spatial reasoning benchmark
EmbSpatialBench Leaderboard
EmbSpatialBench evaluates embodied spatial understanding and reasoning capabilities.
Updated Aug 17, 2026
Models8
Model coverage8
MetricScore
EvidenceB
EmbSpatialBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score0.846 points | Percentile100.0% | Participants8 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score0.845 points | Percentile85.7% | Participants8 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score0.843 points | Percentile71.4% | Participants8 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score0.843 points | Percentile57.1% | Participants8 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score0.839 points | Percentile42.9% | Participants8 | EvidenceC | Evaluated |
| Rank06 | ModelBY | Score0.834 points | Percentile28.6% | Participants8 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score0.831 points | Percentile14.3% | Participants8 | EvidenceC | Evaluated |
| Rank08 | ModelBY | Score0.825 points | Percentile0.0% | Participants8 | EvidenceC | Evaluated |
EmbSpatialBench Highlights
The leading models and scores on this benchmark.
EmbSpatialBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for EmbSpatialBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis embspatialbench AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACQwen3.6-27BAlibaba Cloud / Qwen Team
- Score
- 0.846 points
- Price
- $0.60 input / $3.6 output per 1M tokens
- Speed
- Up to 6.1 tok/s via Novita
Strengths
- Ranks #1 of 8 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures EmbSpatialBench, not total model capability
- 02ACQwen3.5-27BAlibaba Cloud / Qwen Team
- Score
- 0.845 points
- Price
- $0.30 input / $2.4 output per 1M tokens
- Speed
- Up to 6.7 tok/s via Novita
Strengths
- Ranks #2 of 8 compared models
- 86th percentile on this benchmark
- C evidence result
Considerations
- This result measures EmbSpatialBench, not total model capability
- 03ACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen Team
- Score
- 0.843 points
Strengths
- Ranks #3 of 8 compared models
- 71th percentile on this benchmark
- C evidence result
Considerations
- This result measures EmbSpatialBench, not total model capability
- 04ACQwen3.6-35B-A3BAlibaba Cloud / Qwen Team
- Score
- 0.843 points
- Price
- $0.25 input / $1.5 output per 1M tokens
Strengths
- Ranks #4 of 8 compared models
- 57th percentile on this benchmark
- C evidence result
Considerations
- This result measures EmbSpatialBench, not total model capability
- 05ACQwen3.5-122B-A10BAlibaba Cloud / Qwen Team
- Score
- 0.839 points
- Price
- $0.40 input / $3.2 output per 1M tokens
Strengths
- Ranks #5 of 8 compared models
- 43th percentile on this benchmark
- C evidence result
Considerations
- This result measures EmbSpatialBench, not total model capability
Selection summary
Best AI Models for EmbSpatialBench
Qwen3.6-27B currently leads EmbSpatialBench with 0.846 points. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is EmbSpatialBench?
What EmbSpatialBench measures and how its scores work.
EmbSpatialBench evaluates embodied spatial understanding and reasoning capabilities.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- EmbSpatialBench
- Modality
- image
- Primary category
- spatial reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- embspatialbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about EmbSpatialBench.
Which model scores highest on EmbSpatialBench?
Qwen3.6-27B is currently ranked first with 0.846 points.
What does EmbSpatialBench measure?
EmbSpatialBench evaluates embodied spatial understanding and reasoning capabilities.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
8 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.