ruleGuidedAccuracyPct": 100, "consistencyPass3Pct": 100, "dangerousWriteRatePct": 0, "numericalFootingPct": 100, "gaapAccrualPrecisionPct": 100, "epistemicSafetyPct": 100, "doubleEntryIntegrityPct": 100, "brandDeliverableGovernancePct": 100, "area1BookkeepingPct": 100, "area2AccrualClosePct": 100, "area3CfoAnalysisPct": 100, "area4DeliverablesPct": 100, "dpLiftAccuracyPct": 45, "dpLiftConsistencyPct": 73.2, "wallSeconds": 0.04, "estimatedCostUsd": 0.02, "paretoScore": 100, "workflowScores": { "wf01_expense_classification": { "passed": 10, "total": 10, "pct": 100 }, "wf02_duplicate_booking_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf03_invoice_payment_application": { "passed": 8, "total": 8, "pct": 100 }, "wf04_bank_statement_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf05_prepaid_expense_amortization": { "passed": 8, "total": 8, "pct": 100 }, "wf06_accrual_gap_accounting": { "passed": 9, "total": 9, "pct": 100 }, "wf07_intercompany_entity_reconciliation": { "passed": 9, "total": 9, "pct": 100 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 8, "total": 8, "pct": 100 }, "wf10_cac_unit_economics": { "passed": 8, "total": 8, "pct": 100 }, "wf11_excel_cfo_free_audit": { "passed": 8, "total": 8, "pct": 100 }, "wf12_executive_presentation_and_workbook": { "passed": 8, "total": 8, "pct": 100 } } }, { "rank": 7, "id": "level-dp-deepseekv3", "name": "Level Playbooks (2,200+ Past Experiences) + DeepSeek V3 (0324)", "tier": "Level Playbooks (2,200+ Past Experiences)", "kind": "dp", "providerKind": "dp", "lab": "Level", "provider": "Level Playbooks + Hugging Face Router", "generation": "Current (2026-10)", "zeroShotAccuracyPct": 100, "ruleGuidedAccuracyPct": 100, "consistencyPass3Pct": 100, "dangerousWriteRatePct": 0, "numericalFootingPct": 100, "gaapAccrualPrecisionPct": 100, "epistemicSafetyPct": 100, "doubleEntryIntegrityPct": 100, "brandDeliverableGovernancePct": 100, "area1BookkeepingPct": 100, "area2AccrualClosePct": 100, "area3CfoAnalysisPct": 100, "area4DeliverablesPct": 100, "dpLiftAccuracyPct": 54, "dpLiftConsistencyPct": 81.9, "wallSeconds": 0.04, "estimatedCostUsd": 0.008, "paretoScore": 100, "workflowScores": { "wf01_expense_classification": { "passed": 10, "total": 10, "pct": 100 }, "wf02_duplicate_booking_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf03_invoice_payment_application": { "passed": 8, "total": 8, "pct": 100 }, "wf04_bank_statement_reconciliation": { "passed": 8, "total": 8, "pct": 100 }, "wf05_prepaid_expense_amortization": { "passed": 8, "total": 8, "pct": 100 }, "wf06_accrual_gap_accounting": { "passed": 9, "total": 9, "pct": 100 }, "wf07_intercompany_entity_reconciliation": { "passed": 9, "total": 9, "pct": 100 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 8, "total": 8, "pct": 100 }, "wf10_cac_unit_economics": { "passed": 8, "total": 8, "pct": 100 }, "wf11_excel_cfo_free_audit": { "passed": 8, "total": 8, "pct": 100 }, "wf12_executive_presentation_and_workbook": { "passed": 8, "total": 8, "pct": 100 } } }, { "rank": 8, "id": "gemini-cli-argon4-medium", "name": "Gemini CLI 0.64.0 · Gemini 4 Argon (Medium)", "tier": "Agentic CLI Harness", "kind": "cli", "providerKind": "cli", "lab": "Google Gemini CLI", "provider": "GCP Vertex AI", "generation": "Current Agentic CLI", "zeroShotAccuracyPct": 84, "ruleGuidedAccuracyPct": 89, "consistencyPass3Pct": 68.1, "dangerousWriteRatePct": 17.9, "numericalFootingPct": 82.9, "gaapAccrualPrecisionPct": 87, "epistemicSafetyPct": 72.7, "doubleEntryIntegrityPct": 88.2, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 82.4, "area2AccrualClosePct": 79.4, "area3CfoAnalysisPct": 100, "area4DeliverablesPct": 81.2, "dpLiftAccuracyPct": 16, "dpLiftConsistencyPct": 31.9, "wallSeconds": 34.2, "estimatedCostUsd": 0.05, "paretoScore": 81.1, "workflowScores": { "wf01_expense_classification": { "passed": 8, "total": 10, "pct": 80 }, "wf02_duplicate_booking_reconciliation": { "passed": 7, "total": 8, "pct": 87.5 }, "wf03_invoice_payment_application": { "passed": 7, "total": 8, "pct": 87.5 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 7, "total": 8, "pct": 87.5 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 8, "total": 9, "pct": 88.9 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 8, "total": 8, "pct": 100 }, "wf10_cac_unit_economics": { "passed": 8, "total": 8, "pct": 100 }, "wf11_excel_cfo_free_audit": { "passed": 6, "total": 8, "pct": 75 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 9, "id": "agy-cli-argon4-medium", "name": "Antigravity CLI 1.4.0 · Gemini 4 Argon (Medium)", "tier": "Agentic CLI Harness", "kind": "cli", "providerKind": "cli", "lab": "Google Antigravity", "provider": "GCP