ConfBench - Extraction Accuracy: leaderboard
Metric: Weighted overall accuracy (%; mean per-field similarity, normalized Levenshtein for strings and a tolerance comparator for numbers; verbalized top-4 guesses with probabilities in one call, OCR text with Amazon Textract confidences plus the document image, over the entity fields of 1,346 degraded variants of 75 RealKIE-FCC-Verified invoices). Source: arxiv.org. Saturation forecast: Around December 2026. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 77 |
| 2 | Kimi K2.5 | 76 |
| 3 | Claude Opus 4.6 | 75 |
| 4 | Qwen 3.6 27B | 74 |
| 5 | Claude Haiku 4.5 | 71 |
| 6 | Gemma 3 12B | 65 |
| 7 | Qwen 3 VL 235B A22B | 64 |
Interactive version: theaggregate.ai/benchmark?slug=confbench-extraction-accuracy · How It Works · Data refreshed daily, snapshot 2026-09-29.