← Heatmap / Gemini 3.1 Flash Lite · Task 23
Gemini 3.1 Flash Lite · Single-turn · Task 23 (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 | 7913.09 | 7913.09 | 7913.09 | 7913.09 |
| employee contribution | 200.00 | 200.00 | 200.00 | 200.00 |
| allowed deduction | 63.29 | 63.29 | 63.29 | 63.29 |
| taxable pay | 7649.80 | 7649.80 | 7649.80 | 7649.80 |
| income tax | 1246.96 | 1278.96 | 1284.96 | 1284.96 |
| net pay | 6402.84 | 6370.84 | 6364.84 | 6364.84 |
| 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: {"a605acd47aaaa8d4-payroll": {"kind": "payroll", "record": {"gross_pay": "7913.09", "payroll_month": "2026-01", "allowed_deduction": "63.29"}}, "a605acd47aaaa8d4-contract": {"kind": "contract", "gross_pay": "7913.09"}}
Authoritative case reference schedule: {"first-half": {"rate": "0.05", "cap": "4000.00", "deduction": "400.00", "free": "1000.00", "upper": "2800.00", "middle_rate": "0.10", "upper_rate": "0.22"}, "second-half": {"rate": "0.04", "cap": "3500.00", "deduction": "400.00", "free": "1200.00", "upper": "3300.00", "middle_rate": "0.12", "upper_rate": "0.18"}}
Rollouts
Rollout #1 -40.0% wrong income tax · 1.5s · $0.0011
| 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": "7913.09",
"employee_contribution": "200.00",
"allowed_deduction": "63.29",
"taxable_pay": "7649.80",
"income_tax": "1278.96",
"net_pay": "6370.84",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"],
"explanation": "Calculated using the authoritative case schedule for first-half 2026. Employee contribution: 0.05 * 4000.00 = 200.00. Taxable pay: 7913.09 - 200.00 - 63.29 = 7649.80. Income tax: (2800.00 - 1000.00) * 0.10 + (7649.80 - 2800.00) * 0.22 = 180.00 + 1066.956 = 1246.956, rounded to 1246.96. Net pay: 7913.09 - 200.00 - 63.29 - 1246.96 = 6370.84."
}
Rollout #2 -40.0% wrong income tax · 1.5s · $0.0011
| 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": "7913.09",
"employee_contribution": "200.00",
"allowed_deduction": "63.29",
"taxable_pay": "7649.80",
"income_tax": "1284.96",
"net_pay": "6364.84",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"],
"explanation": "Calculated using the authoritative case schedule for first-half 2026. Employee contribution: 0.05 * 4000.00 = 200.00. Taxable pay: 7913.09 - 200.00 - 63.29 = 7649.80. Income tax: (2800.00 - 1000.00) * 0.10 + (7649.80 - 2800.00) * 0.22 = 180.00 + 1066.956 = 1246.96 (rounded). Net pay: 7913.09 - 200.00 - 63.29 - 1284.96 = 6364.84."
}
Rollout #3 -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": "7913.09",
"employee_contribution": "200.00",
"allowed_deduction": "63.29",
"taxable_pay": "7649.80",
"income_tax": "1284.96",
"net_pay": "6364.84",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"],
"explanation": "Calculated using the authoritative case schedule for 2026-01 (first-half): contribution is 5% of 4000.00; taxable pay is 7913.09 - 200.00 - 63.29; income tax is (2800.00 - 1000.00) * 0.10 + (7649.80 - 2800.00) * 0.22 = 180.00 + 1104.96 = 1284.96."
}