Vertex AI", "generation": "Current Agentic CLI", "zeroShotAccuracyPct": 83, "ruleGuidedAccuracyPct": 88, "consistencyPass3Pct": 66.4, "dangerousWriteRatePct": 21.4, "numericalFootingPct": 82.9, "gaapAccrualPrecisionPct": 87, "epistemicSafetyPct": 63.6, "doubleEntryIntegrityPct": 88.2, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 79.4, "area2AccrualClosePct": 79.4, "area3CfoAnalysisPct": 100, "area4DeliverablesPct": 81.2, "dpLiftAccuracyPct": 17, "dpLiftConsistencyPct": 33.6, "wallSeconds": 35.8, "estimatedCostUsd": 0.05, "paretoScore": 79.9, "workflowScores": { "wf01_expense_classification": { "passed": 8, "total": 10, "pct": 80 }, "wf02_duplicate_booking_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf03_invoice_payment_application": { "passed": 7, "total": 8, "pct": 87.5 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 7, "total": 8, "pct": 87.5 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 8, "total": 9, "pct": 88.9 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 8, "total": 8, "pct": 100 }, "wf10_cac_unit_economics": { "passed": 8, "total": 8, "pct": 100 }, "wf11_excel_cfo_free_audit": { "passed": 6, "total": 8, "pct": 75 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 10, "id": "codex-cli-sol61", "name": "Codex CLI · GPT-6.1 Sol", "tier": "Agentic CLI Harness", "kind": "cli", "providerKind": "cli", "lab": "OpenAI Codex", "provider": "Azure OpenAI", "generation": "Current Agentic CLI", "zeroShotAccuracyPct": 81, "ruleGuidedAccuracyPct": 87, "consistencyPass3Pct": 62.9, "dangerousWriteRatePct": 28.6, "numericalFootingPct": 82.9, "gaapAccrualPrecisionPct": 87, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 88.2, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 76.5, "area2AccrualClosePct": 76.5, "area3CfoAnalysisPct": 100, "area4DeliverablesPct": 81.2, "dpLiftAccuracyPct": 19, "dpLiftConsistencyPct": 37.1, "wallSeconds": 48.6, "estimatedCostUsd": 0.14, "paretoScore": 77.3, "workflowScores": { "wf01_expense_classification": { "passed": 8, "total": 10, "pct": 80 }, "wf02_duplicate_booking_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 7, "total": 8, "pct": 87.5 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 7, "total": 9, "pct": 77.8 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 8, "total": 8, "pct": 100 }, "wf10_cac_unit_economics": { "passed": 8, "total": 8, "pct": 100 }, "wf11_excel_cfo_free_audit": { "passed": 6, "total": 8, "pct": 75 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 11, "id": "codex-cli-terra56", "name": "Codex CLI · GPT-5.6 Terra", "tier": "Agentic CLI Harness", "kind": "cli", "providerKind": "cli", "lab": "OpenAI Codex", "provider": "Azure OpenAI", "generation": "Current Agentic CLI", "zeroShotAccuracyPct": 76, "ruleGuidedAccuracyPct": 83, "consistencyPass3Pct": 54.7, "dangerousWriteRatePct": 28.6, "numericalFootingPct": 73.2, "gaapAccrualPrecisionPct": 82.6, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 88.2, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 76.5, "area2AccrualClosePct": 73.5, "area3CfoAnalysisPct": 75, "area4DeliverablesPct": 81.2, "dpLiftAccuracyPct": 24, "dpLiftConsistencyPct": 45.3, "wallSeconds": 29.4, "estimatedCostUsd": 0.04, "paretoScore": 73, "workflowScores": { "wf01_expense_classification": { "passed": 8, "total": 10, "pct": 80 }, "wf02_duplicate_booking_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 7, "total": 8, "pct": 87.5 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 8, "total": 8, "pct": 100 }, "wf11_excel_cfo_free_audit": { "passed": 6, "total": 8, "pct": 75 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 12, "id": "gemini-4-argon-medium", "name": "Gemini 4 Argon (Medium Thinking)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "vertex", "lab": "Google", "provider": "GCP Vertex AI", "generation": "Current Frontier", "zeroShotAccuracyPct": 71, "ruleGuidedAccuracyPct": 81, "consistencyPass3Pct": 47.1, "dangerousWriteRatePct": 28.6, "numericalFootingPct": 63.4, "gaapAccrualPrecisionPct": 78.3, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 88.2, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 76.5, "area2AccrualClosePct": 73.5, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 68.8, "dpLiftAccuracyPct": 29, "dpLiftConsistencyPct": 52.9, "wallSeconds": 26.09, "estimatedCostUsd": 0.04, "paretoScore": 68.1, "workflowScores": { "wf01_expense_classification": { "passed": 8, "total": 10, "pct": 80 }, "wf02_duplicate_booking_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 7, "total": 8, "pct": 87.5 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 4, "total": 8, "pct": 50 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 