14 models ranked by quality score, sorted by rank with pricing and best-value picks.
Verdict
For extraction, use GPT 5.4 for quality or Gemini 3.5 Flash-Lite for cost. The quality gap between #1 and #2 is -1 points.
Rankings
GPT 5.4 ranks #1 for extraction with a confidence score of 89/100.
Gemini 3.5 Flash-Lite offers the best value for extraction at $0.25/$1.50 per million tokens with a confidence of 83/100.
Comparisons show estimated costs at list price. The dashboard reveals your real spend and savings.