Skip to main content
PolicyBench

GPT-5.6 Sol

OpenAI · AI alone, no tools
United States rank
#1 of 23
US exact
88.7%
United States

United States benchmark

Exact match
88.7%
Bounded score
95.3%
Parse rate
100.0%
Eligibility flags
965/984

Score by programhardest first

ProgramExactWithin 1%n
State tax before refundable credits64.0%68.0%100
Federal tax before refundable credits75.0%84.0%100
SNAP78.0%82.0%100
State refundable credits84.0%84.0%100
Federal refundable credits94.0%96.0%100
Payroll tax94.0%94.0%100
Person-level Medicare eligibility94.4%94.4%177
Person-level Medicaid eligibility96.6%96.6%177
SSI97.0%97.0%100
Person-level CHIP eligibility98.9%98.9%177
Reduced-price school meals eligibility99.0%99.0%100
TANF99.0%99.0%100
Free school meals eligibility100.0%100.0%100
Local income tax100.0%100.0%100
Person-level Early Head Start eligibility100.0%100.0%38
Person-level Head Start eligibility100.0%100.0%38
Person-level WIC eligibility100.0%100.0%177
Self-employment 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.