← Heatmap / Gemini 3.1 Flash Lite · Task 83
Gemini 3.1 Flash Lite · Tool use · Task 83 (Traps, missing month)
Mean -3.3%
| Field | Expected | Rollout #1 (90%) | Rollout #2 (-50%) | Rollout #3 (-50%) |
|---|---|---|---|---|
| decision | clarify | clarify | calculate | calculate |
| currency | LCR | LCR | ||
| gross pay | 3229.23 | 3229.23 | ||
| employee contribution | 193.75 | 193.75 | ||
| allowed deduction | 40.33 | 40.33 | ||
| taxable pay | 2995.15 | 2995.15 | ||
| income tax | 151.61 | 151.61 | ||
| net pay | 2843.54 | 2843.54 | ||
| reason code | MISSING_PAYROLL_MONTH | MISSING_PAYROLL_MONTH | ||
| clauses | R1 R7 | R1 R7 | 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 90.0% explanation · 4 tool calls · 5.6s · $0.0031
| Component | Score | Clauses |
|---|---|---|
| decision | 100.0% | R1 R7 |
| exact | 100.0% | R1 R7 |
| field accuracy | 100.0% | R1 R7 |
| citations | 100.0% | R1 R7 |
| explanation | 0.0% | R1 R7 |
Assistant
list_documents()Tool
[
{"id": "4b62047c2fc0a2f2-payroll", "kind": "payroll"}
]
Assistant
read_document(document_id="4b62047c2fc0a2f2-payroll")Tool
{
"kind": "payroll",
"record": {"gross_pay": "3229.23", "allowed_deduction": "40.33"}
}
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": "1100.00",
"upper": "3600.00",
"middle_rate": "0.08",
"upper_rate": "0.20"
}
Assistant
calculate(program="employee_contribution = round(min(3229.23, 5000.00) * 0.06, 2)\ntaxable_pay = 3229.23 - employee_contribution - 40.33\ntax_free_amount = 1100.00\nupper_bracket_boundary = 3600.00\ntaxable_bracket_1 = max(0, min(taxable_pay, upper_bracket_boundary) - tax_free_amount)\ntaxable_bracket_2 = max(0, taxable_pay - upper_bracket_boundary)\nincome_tax = round(taxable_bracket_1 * 0.08 + taxable_bracket_2 * 0.20, 2)\nnet_pay = 3229.23 - employee_contribution - 40.33 - income_tax")Tool
{
"results": {"employee_contribution": "193.75", "taxable_pay": "2995.15", "tax_free_amount": "1100.00", "upper_bracket_boundary": "3600.00", "taxable_bracket_1": "1895.15", "taxable_bracket_2": "0", "income_tax": "151.61", "net_pay": "2843.54"}
}
Assistant
{
"decision": "clarify",
"reason_code": "MISSING_PAYROLL_MONTH",
"clauses": ["R1", "R7"]
}
Rollout #2 -50.0% answered trap · 4 tool calls · 5.7s · $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": "4b62047c2fc0a2f2-payroll", "kind": "payroll"}
]
Assistant
read_document(document_id="4b62047c2fc0a2f2-payroll")Tool
{
"kind": "payroll",
"record": {"gross_pay": "3229.23", "allowed_deduction": "40.33"}
}
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": "1100.00",
"upper": "3600.00",
"middle_rate": "0.08",
"upper_rate": "0.20"
}
Assistant
calculate(program="employee_contribution = round(min(3229.23, 5000.00) * 0.06, 2)\ntaxable_pay = 3229.23 - employee_contribution - 40.33\nincome_tax = round(max(0, min(taxable_pay - 1100.00, 3600.00 - 1100.00)) * 0.08 + max(0, taxable_pay - 3600.00) * 0.20, 2)\nnet_pay = 3229.23 - employee_contribution - 40.33 - income_tax\n")Tool
{
"results": {"employee_contribution": "193.75", "taxable_pay": "2995.15", "income_tax": "151.61", "net_pay": "2843.54"}
}
Assistant
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "3229.23",
"employee_contribution": "193.75",
"allowed_deduction": "40.33",
"taxable_pay": "2995.15",
"income_tax": "151.61",
"net_pay": "2843.54",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}
Rollout #3 -50.0% answered trap · 4 tool calls · 5.5s · $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": "4b62047c2fc0a2f2-payroll", "kind": "payroll"}
]
Assistant
read_document(document_id="4b62047c2fc0a2f2-payroll")Tool
{
"kind": "payroll",
"record": {"gross_pay": "3229.23", "allowed_deduction": "40.33"}
}
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": "1100.00",
"upper": "3600.00",
"middle_rate": "0.08",
"upper_rate": "0.20"
}
Assistant
calculate(program="employee_contribution = round(min(3229.23, 5000.00) * 0.06, 2)\ntaxable_pay = 3229.23 - employee_contribution - 40.33\ntax_part1 = max(0, min(taxable_pay, 3600.00) - 1100.00) * 0.08\ntax_part2 = max(0, taxable_pay - 3600.00) * 0.20\nincome_tax = round(tax_part1 + tax_part2, 2)\nnet_pay = 3229.23 - employee_contribution - 40.33 - income_tax\n")Tool
{
"results": {"employee_contribution": "193.75", "taxable_pay": "2995.15", "tax_part1": "151.6120", "tax_part2": "0.00", "income_tax": "151.61", "net_pay": "2843.54"}
}
Assistant
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "3229.23",
"employee_contribution": "193.75",
"allowed_deduction": "40.33",
"taxable_pay": "2995.15",
"income_tax": "151.61",
"net_pay": "2843.54",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}