ReceiptBench - Perception: leaderboard
Basic perception fields (raw times, totals, currency clues, invoice and tax numbers, seller name) of ReceiptBench (2026), structured extraction of 19 fields from photos and scans of real receipts and invoices (purchase, dining, travel, hotel, taxi and more), 2,000 held-out test images, JSON output. Field-level F1 times 100 (0-100), exact, numeric or list matching with a small LLM judge for near misses; higher is better.
Metric: Basic perception fields (raw times, totals, currency clues, invoice and tax numbers, seller name), field-level F1 (times 100, so 0-100) on the 2,000-image held-out test set of ReceiptBench (real travel and expense receipts and invoices, 19 annotated fields), one-shot schema prompt with JSON output; fields are scored by exact, numeric or structured-list matching with a Qwen3-4B semantic judge when string similarity falls below the match threshold; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 14 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 73.6 | #145 |
| 2 | Qwen 3 VL Plus | 73.06 | #512 |
| 3 | GPT-5 | 73.04 | #178 |
| 4 | InternVL3.5-241B | 68.53 | #629 |
| 5 | Qwen 3 VL 8B | 66.64 | #917 |
| 6 | Qwen 3 VL 32B | 66.45 | #622 |
| 7 | InternVL3-78B | 64.86 | #759 |
| 8 | Qwen 3 VL 4B | 64.07 | #1151 |
| 9 | PaddleOCR-VL | 61.33 | |
| 10 | olmOCR-7B | 57.36 | |
| 11 | InternVL3-8B | 56.96 | #1782 |
| 12 | DianJin-OCR-R1 | 50.38 | |
| 13 | InternVL3-2B | 38.51 | #3290 |
| 14 | DeepSeek-OCR-small | 36.88 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=receiptbench-perception · How It Works · Data refreshed daily, snapshot 2026-11-21.