ExStrucTiny - Financial Reports (Schema Query): leaderboard

Metric: Average ANLS on the closed queries giving a target JSON schema over financial reports; ExStrucTiny's 304 structured-extraction queries over 110 enterprise document images (forms, financial reports, slide decks, web pages; 102 manually written and 202 Gemini-drafted, human-validated), answered as JSON with three in-context examples; ground-truth and predicted keys are aligned by a gpt-oss-20b schema mapper and each matched leaf is scored by ANLS (unmatched leaves score 0), shown times 100; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 12 models tracked.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Pro82.5#145
2Gemini 2.5 Flash80.9#237
3Mistral Small 3.278.5#587
4Qwen 2.5 VL 32B Instruct66.4#443
5Qwen 2.5 VL 7B Instruct63.1#643
6Gemma 3 27B61.8#596
7Gemma 3 12B59.8#666
8Pixtral-12B47.1#795
9Gemma 3 4B46.6#1084

No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.

Interactive version: theaggregate.ai/benchmark?slug=exstructiny-financial-reports-schema-query · How It Works · Data refreshed daily, snapshot 2026-10-11.