OpenRef - Negative Rejection: leaderboard
Rejection of absent targets on OpenRef (2026), an open-world referring expression benchmark: for expressions whose object is not in the image, N3R rewards outputting no box and penalizes confident hallucinated boxes. Scored 0-100; higher is better.
Metric: N3R (0-100), negative relative rejection reliability: mean over expressions whose target is absent of the product of (1 - confidence) over the hallucinated boxes, average over five categories, zero-shot box grounding, each model prompted in its own grounding format; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2 VL 7B | 90.9 | #2275 |
| 2 | Qwen 3 VL 8B | 84.6 | #917 |
| 3 | GLM-4.6V-Flash | 78.7 | #1040 |
| 4 | LLaVA-OneVision-1.5-8B | 75.1 | #1864 |
| 5 | MiniCPM-V-4.5 | 73.6 | #1441 |
| 6 | OpenRef Mistral-3 8B (checkpoint unspecified) | 70.9 | |
| 7 | Keye-VL-1.5-8B | 70.3 | #1720 |
| 8 | InternVL3.5-8B | 51 | #1604 |
| 9 | Qwen 3 VL 2B | 38.1 | #2134 |
| 10 | Qwen 3 VL 4B | 37.9 | #1151 |
| 11 | Qwen 2.5 VL 32B | 37.9 | #941 |
| 12 | MiMo-VL-7B-RL | 20.7 | #1155 |
| 13 | Qwen 2.5 VL 7B | 14.1 | #1862 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=openref-negative-rejection · How It Works · Data refreshed daily, snapshot 2026-11-21.