← Heatmap / Gemini 3.1 Flash Lite · Task 7
Gemini 3.1 Flash Lite · Single-turn · Task 7 (Calculation, wage cap binds)
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 | 8370.45 | 8370.45 | 8370.45 | 8370.45 |
| employee contribution | 200.00 | 200.00 | 200.00 | 200.00 |
| allowed deduction | 370.62 | 370.62 | 370.62 | 370.62 |
| taxable pay | 7799.83 | 7799.83 | 7799.83 | 7799.83 |
| income tax | 1267.96 | 1259.96 | 1235.96 | 1235.96 |
| net pay | 6531.87 | 6539.87 | 6563.87 | 6563.87 |
| clauses | R1 R2 R3 R4 R5 R6 | R1 R2 R3 R4 R5 R6 | R1 R2 R3 R4 R5 R6 | R1 R2 R3 R4 R5 R6 |
Prompt
Process this monthly payroll record under the supplied rulebook. Return the R6 or R7 JSON answer.
Source documents: {"9869ba945ef7380b-payroll": {"kind": "payroll", "record": {"gross_pay": "8370.45", "payroll_month": "2026-05", "allowed_deduction": "370.62"}}}
Authoritative case reference schedule: {"first-half": {"rate": "0.04", "cap": "5000.00", "deduction": "400.00", "free": "1000.00", "upper": "3600.00", "middle_rate": "0.10", "upper_rate": "0.24"}, "second-half": {"rate": "0.04", "cap": "4000.00", "deduction": "400.00", "free": "1000.00", "upper": "3600.00", "middle_rate": "0.12", "upper_rate": "0.22"}}
Rollouts
Rollout #1 -40.0% wrong income tax · 1.5s · $0.0009
| Component | Score | Clauses |
|---|---|---|
| decision | 100.0% | R1 R2 R3 R4 R5 R6 |
| exact | 0.0% | R1 R2 R3 R4 R5 R6 |
| field accuracy | 50.0% | R1 R2 R3 R4 R5 R6 |
| citations | 100.0% | R1 R2 R3 R4 R5 R6 |
Assistant
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "8370.45",
"employee_contribution": "200.00",
"allowed_deduction": "370.62",
"taxable_pay": "7799.83",
"income_tax": "1259.96",
"net_pay": "6539.87",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"],
"explanation": "Calculated using the first-half schedule (rate 0.04, cap 5000.00, deduction cap 400.00, tax-free 1000.00, upper 3600.00, middle_rate 0.10, upper_rate 0.24)."
}
Rollout #2 -40.0% wrong income tax · 1.5s · $0.0010
| Component | Score | Clauses |
|---|---|---|
| decision | 100.0% | R1 R2 R3 R4 R5 R6 |
| exact | 0.0% | R1 R2 R3 R4 R5 R6 |
| field accuracy | 50.0% | R1 R2 R3 R4 R5 R6 |
| citations | 100.0% | R1 R2 R3 R4 R5 R6 |
Assistant
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "8370.45",
"employee_contribution": "200.00",
"allowed_deduction": "370.62",
"taxable_pay": "7799.83",
"income_tax": "1235.96",
"net_pay": "6563.87",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"],
"explanation": "Calculated using the first-half schedule provided in the case reference. Employee contribution: 5000.00 * 0.04 = 200.00. Taxable pay: 8370.45 - 200.00 - 370.62 = 7799.83. Income tax: (3600.00 - 1000.00) * 0.10 + (7799.83 - 3600.00) * 0.24 = 260.00 + 1007.96 = 1235.96."
}
Rollout #3 -40.0% wrong income tax · 2.0s · $0.0008
| Component | Score | Clauses |
|---|---|---|
| decision | 100.0% | R1 R2 R3 R4 R5 R6 |
| exact | 0.0% | R1 R2 R3 R4 R5 R6 |
| field accuracy | 50.0% | R1 R2 R3 R4 R5 R6 |
| citations | 100.0% | R1 R2 R3 R4 R5 R6 |
Assistant
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "8370.45",
"employee_contribution": "200.00",
"allowed_deduction": "370.62",
"taxable_pay": "7799.83",
"income_tax": "1235.96",
"net_pay": "6563.87",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}