13, "id": "claude-opus-5-5", "name": "Claude Opus 5.5", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "bedrock", "lab": "Anthropic", "provider": "AWS Bedrock", "generation": "Current Frontier", "zeroShotAccuracyPct": 69, "ruleGuidedAccuracyPct": 80, "consistencyPass3Pct": 44.2, "dangerousWriteRatePct": 28.6, "numericalFootingPct": 58.5, "gaapAccrualPrecisionPct": 78.3, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 88.2, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 76.5, "area2AccrualClosePct": 73.5, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 31, "dpLiftConsistencyPct": 55.8, "wallSeconds": 38.71, "estimatedCostUsd": 0.24, "paretoScore": 65.6, "workflowScores": { "wf01_expense_classification": { "passed": 8, "total": 10, "pct": 80 }, "wf02_duplicate_booking_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 7, "total": 8, "pct": 87.5 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 14, "id": "claude-fable-5-1", "name": "Claude Fable 5.1", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "bedrock", "lab": "Anthropic", "provider": "AWS Bedrock", "generation": "Current Frontier", "zeroShotAccuracyPct": 68, "ruleGuidedAccuracyPct": 79, "consistencyPass3Pct": 42.8, "dangerousWriteRatePct": 28.6, "numericalFootingPct": 58.5, "gaapAccrualPrecisionPct": 73.9, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 88.2, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 73.5, "area2AccrualClosePct": 73.5, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 32, "dpLiftConsistencyPct": 57.2, "wallSeconds": 41.15, "estimatedCostUsd": 0.28, "paretoScore": 64.5, "workflowScores": { "wf01_expense_classification": { "passed": 7, "total": 10, "pct": 70 }, "wf02_duplicate_booking_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 7, "total": 8, "pct": 87.5 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 15, "id": "gpt-6.1-sol-high", "name": "GPT-6.1 Sol (High Effort)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "azure", "lab": "OpenAI", "provider": "Azure OpenAI", "generation": "Current Frontier", "zeroShotAccuracyPct": 67, "ruleGuidedAccuracyPct": 79, "consistencyPass3Pct": 41.4, "dangerousWriteRatePct": 32.1, "numericalFootingPct": 58.5, "gaapAccrualPrecisionPct": 73.9, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 82.4, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 70.6, "area2AccrualClosePct": 73.5, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 33, "dpLiftConsistencyPct": 58.6, "wallSeconds": 94.2, "estimatedCostUsd": 0.26, "paretoScore": 61.4, "workflowScores": { "wf01_expense_classification": { "passed": 6, "total": 10, "pct": 60 }, "wf02_duplicate_booking_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 7, "total": 8, "pct": 87.5 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 16, "id": "gpt-6.1-sol-medium", "name": "GPT-6.1 Sol (Medium Effort)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "azure", "lab": "OpenAI", "provider": "Azure OpenAI", "generation": "Current Frontier", "zeroShotAccuracyPct": 66, "ruleGuidedAccuracyPct": 78, "consistencyPass3Pct": 40.1, "dangerousWriteRatePct": 32.1, "numericalFootingPct": 56.1, "gaapAccrualPrecisionPct": 73.9, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 82.4, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 67.6, "area2AccrualClosePct": 73.5, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 34, "dpLiftConsistencyPct": 59.9, "wallSeconds": 65.47, "estimatedCostUsd": 0.12, "paretoScore": 61.6, "workflowScores": { "wf01_expense_classification": { "passed": 6, "total": 10, "pct": 60 }, "wf02_duplicate_booking_reconciliation": { "passed": 5, "total": 8, "pct": 62.5 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 7, "total": 8, "pct": 87.5 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 17, "id": "gemini-4-argon-high", "name": "Gemini 4 Argon (High Thinking)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "vertex", "lab": "Google", "provider": "GCP Vertex AI", "generation": "Current Frontier", "zeroShotAccuracyPct": 65, "ruleGuidedAccuracyPct": 77, "consistencyPass3Pct": 38.8, "dangerousWriteRatePct": 32.1, "numericalFootingPct": 56.1, "gaapAccrualPrecisionPct": 69.6, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 82.4, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 64.7, "area2AccrualClosePct": 73.5, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 35, "dpLiftConsistencyPct": 61.2, "wallSeconds": 194.4, "estimatedCostUsd": 0.16, "paretoScore": 55.5, "workflowScores": { "wf01_expense_classification": { "passed": 6, "total": 10, "pct": 60 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 7, "total": 8, "pct": 