Claude Fable 5
United States benchmark
Serving sensitivity This row ran under the board's forced answer-tool call, which switches Claude's extended thinking off, one output per request. The same model, re-run with tool_choice: auto and the whole household in one request, scores 92.8% exact (+7.9) and would rank #6 on the live board; the board keeps the request shape its model card records. Read the note.
Exact match by programall 18 output groups, best first
Bar length is the unweighted exact-match rate on that program's outputs; the right column is the program's share of the headline weight, which follows household dollars, so the bars do not average to the headline.
- Local income tax100.0%0.3%
- Person-level Early Head Start eligibility100.0%3.1%
- Person-level Head Start eligibility100.0%1.2%
- Person-level WIC eligibility99.4%0.3%
- Free school meals eligibility99.0%0.7%
- Reduced-price school meals eligibility99.0%0.1%
- TANF99.0%0.3%
- Person-level CHIP eligibility98.9%0.2%
- Self-employment tax97.0%2.1%
- SSI96.9%2.0%
- Person-level Medicaid eligibility94.8%30%
- Person-level Medicare eligibility91.3%11%
- Federal refundable credits87.8%3.7%
- Payroll tax86.3%16%
- SNAP83.9%4.1%
- State refundable credits82.7%0.6%
- State tax before refundable credits63.5%6.0%
- Federal tax before refundable credits60.8%19%
Table view (exact, within 1%, outputs), hardest first
| Program | Exact | Within 1% | n |
|---|---|---|---|
| Federal tax before refundable credits | 60.8% | 62.0% | 79 |
| State tax before refundable credits | 63.5% | 64.7% | 85 |
| State refundable credits | 82.7% | 82.7% | 98 |
| SNAP | 83.9% | 83.9% | 93 |
| Payroll tax | 86.3% | 86.3% | 95 |
| Federal refundable credits | 87.8% | 90.8% | 98 |
| Person-level Medicare eligibility | 91.3% | 91.3% | 172 |
| Person-level Medicaid eligibility | 94.8% | 94.8% | 173 |
| SSI | 96.9% | 96.9% | 97 |
| Self-employment tax | 97.0% | 99.0% | 100 |
| Person-level CHIP eligibility | 98.9% | 98.9% | 177 |
| Free school meals eligibility | 99.0% | 99.0% | 100 |
| Reduced-price school meals eligibility | 99.0% | 99.0% | 100 |
| TANF | 99.0% | 99.0% | 100 |
| Person-level WIC eligibility | 99.4% | 99.4% | 177 |
| Local income tax | 100.0% | 100.0% | 100 |
| Person-level Early Head Start eligibility | 100.0% | 100.0% | 38 |
| Person-level Head Start eligibility | 100.0% | 100.0% | 38 |
Hardest casesworst misses on positive references
- Federal tax before refundable credits593% offReference $500 · predicted $3,465Inspect household #046
- Federal tax before refundable credits332% offReference $1,910 · predicted $8,258Inspect household #068
- State refundable credits322% offReference $95 · predicted $402Inspect household #023
- State tax before refundable credits265% offReference $1,255 · predicted $4,580Inspect household #068
- State tax before refundable credits182% offReference $1,026 · predicted $2,896Inspect household #122
- SNAP100% offReference $240 · predicted $0Inspect household #013
Scores are from the frozen manuscript snapshot under the AI-alone condition: structured responses over the same household facts (whole-scenario or in output subsets, per the serving-configuration table), no tools, graded against PolicyEngine reference outputs. See the leaderboard and paper for methodology. The frozen US annotations cover 7,527 rows whose legacy threshold score is below 1. That universe contains 7,523 of 7,523 exact-match misses and 4 exact hits. Another 2,072 rows with bounded score below 100 were not selected and have no audit annotation.