← Heatmap / Gemini 3.1 Flash Lite · Task 15
Gemini 3.1 Flash Lite · Single-turn · Task 15 (Calculation, half-cent rounding tie)
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 | 3872.25 | 3872.25 | 3872.25 | 3872.25 |
| employee contribution | 232.34 | 232.34 | 232.34 | 232.34 |
| allowed deduction | 61.98 | 61.98 | 61.98 | 61.98 |
| taxable pay | 3577.93 | 3577.93 | 3577.93 | 3577.93 |
| income tax | 388.70 | 439.70 | 446.70 | 449.70 |
| net pay | 3189.23 | 3138.23 | 3131.23 | 3128.23 |
| 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: {"35d44967e5524da6-payroll": {"kind": "payroll", "record": {"gross_pay": "3872.25", "payroll_month": "2026-04", "allowed_deduction": "61.98"}}}
Authoritative case reference schedule: {"first-half": {"rate": "0.06", "cap": "4000.00", "deduction": "400.00", "free": "1000.00", "upper": "3300.00", "middle_rate": "0.14", "upper_rate": "0.24"}, "second-half": {"rate": "0.08", "cap": "4000.00", "deduction": "400.00", "free": "1100.00", "upper": "2800.00", "middle_rate": "0.14", "upper_rate": "0.18"}}
Rollouts
Rollout #1 -40.0% wrong income tax · 1.0s · $0.0007
| 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": "3872.25",
"employee_contribution": "232.34",
"allowed_deduction": "61.98",
"taxable_pay": "3577.93",
"income_tax": "439.70",
"net_pay": "3138.23",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}
Rollout #2 -40.0% wrong income tax · 1.3s · $0.0007
| 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": "3872.25",
"employee_contribution": "232.34",
"allowed_deduction": "61.98",
"taxable_pay": "3577.93",
"income_tax": "446.70",
"net_pay": "3131.23",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}
Rollout #3 -40.0% wrong income tax · 1.1s · $0.0007
| 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": "3872.25",
"employee_contribution": "232.34",
"allowed_deduction": "61.98",
"taxable_pay": "3577.93",
"income_tax": "449.70",
"net_pay": "3128.23",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}