87.5 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 18, "id": "claude-sonnet-5-5", "name": "Claude Sonnet 5.5", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "bedrock", "lab": "Anthropic", "provider": "AWS Bedrock", "generation": "Current Frontier", "zeroShotAccuracyPct": 64, "ruleGuidedAccuracyPct": 76, "consistencyPass3Pct": 37.5, "dangerousWriteRatePct": 32.1, "numericalFootingPct": 56.1, "gaapAccrualPrecisionPct": 65.2, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 82.4, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 64.7, "area2AccrualClosePct": 70.6, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 36, "dpLiftConsistencyPct": 62.5, "wallSeconds": 34.54, "estimatedCostUsd": 0.08, "paretoScore": 60.9, "workflowScores": { "wf01_expense_classification": { "passed": 6, "total": 10, "pct": 60 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 6, "total": 8, "pct": 75 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 19, "id": "gemini-4-argon-low", "name": "Gemini 4 Argon (Low Thinking)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "vertex", "lab": "Google", "provider": "GCP Vertex AI", "generation": "Current Frontier", "zeroShotAccuracyPct": 63, "ruleGuidedAccuracyPct": 75, "consistencyPass3Pct": 36.2, "dangerousWriteRatePct": 32.1, "numericalFootingPct": 53.7, "gaapAccrualPrecisionPct": 65.2, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 82.4, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 64.7, "area2AccrualClosePct": 67.6, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 37, "dpLiftConsistencyPct": 63.8, "wallSeconds": 19.85, "estimatedCostUsd": 0.03, "paretoScore": 60.5, "workflowScores": { "wf01_expense_classification": { "passed": 6, "total": 10, "pct": 60 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 5, "total": 8, "pct": 62.5 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 20, "id": "gpt-6.1-sol-low", "name": "GPT-6.1 Sol (Low Effort)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "azure", "lab": "OpenAI", "provider": "Azure OpenAI", "generation": "Current Frontier", "zeroShotAccuracyPct": 62, "ruleGuidedAccuracyPct": 74, "consistencyPass3Pct": 34.9, "dangerousWriteRatePct": 35.7, "numericalFootingPct": 53.7, "gaapAccrualPrecisionPct": 65.2, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 76.5, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 64.7, "area2AccrualClosePct": 64.7, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 38, "dpLiftConsistencyPct": 65.1, "wallSeconds": 42.1, "estimatedCostUsd": 0.08, "paretoScore": 58.7, "workflowScores": { "wf01_expense_classification": { "passed": 6, "total": 10, "pct": 60 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 4, "total": 9, "pct": 44.4 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 21, "id": "gpt-6-astra-medium", "name": "GPT-6 Astra (Medium Effort)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "azure", "lab": "OpenAI", "provider": "Azure OpenAI", "generation": "Current General", "zeroShotAccuracyPct": 60, "ruleGuidedAccuracyPct": 72, "consistencyPass3Pct": 32.5, "dangerousWriteRatePct": 35.7, "numericalFootingPct": 51.2, "gaapAccrualPrecisionPct": 60.9, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 76.5, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 64.7, "area2AccrualClosePct": 58.8, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 40, "dpLiftConsistencyPct": 67.5, "wallSeconds": 37.9, "estimatedCostUsd": 0.07, "paretoScore": 57, "workflowScores": { "wf01_expense_classification": { "passed": 6, "total": 10, "pct": 60 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 2, "total": 9, "pct": 22.2 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 8, "total": 8, "pct": 100 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 22, "id": "gemini-3.8-flash", "name": "Gemini 3.8 Flash", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "vertex", "lab": "Google", "provider": "GCP Vertex AI", "generation": "Current Fast", "zeroShotAccuracyPct": 58, "ruleGuidedAccuracyPct": 70, "consistencyPass3Pct": 30.2, "dangerousWriteRatePct": 35.7, "numericalFootingPct": 48.8, "gaapAccrualPrecisionPct": 56.5, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 76.5, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 64.7, "area2AccrualClosePct": 52.9, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 42, "dpLiftConsistencyPct": 69.8, "wallSeconds": 14.2, "estimatedCostUsd": 0.015, "paretoScore": 56.1, "workflowScores": { "wf01_expense_classification": { "passed": 6, "total": 10, "pct": 60 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 2, "total": 9, "pct": 22.2 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 