SpatialThinker Release - CV-BenchAverage: leaderboard
SpatialThinker release: zero-shot, greedy temperature0,max_new_tokens2048; default reasoning templates; depth input only SpatialRGPT; othermodels RGB. STVQA7K SFT/vanillaGRPO comparators remain separately trained identities. Metric: Accuracy (%). Higher is better. Source: https://arxiv.org/html/2511.07403v1
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 79.4 | #339 |
| 2 | Claude 3.5 Sonnet | 65.9 | #347 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=spatialthinker-release-cv-benchaverage · How It Works · Data refreshed daily, snapshot 2026-10-17.