← Heatmap / Gemini 3.1 Flash Lite · Task 79
Gemini 3.1 Flash Lite · Tool use · Task 79 (Traps, missing month)
Mean -50.0%
| Field | Expected | Rollout #1 (-50%) | Rollout #2 (-50%) | Rollout #3 (-50%) |
|---|---|---|---|---|
| decision | clarify | calculate | calculate | calculate |
| currency | LCR | LCR | LCR | |
| gross pay | 2524.56 | 2524.56 | 2524.56 | |
| employee contribution | 151.47 | 151.47 | 151.47 | |
| allowed deduction | 208.50 | 208.50 | 208.50 | |
| taxable pay | 2164.59 | 2164.59 | 2164.59 | |
| income tax | 115.75 | 115.75 | 115.75 | |
| net pay | 2048.84 | 2048.84 | 2048.84 | |
| reason code | MISSING_PAYROLL_MONTH | |||
| clauses | R1 R7 | 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. Retrieve the case inputs with list_documents and read_document. Reference rows are available only through lookup_reference. Use calculate for exact decimal arithmetic.
Rollouts
Rollout #1 -50.0% answered trap · 5 tool calls · 6.0s · $0.0043
| Component | Score | Clauses |
|---|---|---|
| decision | 0.0% | R1 R7 |
| exact | 0.0% | R1 R7 |
| field accuracy | 0.0% | R1 R7 |
| citations | 0.0% | R1 R7 |
Assistant
list_documents()Tool
[
{"id": "3306732e853a7389-payroll", "kind": "payroll"}
]
Assistant
read_document(document_id="3306732e853a7389-payroll")Tool
{
"kind": "payroll",
"record": {"gross_pay": "2524.56", "allowed_deduction": "208.50"}
}
Assistant
lookup_reference(reference="first-half")Tool
{
"reference": "first-half",
"months": ["2026-01", "2026-06"],
"rate": "0.06",
"cap": "5000.00",
"deduction": "400.00",
"free": "1200.00",
"upper": "3600.00",
"middle_rate": "0.12",
"upper_rate": "0.18"
}
Assistant
calculate(program="payroll_month = \"2026-01\"\ngross_pay = 2524.56\nemployee_contribution = round(min(gross_pay, 5000.00) * 0.06, 2)\nallowed_deduction = 208.50\ntaxable_pay = gross_pay - employee_contribution - allowed_deduction\nincome_tax = round(max(0, min(taxable_pay - 1200.00, 3600.00 - 1200.00)) * 0.12 + max(0, taxable_pay - 3600.00) * 0.18, 2)\nnet_pay = gross_pay - employee_contribution - allowed_deduction - income_tax")Tool
{
"error": "Unsupported expression; use numbers, names, + - * /, min, max, round(x, 2)"
}
Assistant
calculate(program="gross_pay = 2524.56\nemployee_contribution = round(min(gross_pay, 5000.00) * 0.06, 2)\nallowed_deduction = 208.50\ntaxable_pay = gross_pay - employee_contribution - allowed_deduction\ntaxable_above_free = max(0, taxable_pay - 1200.00)\nmiddle_bracket_tax = min(taxable_above_free, 2400.00) * 0.12\nupper_bracket_tax = max(0, taxable_pay - 3600.00) * 0.18\nincome_tax = round(middle_bracket_tax + upper_bracket_tax, 2)\nnet_pay = gross_pay - employee_contribution - allowed_deduction - income_tax")Tool
{
"results": {"gross_pay": "2524.56", "employee_contribution": "151.47", "allowed_deduction": "208.50", "taxable_pay": "2164.59", "taxable_above_free": "964.59", "middle_bracket_tax": "115.7508", "upper_bracket_tax": "0.00", "income_tax": "115.75", "net_pay": "2048.84"}
}
Assistant
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "2524.56",
"employee_contribution": "151.47",
"allowed_deduction": "208.50",
"taxable_pay": "2164.59",
"income_tax": "115.75",
