← Heatmap / Gemini 3.1 Flash Lite · Task 63
Gemini 3.1 Flash Lite · Single-turn · Task 63 (Calculation, at the upper bracket line)
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 | 4093.39 | 4093.39 | 4093.39 | 4093.39 |
| employee contribution | 245.60 | 245.60 | 245.60 | 245.60 |
| allowed deduction | 247.81 | 247.81 | 247.81 | 247.81 |
| taxable pay | 3599.98 | 3599.98 | 3599.98 | 3599.98 |
| income tax | 324.00 | 455.99 | 383.99 | 456.00 |
| net pay | 3275.98 | 3143.99 | 3215.99 | 3143.98 |
| 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: {"c9a494472e6b6cd2-payroll": {"kind": "payroll", "record": {"gross_pay": "4093.39", "payroll_month": "2026-06", "allowed_deduction": "247.81"}}}
Authoritative case reference schedule: {"first-half": {"rate": "0.06", "cap": "5000.00", "deduction": "400.00", "free": "900.00", "upper": "3600.00", "middle_rate": "0.12", "upper_rate": "0.24"}, "second-half": {"rate": "0.05", "cap": "4000.00", "deduction": "400.00", "free": "1100.00", "upper": "3300.00", "middle_rate": "0.10", "upper_rate": "0.24"}}
Rollouts
Rollout #1 -40.0% wrong income tax · 1.3s · $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": "4093.39",
"employee_contribution": "245.60",
"allowed_deduction": "247.81",
"taxable_pay": "3599.98",
"income_tax": "455.99",
"net_pay": "3143.99",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}
Rollout #2 -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": "4093.39",
"employee_contribution": "245.60",
"allowed_deduction": "247.81",
"taxable_pay": "3599.98",
"income_tax": "383.99",
"net_pay": "3215.99",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}
Rollout #3 -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": "4093.39",
"employee_contribution": "245.60",
"allowed_deduction": "247.81",
"taxable_pay": "3599.98",
"income_tax": "456.00",
"net_pay": "3143.98",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}