Doc2DB-Bench - Global Aggregation: leaderboard

Metric: Cell-level F1 (%; relation-table cells annotated with the Global Aggregation capability of the inter-table taxonomy (Section 5.3); 203 synthesized long-document instances over 42 database schemas from BIRD and Spider in seven domain groups; identical prompts, greedy decoding at temperature 0; cells aligned by global maximum-weight tuple matching, a cell matching on exact numeric equality or at least 90 percent string similarity). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.

Top models

#ModelScore
1GPT-5.482.2
2Gemini 2.5 Pro73.03
3GPT-4o71.59
4Claude Opus 4.664.25
5Qwen 3 Max62.15
6DeepSeek V4 Flash59.83
7Qwen 2.5 14B Instruct49.23
8Llama 3.1 70B Instruct48.3

Interactive version: theaggregate.ai/benchmark?slug=doc2db-bench-global-aggregation · How It Works · Data refreshed daily, snapshot 2026-09-29.