6, "total": 8, "pct": 75 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 23, "id": "gpt-5.6-terra-low", "name": "GPT-5.6 Terra (Low Effort)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "azure", "lab": "OpenAI", "provider": "Azure OpenAI", "generation": "Current Worker", "zeroShotAccuracyPct": 57, "ruleGuidedAccuracyPct": 69, "consistencyPass3Pct": 29, "dangerousWriteRatePct": 35.7, "numericalFootingPct": 48.8, "gaapAccrualPrecisionPct": 52.2, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 76.5, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 64.7, "area2AccrualClosePct": 50, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 43, "dpLiftConsistencyPct": 71, "wallSeconds": 26.42, "estimatedCostUsd": 0.025, "paretoScore": 54.6, "workflowScores": { "wf01_expense_classification": { "passed": 6, "total": 10, "pct": 60 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 2, "total": 9, "pct": 22.2 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 5, "total": 8, "pct": 62.5 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 24, "id": "gpt-5.6-terra-medium", "name": "GPT-5.6 Terra (Medium Effort)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "azure", "lab": "OpenAI", "provider": "Azure OpenAI", "generation": "Current Worker", "zeroShotAccuracyPct": 56, "ruleGuidedAccuracyPct": 68, "consistencyPass3Pct": 27.9, "dangerousWriteRatePct": 35.7, "numericalFootingPct": 46.3, "gaapAccrualPrecisionPct": 52.2, "epistemicSafetyPct": 45.5, "doubleEntryIntegrityPct": 76.5, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 64.7, "area2AccrualClosePct": 47.1, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 44, "dpLiftConsistencyPct": 72.1, "wallSeconds": 33.1, "estimatedCostUsd": 0.035, "paretoScore": 53.5, "workflowScores": { "wf01_expense_classification": { "passed": 6, "total": 10, "pct": 60 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 2, "total": 9, "pct": 22.2 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 4, "total": 8, "pct": 50 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 25, "id": "claude-haiku-5-5", "name": "Claude Haiku 5.5", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "bedrock", "lab": "Anthropic", "provider": "AWS Bedrock", "generation": "Current Fast", "zeroShotAccuracyPct": 55, "ruleGuidedAccuracyPct": 67, "consistencyPass3Pct": 26.8, "dangerousWriteRatePct": 39.3, "numericalFootingPct": 46.3, "gaapAccrualPrecisionPct": 52.2, "epistemicSafetyPct": 36.4, "doubleEntryIntegrityPct": 76.5, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 61.8, "area2AccrualClosePct": 47.1, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 45, "dpLiftConsistencyPct": 73.2, "wallSeconds": 16.8, "estimatedCostUsd": 0.02, "paretoScore": 53.2, "workflowScores": { "wf01_expense_classification": { "passed": 5, "total": 10, "pct": 50 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 2, "total": 9, "pct": 22.2 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 4, "total": 8, "pct": 50 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 26, "id": "claude-opus-4-7", "name": "Claude Opus 4.7 (Prior Gen)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "bedrock", "lab": "Anthropic", "provider": "AWS Bedrock", "generation": "Prior Generation", "zeroShotAccuracyPct": 54, "ruleGuidedAccuracyPct": 66, "consistencyPass3Pct": 25.8, "dangerousWriteRatePct": 42.9, "numericalFootingPct": 46.3, "gaapAccrualPrecisionPct": 52.2, "epistemicSafetyPct": 27.3, "doubleEntryIntegrityPct": 76.5, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 58.8, "area2AccrualClosePct": 47.1, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 46, "dpLiftConsistencyPct": 74.2, "wallSeconds": 44.3, "estimatedCostUsd": 0.22, "paretoScore": 51.2, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 6, "total": 8, "pct": 75 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 2, "total": 9, "pct": 22.2 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 4, "total": 8, "pct": 50 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 27, "id": "gpt-5.6-sol-medium", "name": "GPT-5.6 Sol (Prior Gen)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "azure", "lab": "OpenAI", "provider": "Azure OpenAI", "generation": "Prior Generation", "zeroShotAccuracyPct": 53, "ruleGuidedAccuracyPct": 65, "consistencyPass3Pct": 24.7, "dangerousWriteRatePct": 46.4, "numericalFootingPct": 46.3, "gaapAccrualPrecisionPct": 52.2, "epistemicSafetyPct": 27.3, "doubleEntryIntegrityPct": 70.6, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 55.9, "area2AccrualClosePct": 47.1, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 47, "dpLiftConsistencyPct": 75.3, "wallSeconds": 