BaFCo - Key Information Extraction: leaderboard

Metric: Macro-F1 of extracted values (%; value extraction from Bangla government forms: given each key, return its value from the form image, formulated as visual question answering; 1,926 key-value pairs on 186 pages, Bangla subset; zero-shot prompt). Source: arxiv.org. Saturation forecast: Around December 2026. 5 models tracked.

Top models

#ModelScore
1Gemini 3 Pro84.8
2Qwen 3.6 Plus79.4
3GPT-5.278.1
4Kimi K2.568.1
5Claude Opus 4.667.8

Interactive version: theaggregate.ai/benchmark?slug=bafco-key-information-extraction · How It Works · Data refreshed daily, snapshot 2026-09-29.