Model Performance Leaderboard
Structured Data Extraction Scoring
Login
unknown
🥇
Gemini 3.1-pro-preview
Google
100%
Avg Score
100%/100%
Best / Worst
3 / 3
Runs / Docs
9.9s
Avg Time
$14
$/M Tokens
🥈
GPT 5.2
OpenAI
100%
Avg Score
100%/100%
Best / Worst
2 / 2
Runs / Docs
24.7s
Avg Time
$15.75
$/M Tokens
Model Performance Over Time
Cost vs Performance
Value Score (Score per $/M Tokens)
Head-to-Head Win Rate
Consistency (Lower Std Dev = More Reliable)
Last updated Apr 15, 2026, 11:33 PM