U.S. House — accuracy by surface
“Who is my U.S. representative in {district}?” · latest graded response per district per surface, across all runs (web apps and APIs). Verdicts are human-authoritative where reviewed.
API · paid
ChatGPT API — GPT-5
90%
394/436 accurate
API · paid
ChatGPT API — GPT-5 + web search
99%
430/436 accurate
API · paid
Claude API — Opus 4.8
9%
40/436 accurate
API · paid
Claude API — Opus 4.8 + thinking
11%
46/436 accurate
API · paid
Claude API — Opus 4.8 + web search
97%
425/436 accurate
API · paid
Gemini API — 3.1 Pro Preview
83%
170/204 accurate
API · paid
Gemini API — 3.1 Pro Preview + search
95%
167/176 accurate
API · paid
Grok API — Grok 4
80%
348/436 accurate
Web app · paid
ChatGPT web — Plus
97%
227/234 accurate
Web app · free
ChatGPT web — free account
96%
188/196 accurate
Web app · paid
Claude web — Pro
92%
370/402 accurate
Web app · free
Claude web — free account
100%
10/10 accurate
Web app · free
Google Search — AI Overview
99%
311/315 accurate
Surface:
● accurate
● partially accurate
● inaccurate
● hallucinated
● no answer
● ungradeable
● not captured