OccludeBench - Direct: leaderboard
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around January 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 71.6 | #57 |
| 2 | Claude Opus 4.6 | 51.8 | #61 |
| 3 | GPT-5.4 | 37.6 | #79 |
| 4 | Llama 4 Maverick | 31.6 | #454 |
| 5 | Qwen 3 VL 8B Instruct | 20.9 | #409 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=occludebench-direct · How It Works · Data refreshed daily, snapshot 2026-10-14.