PolicyBench - US Exact Match - state_refundable_credits: leaderboard

The state_refundable_credits 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: Around February 2027. 52 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1Claude Fable 5.291.84#1
2GPT-6.1 Sol90.82#12
3Claude Fable 5.190.82#17
4Claude Opus 5.589.8#7
5GPT-5.6 Sol87.76#33
6GPT-6 Astra87.76#8
7GPT-5.586.73#50
8GPT-6 Luna86.73#105
9Gemini 3.8 Flash85.71#39
10Grok 4.785.71#48
11GPT-6 Sol85.71#29
12Grok 4.685.71#47
13DeepSeek V4.1 Flash84.69#69
14Gemini 4 Argon84.69#14
15GPT-6.1 Terra84.69#22

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-state-refundable-credits · How It Works · Data refreshed daily, snapshot 2026-11-17.