Luma Payroll Gym
← Heatmap / Gemini 3.1 Flash Lite · Task 104
Gemini 3.1 Flash Lite · Single-turn · Task 104 (Calculation, wage cap binds, resolved amendment) Mean -40.0%
Field Expected Rollout #1 (-40%) Rollout #2 (-40%) Rollout #3 (-40%)
decision calculate calculate calculate calculate
currency LCR LCR LCR LCR
gross pay 5662.30 5662.30 5662.30 5662.30
employee contribution 180.00 180.00 180.00 180.00
allowed deduction 169.02 169.02 169.02 169.02
taxable pay 5313.28 5313.28 5313.28 5313.28
income tax 748.92 764.92 761.92 761.92
net pay 4564.36 4548.36 4551.36 4551.36
clauses R1 R2 R3 R4 R5 R6 R9 R1 R2 R3 R4 R5 R6 R9 R1 R2 R3 R4 R5 R6 R9 R1 R2 R3 R4 R5 R6 R9
Prompt
Process this monthly payroll record under the supplied rulebook. Return the R6 or R7 JSON answer.
Source documents: {"1fb17c8b15731951-payroll": {"kind": "payroll", "record": {"gross_pay": "5662.30", "payroll_month": "2026-09", "allowed_deduction": "169.02"}}, "1fb17c8b15731951-contract": {"kind": "contract", "gross_pay": "6025.51"}, "1fb17c8b15731951-amendment": {"kind": "amendment", "gross_pay": "5662.30", "approved": true, "effective_month": "2026-03"}}
Authoritative case reference schedule: {"first-half": {"rate": "0.07", "cap": "3500.00", "deduction": "400.00", "free": "1100.00", "upper": "2800.00", "middle_rate": "0.14", "upper_rate": "0.20"}, "second-half": {"rate": "0.04", "cap": "4500.00", "deduction": "400.00", "free": "1000.00", "upper": "3000.00", "middle_rate": "0.12", "upper_rate": "0.22"}}
Rollouts
Rollout #1 -40.0% wrong income tax · 1.1s · $0.0008
ComponentScoreClauses
decision 100.0% R1 R2 R3 R4 R5 R6 R9
exact 0.0% R1 R2 R3 R4 R5 R6 R9
field accuracy 50.0% R1 R2 R3 R4 R5 R6 R9
citations 100.0% R1 R2 R3 R4 R5 R6 R9
Assistant
{
  "decision": "calculate",
  "currency": "LCR",
  "gross_pay": "5662.30",
  "employee_contribution": "180.00",
  "allowed_deduction": "169.02",
  "taxable_pay": "5313.28",
  "income_tax": "764.92",
  "net_pay": "4548.36",
  "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R9"],
  "explanation": "The contract conflict was resolved by the approved amendment under R9."
}
Rollout #2 -40.0% wrong income tax · 1.5s · $0.0008
ComponentScoreClauses
decision 100.0% R1 R2 R3 R4 R5 R6 R9
exact 0.0% R1 R2 R3 R4 R5 R6 R9
field accuracy 50.0% R1 R2 R3 R4 R5 R6 R9
citations 100.0% R1 R2 R3 R4 R5 R6 R9
Assistant
{
  "decision": "calculate",
  "currency": "LCR",
  "gross_pay": "5662.30",
  "employee_contribution": "180.00",
  "allowed_deduction": "169.02",
  "taxable_pay": "5313.28",
  "income_tax": "761.92",
  "net_pay": "4551.36",
  "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R9"],
  "explanation": "The contract conflict was resolved by the approved amendment under R9."
}
Rollout #3 -40.0% wrong income tax · 1.5s · $0.0010
ComponentScoreClauses
decision 100.0% R1 R2 R3 R4 R5 R6 R9
exact 0.0% R1 R2 R3 R4 R5 R6 R9
field accuracy 50.0% R1 R2 R3 R4 R5 R6 R9
citations 100.0% R1 R2 R3 R4 R5 R6 R9
Assistant
{
  "decision": "calculate",
  "currency": "LCR",
  "gross_pay": "5662.30",
  "employee_contribution": "180.00",
  "allowed_deduction": "169.02",
  "taxable_pay": "5313.28",
  "income_tax": "761.92",
  "net_pay": "4551.36",
  "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R9"],
  "explanation": "The contract conflict was resolved by the approved amendment under R9. Income tax calculated using second-half schedule: (3000.00 - 1000.00) * 0.12 + (5313.28 - 3000.00) * 0.22 = 240.00 + 508.9216 = 748.9216, rounded to 748.92."
}