The AI arena is free today

Open Superagent

SUNRGBD

Progress Over Time

Interactive timeline showing model performance evolution on SUNRGBD

State-of-the-art frontier
Open
Proprietary

SUNRGBD Leaderboard

4 models
ContextCostLicense
1
Alibaba Cloud / Qwen Team
Alibaba Cloud / Qwen Team
122B
2
Alibaba Cloud / Qwen Team
Alibaba Cloud / Qwen Team
27B262K$0.30 / $2.40
3
Alibaba Cloud / Qwen Team
Alibaba Cloud / Qwen Team
236B
4
Alibaba Cloud / Qwen Team
Alibaba Cloud / Qwen Team
35B
Notice missing or incorrect data?
About this benchmark

What is SUNRGBD?

SUNRGBD evaluates RGB-D scene understanding and 3D grounding capabilities.

SUNRGBD is a image benchmark evaluating models on spatial reasoning, 3d, and vision tasks. LLM Stats tracks 4 models on this benchmark, scored on a 0–100 scale. The current average is 0.3, with the leader at 0.4.

Compare leaders on the best AI for spatial reasoning, best AI for 3d and best AI for vision leaderboards.

Current leaders

Qwen3.5-122B-A10B from Alibaba Cloud / Qwen Team currently leads the SUNRGBD leaderboard with a score of 0.362 across 4 evaluated AI models.

1Qwen3.5-122B-A10BAlibaba Cloud / Qwen Team0.4%
2Qwen3.5-27BAlibaba Cloud / Qwen Team0.4%
3Qwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen Team0.3%

FAQ

Common questions about the SUNRGBD benchmark and leaderboard.

What is the SUNRGBD benchmark?

SUNRGBD evaluates RGB-D scene understanding and 3D grounding capabilities.

What is the SUNRGBD leaderboard?

The SUNRGBD leaderboard ranks 4 AI models based on their performance on this benchmark. Currently, Qwen3.5-122B-A10B by Alibaba Cloud / Qwen Team leads with a score of 0.362. The average score across all models is 0.350.

What is the highest SUNRGBD score?

The highest SUNRGBD score is 0.362, achieved by Qwen3.5-122B-A10B from Alibaba Cloud / Qwen Team.

How many models are evaluated on SUNRGBD?

4 models have been evaluated on the SUNRGBD benchmark, with 0 verified results and 4 self-reported results.

What categories does SUNRGBD cover?

SUNRGBD is categorized under spatial reasoning, 3d, and vision. The benchmark evaluates image models.

What is the best open-source model on SUNRGBD?

Qwen3.5-122B-A10B by Alibaba Cloud / Qwen Team is the top-ranked open-source model on SUNRGBD, with a score of 0.362 (rank #1).

Which model offers the best value on SUNRGBD?

Among models scoring within 10% of the leader, Qwen3.5-27B from Alibaba Cloud / Qwen Team is the cheapest, at $0.30 per million input tokens with a score of 0.354.

How recent are the SUNRGBD leaderboard results?

The SUNRGBD leaderboard was last updated in August 2026 and currently includes 4 evaluated models.
SUNRGBD Leaderboard