PolicyBench - US Exact Match - free_school_meals_eligible: leaderboard

The free_school_meals_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-5.6 Sol97#33
2Gemini 3 Flash (Preview)97#151
3Gemini 3.5 Flash97#107
4GPT-6 Astra97#8
5GPT-6.1 Sol97#12
6GPT-6 Sol97#29
7Gemini 3.1 Pro (Preview)96#99
8Claude Opus 4.796#82
9MiniMax-M396#278
10Gemini 3.1 Flash Lite (Preview)96#418
11Claude Sonnet 596#118
12Qwen 3.7 Max96#156
13Gemini 3.7 Flash96#38
14Gemini 3.6 Flash96#79
15Claude Fable 596#28

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-free-school-meals-eligible · How It Works · Data refreshed daily, snapshot 2026-11-17.