← Heatmap / Gemini 3.1 Flash Lite · Task 57
Gemini 3.1 Flash Lite · Tool use · Task 57 (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 | 3362.67 | 3362.67 | 3362.67 | |
| employee contribution | 269.01 | 269.01 | 269.01 | |
| allowed deduction | 72.10 | 72.10 | 72.10 | |
| taxable pay | 3021.56 | 3021.56 | 3021.56 | |
| income tax | 242.59 | 242.59 | 242.59 | |
| net pay | 2778.97 | 2778.97 | 2778.97 | |
| 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 · 4 tool calls · 5.6s · $0.0033
| 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": "1da1cc4780ca4865-payroll", "kind": "payroll"}
]
Assistant
read_document(document_id="1da1cc4780ca4865-payroll")Tool
{
"kind": "payroll",
"record": {"gross_pay": "3362.67", "allowed_deduction": "72.10"}
}
Assistant
lookup_reference(reference="first-half")Tool
{
"reference": "first-half",
"months": ["2026-01", "2026-06"],
"rate": "0.08",
"cap": "5000.00",
"deduction": "400.00",
"free": "1000.00",
"upper": "3300.00",
"middle_rate": "0.12",
"upper_rate": "0.22"
}
Assistant
calculate(program="employee_contribution = round(min(3362.67, 5000.00) * 0.08, 2)\ntaxable_pay = 3362.67 - employee_contribution - 72.10\ntax_part1 = max(0, min(taxable_pay, 1000.00) - 0.00) * 0.00\ntax_part2 = max(0, min(taxable_pay, 3300.00) - 1000.00) * 0.12\ntax_part3 = max(0, taxable_pay - 3300.00) * 0.22\nincome_tax = round(tax_part1 + tax_part2 + tax_part3, 2)\nnet_pay = 3362.67 - employee_contribution - 72.10 - income_tax")Tool
{
"results": {"employee_contribution": "269.01", "taxable_pay": "3021.56", "tax_part1": "0.0000", "tax_part2": "242.5872", "tax_part3": "0.00", "income_tax": "242.59", "net_pay": "2778.97"}
}
Assistant
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "3362.67",
"employee_contribution": "269.01",
"allowed_deduction": "72.10",
"taxable_pay": "3021.56",
"income_tax": "242.59",
"net_pay": "2778.97",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}
Rollout #2 -50.0% answered trap · 4 tool calls · 5.0s · $0.0033
| 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": "1da1cc4780ca4865-payroll", "kind": "payroll"}
]
Assistant
read_document(document_id="1da1cc4780ca4865-payroll")Tool
{
"kind": "payroll",
"record": {"gross_pay": "3362.67", "allowed_deduction": "72.10"}
}
Assistant
lookup_reference(reference="first-half")Tool
{
"reference": "first-half",
"months": ["2026-01", "2026-06"],
"rate": "0.08",
"cap": "5000.00",
"deduction": "400.00",
"free": "1000.00",
"upper": "3300.00",
"middle_rate": "0.12",
"upper_rate": "0.22"
}
Assistant
calculate(program="employee_contribution = round(min(3362.67, 5000.00) * 0.08, 2)\ntaxable_pay = 3362.67 - employee_contribution - 72.10\ntax_part1 = max(0, min(taxable_pay, 1000.00) - 0.00) * 0.00\ntax_part2 = max(0, min(taxable_pay, 3300.00) - 1000.00) * 0.12\ntax_part3 = max(0, taxable_pay - 3300.00) * 0.22\nincome_tax = round(tax_part1 + tax_part2 + tax_part3, 2)\nnet_pay = 3362.67 - employee_contribution - 72.10 - income_tax")Tool
{
"results": {"employee_contribution": "269.01", "taxable_pay": "3021.56", "tax_part1": "0.0000", "tax_part2": "242.5872", "tax_part3": "0.00", "income_tax": "242.59", "net_pay": "2778.97"}
}
Assistant
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "3362.67",
"employee_contribution": "269.01",
"allowed_deduction": "72.10",
"taxable_pay": "3021.56",
"income_tax": "242.59",
"net_pay": "2778.97",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}
Rollout #3 -50.0% answered trap · 4 tool calls · 4.4s · $0.0033
| 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": "1da1cc4780ca4865-payroll", "kind": "payroll"}
]
Assistant
read_document(document_id="1da1cc4780ca4865-payroll")Tool
{
"kind": "payroll",
"record": {"gross_pay": "3362.67", "allowed_deduction": "72.10"}
}
Assistant
lookup_reference(reference="first-half")Tool
{
"reference": "first-half",
"months": ["2026-01", "2026-06"],
"rate": "0.08",
"cap": "5000.00",
"deduction": "400.00",
"free": "1000.00",
"upper": "3300.00",
"middle_rate": "0.12",
"upper_rate": "0.22"
}
Assistant
calculate(program="employee_contribution = round(min(3362.67, 5000.00) * 0.08, 2)\ntaxable_pay = 3362.67 - employee_contribution - 72.10\ntax_bracket1 = min(max(taxable_pay - 1000.00, 0), 3300.00 - 1000.00)\ntax_bracket2 = max(taxable_pay - 3300.00, 0)\nincome_tax = round(tax_bracket1 * 0.12 + tax_bracket2 * 0.22, 2)\nnet_pay = 3362.67 - employee_contribution - 72.10 - income_tax")Tool
{
"results": {"employee_contribution": "269.01", "taxable_pay": "3021.56", "tax_bracket1": "2021.56", "tax_bracket2": "0", "income_tax": "242.59", "net_pay": "2778.97"}
}
Assistant
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "3362.67",
"employee_contribution": "269.01",
"allowed_deduction": "72.10",
"taxable_pay": "3021.56",
"income_tax": "242.59",
"net_pay": "2778.97",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}