ElecVQA-Bench - Binary Defect Assessment (Zero-Shot): leaderboard

Metric: Balanced accuracy (%; mean of the defective and normal class recalls on the 2,021-item T2 test split, 766 defective and 1,255 normal crops, with abstentions scored as errors; zero-shot with the P3 prompt (asset description and decision tree) and JSON-constrained guided decoding). Source: arxiv.org. Saturation forecast: Around December 2026. 7 models tracked.

Top models

#ModelScore
1Qwen 3 VL 8B74.3
2Qwen 3.8 27B (Non-reasoning)66.5
3Qwen 2.5 VL 7B57.8

Interactive version: theaggregate.ai/benchmark?slug=elecvqa-bench-binary-defect-assessment-zero-shot · How It Works · Data refreshed daily, snapshot 2026-09-26.