Claude Fable 5.1
United States benchmark
Serving sensitivity This row rejects forced tool calls, so its row answers as a JSON object and reasons at the provider default. The same model, re-run with the answer tool declared under tool_choice: auto (it reasons in both runs, so this compares transports), scores 91.7% exact (+0.8) and would rank #4 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 eligibility100.0%0.3%
- Self-employment tax100.0%2.1%
- Reduced-price school meals eligibility99.0%0.1%
- TANF99.0%0.3%
- SSI99.0%2.0%
- Federal refundable credits98.0%3.7%
- Free school meals eligibility98.0%0.7%
- Person-level CHIP eligibility97.2%0.2%
- Person-level Medicaid eligibility97.1%30%
- Person-level Medicare eligibility96.5%11%
- Payroll tax91.7%16%
- State refundable credits90.9%0.6%
- SNAP88.2%4.1%
- Federal tax before refundable credits79.8%19%
- State tax before refundable credits68.8%6.0%
Table view (exact, within 1%, outputs), hardest first
| Program | Exact | Within 1% | n |
|---|---|---|---|
| State tax before refundable credits | 68.8% | 72.0% | 93 |
| Federal tax before refundable credits | 79.8% | 84.5% | 84 |
| SNAP | 88.2% | 92.5% | 93 |
| State refundable credits | 90.9% | 90.9% | 99 |
| Payroll tax | 91.7% | 93.8% | 96 |
| Person-level Medicare eligibility | 96.5% | 96.5% | 172 |
| Person-level Medicaid eligibility | 97.1% | 97.1% | 173 |
| Person-level CHIP eligibility | 97.2% | 97.2% | 177 |
| Federal refundable credits | 98.0% | 98.0% | 100 |
| Free school meals eligibility | 98.0% | 98.0% | 100 |
| SSI | 99.0% | 99.0% | 97 |
| Reduced-price school meals eligibility | 99.0% | 99.0% | 100 |
| TANF | 99.0% | 99.0% | 100 |
| Local income tax | 100.0% | 100.0% | 98 |
| Person-level Early Head Start eligibility | 100.0% | 100.0% | 38 |
| Person-level Head Start eligibility | 100.0% | 100.0% | 38 |
| Person-level WIC eligibility | 100.0% | 100.0% | 177 |
| Self-employment tax | 100.0% | 100.0% | 100 |
Hardest casesworst misses on positive references
- SNAP100% offReference $240 · predicted $0Inspect household #013
- Federal tax before refundable credits100% offReference $643 · predicted $0Inspect household #023
- SNAP100% offReference $288 · predicted $0Inspect household #027
- State refundable credits100% offReference $62 · predicted $0Inspect household #028
- SNAP100% offReference $288 · predicted $0Inspect household #030
- SNAP100% offReference $288 · predicted $0Inspect household #073
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 8,765 rows whose legacy threshold score is below 1. That universe contains 8,761 of 8,761 exact-match misses and 4 exact hits. Another 2,329 rows with bounded score below 100 were not selected and have no audit annotation.