Skip to main content
PolicyBench

GPT-5.4 mini

OpenAI · AI alone, no tools
United States rank
#20 of 23
US exact
70.5%
United States

United States benchmark

Exact match
70.5%
Bounded score
78.8%
Parse rate
100.0%
Eligibility flags
898/984

Score by programhardest first

ProgramExactWithin 1%n
Federal tax before refundable credits50.0%50.0%100
Payroll tax54.0%65.0%100
State tax before refundable credits56.0%56.0%100
SNAP74.0%74.0%100
State refundable credits79.0%79.0%100
Federal refundable credits81.0%81.0%100
Person-level Medicaid eligibility83.6%83.6%177
Person-level Head Start eligibility84.2%84.2%38
Person-level WIC eligibility86.4%86.4%177
Self-employment tax90.0%95.0%100
Person-level CHIP eligibility92.1%92.1%177
Person-level Early Head Start eligibility92.1%92.1%38
Person-level Medicare eligibility96.0%96.0%177
SSI97.0%97.0%100
Free school meals eligibility98.0%98.0%100
Reduced-price school meals eligibility99.0%99.0%100
TANF99.0%99.0%100
Local income tax100.0%100.0%100

Hardest casesworst misses on positive references

Scores are from the frozen manuscript snapshot under the AI-alone condition: one structured response per household, no tools, graded against PolicyEngine reference outputs. See the leaderboard and paper for methodology.