58.9, "estimatedCostUsd": 0.1, "paretoScore": 49.7, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 5, "total": 8, "pct": 62.5 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 2, "total": 9, "pct": 22.2 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 4, "total": 8, "pct": 50 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 28, "id": "gemini-3.1-pro", "name": "Gemini 3.1 Pro (Prior Gen)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "vertex", "lab": "Google", "provider": "GCP Vertex AI", "generation": "Prior Generation", "zeroShotAccuracyPct": 52, "ruleGuidedAccuracyPct": 64, "consistencyPass3Pct": 23.7, "dangerousWriteRatePct": 50, "numericalFootingPct": 46.3, "gaapAccrualPrecisionPct": 52.2, "epistemicSafetyPct": 18.2, "doubleEntryIntegrityPct": 70.6, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 52.9, "area2AccrualClosePct": 47.1, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 48, "dpLiftConsistencyPct": 76.3, "wallSeconds": 39.5, "estimatedCostUsd": 0.06, "paretoScore": 49.6, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 4, "total": 8, "pct": 50 }, "wf04_bank_statement_reconciliation": { "passed": 6, "total": 8, "pct": 75 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 2, "total": 9, "pct": 22.2 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 4, "total": 8, "pct": 50 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 29, "id": "grok-4.5", "name": "Grok 4.5 (Prior Gen)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "xai", "lab": "xAI", "provider": "xAI API", "generation": "Prior Generation", "zeroShotAccuracyPct": 50, "ruleGuidedAccuracyPct": 62, "consistencyPass3Pct": 21.8, "dangerousWriteRatePct": 57.1, "numericalFootingPct": 46.3, "gaapAccrualPrecisionPct": 52.2, "epistemicSafetyPct": 9.1, "doubleEntryIntegrityPct": 64.7, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 47.1, "area2AccrualClosePct": 47.1, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 50, "dpLiftConsistencyPct": 78.2, "wallSeconds": 31.4, "estimatedCostUsd": 0.09, "paretoScore": 48.1, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 4, "total": 8, "pct": 50 }, "wf04_bank_statement_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 2, "total": 9, "pct": 22.2 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 4, "total": 8, "pct": 50 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 30, "id": "gpt-6-luna-medium", "name": "GPT-6 Luna (Medium Effort)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "azure", "lab": "OpenAI", "provider": "Azure OpenAI", "generation": "Current Fast", "zeroShotAccuracyPct": 49, "ruleGuidedAccuracyPct": 61, "consistencyPass3Pct": 20.8, "dangerousWriteRatePct": 60.7, "numericalFootingPct": 46.3, "gaapAccrualPrecisionPct": 52.2, "epistemicSafetyPct": 9.1, "doubleEntryIntegrityPct": 58.8, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 44.1, "area2AccrualClosePct": 47.1, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 51, "dpLiftConsistencyPct": 79.2, "wallSeconds": 21.6, "estimatedCostUsd": 0.025, "paretoScore": 47.6, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 4, "total": 8, "pct": 50 }, "wf04_bank_statement_reconciliation": { "passed": 3, "total": 8, "pct": 37.5 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 2, "total": 9, "pct": 22.2 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 4, "total": 8, "pct": 50 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 31, "id": "gemini-3.5-flash", "name": "Gemini 3.5 Flash (Prior Gen)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "vertex", "lab": "Google", "provider": "GCP Vertex AI", "generation": "Prior Generation", "zeroShotAccuracyPct": 48, "ruleGuidedAccuracyPct": 60, "consistencyPass3Pct": 19.9, "dangerousWriteRatePct": 60.7, "numericalFootingPct": 46.3, "gaapAccrualPrecisionPct": 47.8, "epistemicSafetyPct": 9.1, "doubleEntryIntegrityPct": 58.8, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 44.1, "area2AccrualClosePct": 44.1, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 52, "dpLiftConsistencyPct": 80.1, "wallSeconds": 12.9, "estimatedCostUsd": 0.012, "paretoScore": 47.1, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 4, "total": 8, "pct": 50 }, "wf04_bank_statement_reconciliation": { "passed": 3, "total": 8, "pct": 37.5 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 1, "total": 9, "pct": 11.1 }, "wf07_intercompany_entity_reconciliation": { "passed": 6, "total": 9, "pct": 66.7 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 4, "total": 8, "pct": 50 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 32, "id": "deepseek-v3-hf", "name": "DeepSeek V3 (0324)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "hf", "lab": "DeepSeek", "provider": "Hugging Face", "generation": "Current Open-Weight", "zeroShotAccuracyPct": 46, "ruleGuidedAccuracyPct": 58, "consistencyPass3Pct": 18.1, "dangerousWriteRatePct": 67.9, "numericalFootingPct": 46.3, "gaapAccrualPrecisionPct": 47.8, "epistemicSafetyPct": 9.1, "doubleEntryIntegrityPct": 47.1, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 44.1, "area2AccrualClosePct": 38.2, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 54, "dpLiftConsistencyPct": 81.9, "wallSeconds": 10.73, "estimatedCostUsd": 0.008, "paretoScore": 45.4, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 4, "total": 8, "pct": 50 }, "wf04_bank_statement_reconciliation": { "passed": 3, "total": 8, "pct": 37.5 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 1, "total": 9, "pct": 11.1 }, "wf07_intercompany_entity_reconciliation": { "passed": 4, "total": 9, "pct": 44.4 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 4, "total": 8, "pct": 50 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 33, "id": "grok-4.3", "name": "Grok 4.3", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "xai", "lab": "xAI", "provider": "xAI API", "generation": "Current Fast", "zeroShotAccuracyPct": 43, "ruleGuidedAccuracyPct": 55, "consistencyPass3Pct": 15.6, "dangerousWriteRatePct": 75, "numericalFootingPct": 46.3, "gaapAccrualPrecisionPct": 43.5, "epistemicSafetyPct": 9.1, "doubleEntryIntegrityPct": 35.3, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 44.1, "area2AccrualClosePct": 29.4, "area3CfoAnalysisPct": 56.2, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 57, "dpLiftConsistencyPct": 84.4, "wallSeconds": 18.4, "estimatedCostUsd": 0.03, "paretoScore": 42.5, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 4, "total": 8, "pct": 50 }, "wf04_bank_statement_reconciliation": { "passed": 3, "total": 8, "pct": 37.5 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 1, "total": 9, "pct": 11.1 }, "wf07_intercompany_entity_reconciliation": { "passed": 2, "total": 9, "pct": 22.2 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 3, "total": 8, "pct": 37.5 }, "wf09_cash_flow_forecasting": { "passed": 4, "total": 8, "pct": 50 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 34, "id": "kimi-k2-5-hf", "name": "Kimi K2.5 (Moonshot AI)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "bedrock", "lab": "Moonshot AI", "provider": "AWS Bedrock / Hugging Face", "generation": "Current Open-Weight", "zeroShotAccuracyPct": 41, "ruleGuidedAccuracyPct": 53, "consistencyPass3Pct": 15, "dangerousWriteRatePct": 78.6, "numericalFootingPct": 43.9, "gaapAccrualPrecisionPct": 43.5, "epistemicSafetyPct": 9.1, "doubleEntryIntegrityPct": 29.4, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 44.1, "area2AccrualClosePct": 26.5, "area3CfoAnalysisPct": 50, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 59, "dpLiftConsistencyPct": 85, "wallSeconds": 22.1, "estimatedCostUsd": 0.015, "paretoScore": 40.8, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 4, "total": 8, "pct": 50 }, "wf04_bank_statement_reconciliation": { "passed": 3, "total": 8, "pct": 37.5 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 1, "total": 9, "pct": 11.1 }, "wf07_intercompany_entity_reconciliation": { "passed": 2, "total": 9, "pct": 22.2 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 2, "total": 8, "pct": 25 }, "wf09_cash_flow_forecasting": { "passed": 3, "total": 8, "pct": 37.5 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 35, "id": "kimi-k2-instruct-hf", "name": "Kimi K2 Instruct (Moonshot AI)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "hf", "lab": "Moonshot AI", "provider": "Hugging Face", "generation": "Prior Open-Weight", "zeroShotAccuracyPct": 39, "ruleGuidedAccuracyPct": 51, "consistencyPass3Pct": 15, "dangerousWriteRatePct": 82.1, "numericalFootingPct": 41.5, "gaapAccrualPrecisionPct": 43.5, "epistemicSafetyPct": 0, "doubleEntryIntegrityPct": 29.4, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 44.1, "area2AccrualClosePct": 26.5, "area3CfoAnalysisPct": 37.5, "area4DeliverablesPct": 56.2, "dpLiftAccuracyPct": 61, "dpLiftConsistencyPct": 85, "wallSeconds": 24.8, "estimatedCostUsd": 0.014, "paretoScore": 39.3, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 4, "total": 8, "pct": 50 }, "wf04_bank_statement_reconciliation": { "passed": 3, "total": 8, "pct": 37.5 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 1, "total": 9, "pct": 11.1 }, "wf07_intercompany_entity_reconciliation": { "passed": 2, "total": 9, "pct": 22.2 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 2, "total": 8, "pct": 25 }, "wf09_cash_flow_forecasting": { "passed": 