OST-Bench: leaderboard
A multimodal model explores an indoor scan as an agent, receiving new frames turn by turn in one dialogue, and answers questions about its own position, what it has seen and where objects are relative to it; unlike offline spatial benchmarks, the observations arrive incrementally. Scores are accuracy (%); the README states 1.4k scenes and 10k question-answer pairs, the per-model sample is not stated.
Metric: Accuracy (%). Source: github.com. Saturation forecast: Estimated already saturated. 10 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 | 53.4 | #505 |
| 2 | InternVL2.5-78B | 51.08 | #1036 |
| 3 | InternVL2.5-38B | 50.78 | #1366 |
| 4 | Gemini 2.0 Flash | 49.54 | #723 |
| 5 | Qwen 2.5 VL 32B Instruct | 46.86 | #1074 |
| 6 | Qwen 2.5 VL 72B Instruct | 45.62 | #849 |
| 7 | InternVL2.5-8B | 44.63 | #2401 |
| 8 | LLaVA-Video-72B-Qwen2 | 43.22 | #1344 |
| 9 | Qwen 2.5 VL 7B Instruct | 41.16 | #1893 |
| 10 | LLaVA-Video-7B-Qwen2 | 39.28 | #1910 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=ost-bench · How It Works · Data refreshed daily, snapshot 2026-11-17.