XTC-Bench - Object Retrieval: leaderboard
XTC-Bench (2026) object-retrieval questions on COCO and Visual Genome images: the model names the object that has the given attributes, judged against the scene-graph reference. Score 0-1, shown times 100; higher is better.
Metric: Understanding score (0-1, times 100) on object-retrieval questions (which object has the given attributes), a Qwen3-235B judge scores each fact 0-5, normalized to 0-1 and shown times 100, over XTC-Bench's 2,000 scene-graph-annotated images from COCO 2017 val and Visual Genome (over 31,000 atomic facts about objects, attributes and relations); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 71.8 | #185 |
| 2 | Gemini 2.5 Flash Image | 68.6 | |
| 3 | BLIP3-o8B | 67.9 | |
| 4 | BAGEL-7B-MoT | 67.4 | #4668 |
| 5 | OmniGen2 | 67.2 | #4625 |
| 6 | Janus-Pro-7B | 61.6 | #6889 |
| 7 | Show-o2-7B | 58.3 | |
| 8 | Tar-7B | 55.7 | |
| 9 | Show-o | 41.5 | |
| 10 | MMaDA-8B | 37.7 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=xtc-bench-object-retrieval · How It Works · Data refreshed daily, snapshot 2026-11-22.