Skip to main content
PolicyBench

Claude Sonnet 4.6

Anthropic · AI alone, no tools
United States rank
#9 of 23
US exact
77.1%
United States

United States benchmark

Exact match
77.1%
Bounded score
89.9%
Parse rate
100.0%
Eligibility flags
924/984

Score by programhardest first

ProgramExactWithin 1%n
Federal tax before refundable credits48.0%50.0%100
State tax before refundable credits54.0%56.0%100
SNAP76.0%76.0%100
State refundable credits79.0%79.0%100
Payroll tax83.0%87.0%100
Person-level Medicaid eligibility87.0%87.0%177
Federal refundable credits89.0%90.0%100
Person-level CHIP eligibility89.3%89.3%177
Person-level Medicare eligibility94.4%94.4%177
Person-level Early Head Start eligibility94.7%94.7%38
SSI97.0%97.0%100
Person-level Head Start eligibility97.4%97.4%38
Free school meals eligibility98.0%98.0%100
Reduced-price school meals eligibility98.0%98.0%100
Self-employment tax98.0%99.0%100
TANF99.0%99.0%100
Person-level WIC eligibility99.4%99.4%177
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.