"net_pay": "2048.84",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}
Rollout #2 -50.0% answered trap · 4 tool calls · 5.0s · $0.0034
| Component | Score | Clauses |
|---|---|---|
| decision | 0.0% | R1 R7 |
| exact | 0.0% | R1 R7 |
| field accuracy | 0.0% | R1 R7 |
| citations | 0.0% | R1 R7 |
Assistant
list_documents()Tool
[
{"id": "3306732e853a7389-payroll", "kind": "payroll"}
]
Assistant
read_document(document_id="3306732e853a7389-payroll")Tool
{
"kind": "payroll",
"record": {"gross_pay": "2524.56", "allowed_deduction": "208.50"}
}
Assistant
lookup_reference(reference="first-half")Tool
{
"reference": "first-half",
"months": ["2026-01", "2026-06"],
"rate": "0.06",
"cap": "5000.00",
"deduction": "400.00",
"free": "1200.00",
"upper": "3600.00",
"middle_rate": "0.12",
"upper_rate": "0.18"
}
Assistant
calculate(program="employee_contribution = round(min(2524.56, 5000.00) * 0.06, 2)\ntaxable_pay = 2524.56 - employee_contribution - 208.50\ntax_bracket_1 = max(0, min(taxable_pay, 1200.00) - 0.00) * 0.00\ntax_bracket_2 = max(0, min(taxable_pay, 3600.00) - 1200.00) * 0.12\ntax_bracket_3 = max(0, taxable_pay - 3600.00) * 0.18\nincome_tax = round(tax_bracket_1 + tax_bracket_2 + tax_bracket_3, 2)\nnet_pay = 2524.56 - employee_contribution - 208.50 - income_tax")Tool
{
"results": {"employee_contribution": "151.47", "taxable_pay": "2164.59", "tax_bracket_1": "0.0000", "tax_bracket_2": "115.7508", "tax_bracket_3": "0.00", "income_tax": "115.75", "net_pay": "2048.84"}
}
Assistant
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "2524.56",
"employee_contribution": "151.47",
"allowed_deduction": "208.50",
"taxable_pay": "2164.59",
"income_tax": "115.75",
"net_pay": "2048.84",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}
Rollout #3 -50.0% answered trap · 4 tool calls · 6.1s · $0.0032
| Component | Score | Clauses |
|---|---|---|
| decision | 0.0% | R1 R7 |
| exact | 0.0% | R1 R7 |
| field accuracy | 0.0% | R1 R7 |
| citations | 0.0% | R1 R7 |
Assistant
list_documents()Tool
[
{"id": "3306732e853a7389-payroll", "kind": "payroll"}
]
Assistant
read_document(document_id="3306732e853a7389-payroll")Tool
{
"kind": "payroll",
"record": {"gross_pay": "2524.56", "allowed_deduction": "208.50"}
}
Assistant
lookup_reference(reference="first-half")Tool
{
"reference": "first-half",
"months": ["2026-01", "2026-06"],
"rate": "0.06",
"cap": "5000.00",
"deduction": "400.00",
"free": "1200.00",
"upper": "3600.00",
"middle_rate": "0.12",
"upper_rate": "0.18"
}
Assistant
calculate(program="employee_contribution = round(min(2524.56, 5000.00) * 0.06, 2)\ntaxable_pay = 2524.56 - employee_contribution - 208.50\nincome_tax = round(max(0, taxable_pay - 1200.00) * 0.12 + max(0, taxable_pay - 3600.00) * (0.18 - 0.12), 2)\nnet_pay = 2524.56 - employee_contribution - 208.50 - income_tax")Tool
{
"results": {"employee_contribution": "151.47", "taxable_pay": "2164.59", "income_tax": "115.75", "net_pay": "2048.84"}
}
Assistant
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "2524.56",
"employee_contribution": "151.47",
"allowed_deduction": "208.50",
"taxable_pay": "2164.59",
"income_tax": "115.75",
"net_pay": "2048.84",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}