Benchmark
ODinW
Object Detection in the Wild (ODinW) benchmark for evaluating object detection models' task-level transfer ability across diverse real-world datasets in…
- Modality
- image
- Categories
- vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 16
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen2.5-Omni-7B | Qwen | 0.424 | 2025-03-27 | evidence |
| Qwen3 VL 235B A22B Instruct | Qwen | 0.486 | 2025-09-22 | evidence |
| Qwen3 VL 235B A22B Thinking | Qwen | 0.432 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Instruct | Qwen | 0.475 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Thinking | Qwen | 0.423 | 2025-09-22 | evidence |
| Qwen3 VL 32B Instruct | Qwen | 0.466 | 2025-09-22 | evidence |
| Qwen3 VL 4B Instruct | Qwen | 0.482 | 2025-09-22 | evidence |
| Qwen3 VL 4B Thinking | Qwen | 0.394 | 2025-09-22 | evidence |
| Qwen3 VL 8B Instruct | Qwen | 0.447 | 2025-09-22 | evidence |
| Qwen3 VL 8B Thinking | Qwen | 0.398 | 2025-09-22 | evidence |
| Qwen3.5-122B-A10B | Qwen | 0.445 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.411 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.426 | 2026-02-24 | evidence |
| Qwen3.6 Plus | Qwen | 0.518 | 2026-04-02 | evidence |
| Qwen3.6-35B-A3B | Qwen | 0.508 | 2026-04-16 | evidence |
| Qwen3.7-Plus | Qwen | 0.511 | 2026-05-31 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.