DRAGON (Diagrams) - Circuit-VQA: leaderboard

DRAGON (2026) evidence-grounded reasoning on circuit schematics from Circuit-VQA: given the question and its answer, the model must box every diagram region needed to justify the answer. Grounding IoU (%) between predicted and human-verified evidence regions, averaged over three prompting strategies; higher is better.

Metric: Evidence grounding on circuit schematics from Circuit-VQA: given the diagram, the question and the verified answer, the model returns bounding boxes for every visual element needed to justify the answer; Grounding IoU (%) between the union of predicted boxes and the union of the human-verified gold evidence boxes, averaged over the EDGE (direct), SAGE (select then ground) and VERGE (verify and refine) prompting strategies; DRAGON test split; temperature 0.2, top-p 0.7; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Pro (Preview)5.6#119
2Claude Opus 4.63.9#113
3Kimi K2.53.4#266
4Claude Sonnet 4.62.2#173
5Qwen 3.5 35B A3B2.1#492
6InternVL3.5-38B2#1021
7Llama 4 Maverick Instruct1.8#1157
8Gemma 3 27B (IT)1.6#1324

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=dragon-diagrams-circuit-vqa · How It Works · Data refreshed daily, snapshot 2026-11-21.