LLM Stats (EmbSpatialBench): leaderboard
Spatial reasoning benchmark evaluating understanding of embedded spatial relationships, positions, and layouts in visual and textual scenarios.
Metric: Score (%). Source: llm-stats.com. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 27B | 84.6 | #170 |
| 2 | Qwen 3.5 27B | 84.5 | #187 |
| 3 | Qwen 3.6 35B A3B | 84.3 | #226 |
| 4 | Qwen 3 VL 235B A22B (Thinking) | 84.3 | #238 (Qwen 3 VL 235B A22B) |
| 5 | Qwen 3.5 122B A10B | 83.9 | #173 |
| 6 | Seed 2.1 Pro | 83.4 | #67 |
| 7 | Qwen 3.5 35B A3B | 83.1 | #256 |
| 8 | Seed 2.1 Turbo | 82.5 | #86 |
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-embspatialbench · How It Works · Data refreshed daily, snapshot 2026-10-20.