PolicyBench - US Exact Match - person_chip_eligible: leaderboard

The person_chip_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: Not forecast. 52 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-6 Astra100#8
2Gemini 3.1 Flash Lite (Preview)100#418
3GPT-5.6 Terra100#68
4GPT-6.1 Sol100#12
5Gemini 4 Argon100#14
6GPT-5.4 Nano100#645
7Inkling100#282
8DeepSeek V4 Pro (0813)100#97
9Muse Wonder100#31
10Gemini 3 Flash (Preview)99.44#151
11GPT-6 Sol99.44#29
12GPT-5.6 Sol98.87#33
13GPT-6 Luna98.87#105
14Claude Fable 598.87#28
15Grok 4.598.87#91

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-chip-eligible · How It Works · Data refreshed daily, snapshot 2026-11-17.