PolicyBench - US Exact Match - person_medicaid_eligible: leaderboard

The person_medicaid_eligible output of PolicyBench US, without tools. Read countries.us.heatmap exact, with the native common per-output denominator and symmetric reference exclusions. Aggregate programStats rows across models are not model scores. Metric: Exact match (%). Source: https://policybench.org

Metric: Exact match (%). Source: policybench.org. Saturation forecast: Estimated already saturated. 52 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-6 Astra99.42#8
2Claude Opus 5.597.69#7
3GPT-6 Luna97.69#105
4Grok 4.797.69#48
5GPT-6 Sol97.69#29
6GPT-6.1 Terra97.69#22
7Inkling97.69#282
8Claude Fable 5.297.69#1
9Gemini 3.1 Pro (Preview)97.11#99
10GPT-5.6 Sol97.11#33
11Gemini 3.8 Flash97.11#39
12Claude Fable 5.197.11#17
13Muse Wonder97.11#31
14GPT-5.596.53#50
15Gemini 3.5 Flash96.53#107

No result here: #2 GPT-6.2 Astra, #3 Gemini 4 Carbon, #6 GPT-6.2 Sol.

Interactive version: theaggregate.ai/benchmark?slug=policybench-us-exact-match-person-medicaid-eligible · How It Works · Data refreshed daily, snapshot 2026-11-17.