SpatialViz-Bench leaderboard
As of 13 Nov 2026, the top score on SpatialViz-Bench is 44.7% by Gemini 2.5 Pro (Google), ahead of o1 at 41.4%, across 8 model configurations with a published result (Epoch AI Benchmarking Hub, result dated 17 Jun 2025). Mental rotation, paper folding and similar spatial tasks presented as images. SpatialViz-Bench is shown for reference only and does not count toward the BenchLeader Index.
Key facts (as of 13 Nov 2026)
- Gemini 2.5 Pro holds the top SpatialViz-Bench score at 44.7% (Epoch AI Benchmarking Hub, 17 Jun 2025).
- o1 is second on SpatialViz-Bench at 41.4% (Epoch AI Benchmarking Hub, 17 Dec 2024).
- SpatialViz-Bench: Spatial visualisation: rotation, folding and animation (Epoch AI Benchmarking Hub).
- 8 model configurations have a published SpatialViz-Bench result on BenchLeader (BenchLeader, 13 Nov 2026).
- SpatialViz-Bench does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).
Spatial visualisation: rotation, folding and animation.
- Published by
- Epoch AI Benchmarking Hub
- Category
- Multimodal
- Index weight
- Reference only
- Models
- 8
- Data as of
- 13 Nov 2026
CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.
What the test looks like
Mental rotation, paper folding and similar spatial tasks presented as images.
How it is scored
Overall score, as published.
What to keep in mind
Vision models only; small set.
- 1Gemini 2.5 Pro44.7%
- 2o141.4%
- 3Gemini 2.5 Flash36.9%
- 4Llama 4 Scout34.2%
- 5Claude 3.7 Sonnet33.9%
- 6Qwen2.5 VL 72B Instruct33.3%
- 7Qwen-VL (max)32.0%
- 8Llama 4 Maverick31.8%
| # | ||||
|---|---|---|---|---|
| 1 |  Gemini 2.5 Pro | 44.7% | 54.5 | 2025-06-17 |
| 2 |  o1 | 41.4% | 53.3 | 2024-12-17 |
| 3 | Gemini 2.5 Flash | 36.9% | 52.8 | 2025-06-17 |
| 4 |  Llama 4 Scoutopen ↗ | 34.2% | 38.4 | 2025-04-05 |
| 5 |  Claude 3.7 Sonnet | 33.9% | 49.8 | 2025-02-24 |
| 6 |  Qwen2.5 VL 72B Instructopen ↗ | 33.3% | – | 2024-09-19 |
| 7 | Qwen-VLmax | 32.0% | – | 2024-01-18 |
| 8 | Llama 4 Maverickopen ↗ | 31.8% | 42.0 | 2025-04-05 |
Multimodal AI benchmark leaderboard · All LLM benchmarks
Related benchmarks
Cite as: BenchLeader, “SpatialViz-Bench leaderboard”, data as of 13 Nov 2026, https://www.benchleader.com/benchmarks/spatialviz_bench.
SpatialViz-Bench: questions
- What does SpatialViz-Bench measure?
- Mental rotation, paper folding and similar spatial tasks presented as images. Scores are reported in percent of tasks solved; higher is better.
- What is the top score on SpatialViz-Bench?
- As of 13 Nov 2026, the highest score on SpatialViz-Bench is 44.7% by Gemini 2.5 Pro (result dated 17 Jun 2025), ahead of o1 at 41.4%. Scores come from Epoch AI Benchmarking Hub and are re-read daily.
- Which AI model leads SpatialViz-Bench?
- Gemini 2.5 Pro leads SpatialViz-Bench with 44.7% as of 13 Nov 2026 (result dated 17 Jun 2025), ahead of o1 at 41.4%.
- How many models have SpatialViz-Bench results?
- 8 model configurations have a SpatialViz-Bench result on BenchLeader, all taken from Epoch AI Benchmarking Hub.
- Who runs SpatialViz-Bench and how often is it updated?
- SpatialViz-Bench is published by Epoch AI Benchmarking Hub. BenchLeader re-reads the published results once a day and records the date each result was published.
- Does SpatialViz-Bench count toward the BenchLeader Index?
- No. SpatialViz-Bench is shown for reference but left out of the composite index.