JaWildText - Receipt KIE: leaderboard
Metric: Key-information extraction F1 (0-1, scaled to 0-100) over the header fields and line items extracted as JSON from 1,151 photographed Japanese receipts, zero-shot open-weight VLM inference at temperature 0 with up to 2,048 output tokens, one image at its original resolution, a fixed prompt per task and unparseable outputs scored 0; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 3 27B (IT) | 39 | #509 |
| 2 | Gemma 3 12B (IT) | 38 | #655 |
| 3 | Gemma 3 4B (IT) | 23 | #971 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=jawildtext-receipt-kie · How It Works · Data refreshed daily, snapshot 2026-10-11.