vision benchmark
ODinW
Object Detection in the Wild (ODinW) benchmark for evaluating object detection models' task-level transfer ability across diverse real-world datasets in terms of prediction accuracy and adaptation efficiency
Updated Aug 11, 2026
Models16
Model coverage16
MetricScore
EvidenceB
ODinW Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 51.8% | 100.0% | 16 | C | |
| 02 | AC | 51.1% | 93.3% | 16 | C | |
| 03 | AC | 50.8% | 86.7% | 16 | C | |
| 04 | AC | 48.6% | 80.0% | 16 | C | |
| 05 | AC | 48.2% | 73.3% | 16 | C | |
| 06 | AC | 47.5% | 66.7% | 16 | C | |
| 07 | AC | 46.6% | 60.0% | 16 | C | |
| 08 | AC | 44.7% | 53.3% | 16 | C | |
| 09 | AC | 44.5% | 46.7% | 16 | C | |
| 10 | AC | 43.2% | 40.0% | 16 | C | |
| 11 | AC | 42.6% | 33.3% | 16 | C | |
| 12 | AC | 42.4% | 26.7% | 16 | C | |
| 13 | AC | 42.3% | 20.0% | 16 | C | |
| 14 | AC | 41.1% | 13.3% | 16 | C | |
| 15 | AC | 39.8% | 6.7% | 16 | C | |
| 16 | AC | 39.4% | 0.0% | 16 | C |
ODinW Score Distribution
A closer view of the leading scores on this benchmark.
ODinW Highlights
The leading models and scores on this benchmark.
What is ODinW?
What ODinW measures and how its scores work.
Object Detection in the Wild (ODinW) benchmark for evaluating object detection models' task-level transfer ability across diverse real-world datasets in terms of prediction accuracy and adaptation efficiency
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- ODinW
- Modality
- image
- Primary category
- vision
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- odinw|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about ODinW.
Which model scores highest on ODinW?
Qwen3.6 Plus is currently ranked first with 51.8%.
What does ODinW measure?
Object Detection in the Wild (ODinW) benchmark for evaluating object detection models' task-level transfer ability across diverse real-world datasets in terms of prediction accuracy and adaptation efficiency
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
16 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.