Chain-of-Procedure: leaderboard
Recent advances in vision-language models (VLMs) have achieved impressive results on standard image-text tasks, yet their potential for visual procedure question answering (VP-QA) remains largely unexplored. VP-QA presents unique challenges where users query next-step actions by uploading images for intermediate states of complex procedures. To systematically evaluate VLMs on this practical task,
Metric: Zero-Shot (self-reported). Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 62.5 | #343 |
| 2 | Claude 3.5 Sonnet | 47.5 | #350 |
| 3 | Gemini 2.5 Flash | 44.7 | #245 |
| 4 | GPT-4o Mini | 34.4 | #599 |
| 5 | Qwen 2.5 VL 7B | 25.1 | #643 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=chain-of-procedure · How It Works · Data refreshed daily, snapshot 2026-10-20.