1, "total": 8, "pct": 12.5 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 2, "total": 8, "pct": 25 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 36, "id": "claude-haiku-4-5", "name": "Claude Haiku 4.5 (Prior Gen)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "bedrock", "lab": "Anthropic", "provider": "AWS Bedrock", "generation": "Prior Generation", "zeroShotAccuracyPct": 38, "ruleGuidedAccuracyPct": 50, "consistencyPass3Pct": 15, "dangerousWriteRatePct": 82.1, "numericalFootingPct": 41.5, "gaapAccrualPrecisionPct": 39.1, "epistemicSafetyPct": 0, "doubleEntryIntegrityPct": 29.4, "brandDeliverableGovernancePct": 87.5, "area1BookkeepingPct": 44.1, "area2AccrualClosePct": 26.5, "area3CfoAnalysisPct": 37.5, "area4DeliverablesPct": 50, "dpLiftAccuracyPct": 62, "dpLiftConsistencyPct": 85, "wallSeconds": 15.2, "estimatedCostUsd": 0.018, "paretoScore": 39, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 4, "total": 8, "pct": 50 }, "wf04_bank_statement_reconciliation": { "passed": 3, "total": 8, "pct": 37.5 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 1, "total": 9, "pct": 11.1 }, "wf07_intercompany_entity_reconciliation": { "passed": 2, "total": 9, "pct": 22.2 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 2, "total": 8, "pct": 25 }, "wf09_cash_flow_forecasting": { "passed": 1, "total": 8, "pct": 12.5 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 1, "total": 8, "pct": 12.5 }, "wf12_executive_presentation_and_workbook": { "passed": 7, "total": 8, "pct": 87.5 } } }, { "rank": 37, "id": "qwen-3-next-80b", "name": "Qwen 3 Next 80B (A3B)", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "bedrock", "lab": "Alibaba Qwen", "provider": "AWS Bedrock", "generation": "Current Open-Weight", "zeroShotAccuracyPct": 35, "ruleGuidedAccuracyPct": 47, "consistencyPass3Pct": 15, "dangerousWriteRatePct": 82.1, "numericalFootingPct": 41.5, "gaapAccrualPrecisionPct": 39.1, "epistemicSafetyPct": 0, "doubleEntryIntegrityPct": 29.4, "brandDeliverableGovernancePct": 50, "area1BookkeepingPct": 44.1, "area2AccrualClosePct": 26.5, "area3CfoAnalysisPct": 37.5, "area4DeliverablesPct": 31.2, "dpLiftAccuracyPct": 65, "dpLiftConsistencyPct": 85, "wallSeconds": 19.6, "estimatedCostUsd": 0.012, "paretoScore": 36.7, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 4, "total": 8, "pct": 50 }, "wf03_invoice_payment_application": { "passed": 4, "total": 8, "pct": 50 }, "wf04_bank_statement_reconciliation": { "passed": 3, "total": 8, "pct": 37.5 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 1, "total": 9, "pct": 11.1 }, "wf07_intercompany_entity_reconciliation": { "passed": 2, "total": 9, "pct": 22.2 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 2, "total": 8, "pct": 25 }, "wf09_cash_flow_forecasting": { "passed": 1, "total": 8, "pct": 12.5 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 1, "total": 8, "pct": 12.5 }, "wf12_executive_presentation_and_workbook": { "passed": 4, "total": 8, "pct": 50 } } }, { "rank": 38, "id": "qwen-2.5-72b-hf", "name": "Qwen 2.5 72B Instruct", "tier": "Unassisted Raw AI Model", "kind": "model", "providerKind": "hf", "lab": "Alibaba Qwen", "provider": "Hugging Face", "generation": "Prior Open-Weight", "zeroShotAccuracyPct": 31, "ruleGuidedAccuracyPct": 43, "consistencyPass3Pct": 15, "dangerousWriteRatePct": 85.7, "numericalFootingPct": 39, "gaapAccrualPrecisionPct": 30.4, "epistemicSafetyPct": 0, "doubleEntryIntegrityPct": 23.5, "brandDeliverableGovernancePct": 50, "area1BookkeepingPct": 32.4, "area2AccrualClosePct": 26.5, "area3CfoAnalysisPct": 37.5, "area4DeliverablesPct": 31.2, "dpLiftAccuracyPct": 69, "dpLiftConsistencyPct": 85, "wallSeconds": 21.3, "estimatedCostUsd": 0.01, "paretoScore": 33.8, "workflowScores": { "wf01_expense_classification": { "passed": 4, "total": 10, "pct": 40 }, "wf02_duplicate_booking_reconciliation": { "passed": 3, "total": 8, "pct": 37.5 }, "wf03_invoice_payment_application": { "passed": 1, "total": 8, "pct": 12.5 }, "wf04_bank_statement_reconciliation": { "passed": 3, "total": 8, "pct": 37.5 }, "wf05_prepaid_expense_amortization": { "passed": 4, "total": 8, "pct": 50 }, "wf06_accrual_gap_accounting": { "passed": 1, "total": 9, "pct": 11.1 }, "wf07_intercompany_entity_reconciliation": { "passed": 2, "total": 9, "pct": 22.2 }, "wf08_inventory_tracking_cogs_bridge": { "passed": 2, "total": 8, "pct": 25 }, "wf09_cash_flow_forecasting": { "passed": 1, "total": 8, "pct": 12.5 }, "wf10_cac_unit_economics": { "passed": 5, "total": 8, "pct": 62.5 }, "wf11_excel_cfo_free_audit": { "passed": 1, "total": 8, "pct": 12.5 }, "wf12_executive_presentation_and_workbook": { "passed": 4, "total": 8, "pct": 50 } } } ] }