FindIt - Multi-Label Object Detection: leaderboard
Multi-label object detection: the model returns labelled boxes for every instance of several categories in images from Pascal VOC, OpenImages and iGround. FindIt (2026), a format-informed localization benchmark for multimodal LLMs, scores each model with the bounding-box and output format it handles best, as F1 at IoU 0.5 averaged over the datasets, in percent; higher is better.
Metric: Average F1@0.5 (%) over multi-label object detection (every instance of several categories, labelled) on 1,000-query subsets of Pascal VOC, OpenImages and iGround; each model scored with the box representation, text or JSON output and JSON key that a two-stage probe on Pascal VOC found best for it; boxes Hungarian-matched to the ground truth, a match counts at IoU 0.5 or more (with the right label for multi-label queries); unparseable outputs count as empty; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 VL 8B Instruct | 63.8 | #981 |
| 2 | Qwen 3.5 9B (Non-reasoning) | 60.9 | #803 (Qwen 3.5 9B) |
| 3 | Gemini 2.5 Flash (Non-reasoning) | 60.3 | #453 (Gemini 2.5 Flash) |
| 4 | Gemma 4 E4B | 58 | #2214 |
| 5 | InternVL3-8B | 57.2 | #1688 |
| 6 | Qwen 3.5 9B (Thinking) | 54 | #803 (Qwen 3.5 9B) |
| 7 | GPT-5.4 (Non-reasoning) | 44.5 | #123 (GPT-5.4) |
| 8 | Qwen 2.5 VL 7B Instruct | 32.7 | #1833 |
| 9 | Claude Sonnet 4.5 | 27 | #250 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=findit-multi-label-object-detection · How It Works · Data refreshed daily, snapshot 2026-11-13.