← Heatmap / Gemini 3.1 Flash Lite · Task 71
Gemini 3.1 Flash Lite · Single-turn · Task 71 (Calculation, upper bracket)
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 | 3693.66 | 3693.66 | 3693.66 | 3693.66 |
| employee contribution | 221.62 | 221.62 | 221.62 | 221.62 |
| allowed deduction | 317.42 | 317.42 | 317.42 | 317.42 |
| taxable pay | 3154.62 | 3154.62 | 3154.62 | 3154.62 |
| income tax | 194.02 | 349.02 | 349.02 | 349.02 |
| net pay | 2960.60 | 2805.60 | 2805.60 | 2805.60 |
| 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: {"58270f5a8f66aa95-payroll": {"kind": "payroll", "record": {"gross_pay": "3693.66", "payroll_month": "2026-08", "allowed_deduction": "317.42"}}, "58270f5a8f66aa95-contract": {"kind": "contract", "gross_pay": "3693.66"}}
Authoritative case reference schedule: {"first-half": {"rate": "0.07", "cap": "3500.00", "deduction": "400.00", "free": "1000.00", "upper": "3600.00", "middle_rate": "0.12", "upper_rate": "0.22"}, "second-half": {"rate": "0.06", "cap": "4000.00", "deduction": "400.00", "free": "1000.00", "upper": "3000.00", "middle_rate": "0.08", "upper_rate": "0.22"}}
Rollouts
Rollout #1 -40.0% wrong income tax · 1.0s · $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": "3693.66",
"employee_contribution": "221.62",
"allowed_deduction": "317.42",
"taxable_pay": "3154.62",
"income_tax": "349.02",
"net_pay": "2805.60",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}
Rollout #2 -40.0% wrong income tax · 1.1s · $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": "3693.66",
"employee_contribution": "221.62",
"allowed_deduction": "317.42",
"taxable_pay": "3154.62",
"income_tax": "349.02",
"net_pay": "2805.60",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"],
"explanation": "Calculated using the second-half reference schedule: contribution rate 0.06, wage cap 4000.00, deduction cap 400.00, tax-free 1000.00, upper boundary 3000.00, middle rate 0.08, upper rate 0.22."
}
Rollout #3 -40.0% wrong income tax · 1.5s · $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": "3693.66",
"employee_contribution": "221.62",
"allowed_deduction": "317.42",
"taxable_pay": "3154.62",
"income_tax": "349.02",
"net_pay": "2805.60",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}