# Causal Spatial Reasoning on CausalSpatial

Source: [Causal Spatial Reasoning on CausalSpatial](<https://www.sota2.com/research/sota/causal-spatial-reasoning-on-causalspatial>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:54:28.783Z

Evaluation of model performance on the CausalSpatial dataset, focusing on causal and spatial reasoning capabilities, measured by overall average score and rank.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Causal Spatial Reasoning |
| Dataset (including any stated split) | CausalSpatial |
| Metric | Overall Average Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Overall Average Score](<https://www.sota2.com/research/sota/causal-spatial-reasoning-on-causalspatial.md?metric=Overall%20Average%20Score>): Higher is better; unit: PERCENT.

- [Rank](<https://www.sota2.com/research/sota/causal-spatial-reasoning-on-causalspatial.md?metric=Rank>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Overall Average Score | Result date | Report paper |
| --- | --- | --- | --- |
| Human | 84.49 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| GPT5 | 54.17 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Gemini2.5 Pro | 50.55 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Qwen3-VL-30B-A3B-T. | 50.5 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Gemini2.5 Flash | 48.82 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Sonnet 3.7 | 48.07 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Qwen3-VL-30B-A3B-I. | 45.8 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| GPT5-mini | 45.44 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Qwen3-VL-4B-I. | 44.76 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Qwen3-VL-8B-I. | 43.53 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Qwen3-VL-8B-T. | 42.65 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Qwen3-VL-2B-I. | 40.6 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Spatial-MLLM | 40 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Qwen2.5-VL-7B-I. | 39.61 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| LLaVAOneVision1.5-8B-I. | 34.62 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Spatial-VLM | 33.5 | Not recorded | 69705ddae25ad2fa9d1ed67a |
| Random | 28.6 | Not recorded | 69705ddae25ad2fa9d1ed67a |

### Human

Overall Average Score: 84.49. Result ID: 6997a7bf5698665ec4fddbfe.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT5

Overall Average Score: 54.17. Result ID: 6997a7bf5698665ec4fddbf9.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Gemini2.5 Pro

Overall Average Score: 50.55. Result ID: 6997a7bf5698665ec4fddbfb.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen3-VL-30B-A3B-T.

Overall Average Score: 50.5. Result ID: 6997a7bf5698665ec4fddbf8.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Gemini2.5 Flash

Overall Average Score: 48.82. Result ID: 6997a7bf5698665ec4fddbfc.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Sonnet 3.7

Overall Average Score: 48.07. Result ID: 6997a7bf5698665ec4fddbfd.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen3-VL-30B-A3B-I.

Overall Average Score: 45.8. Result ID: 6997a7bf5698665ec4fddbf7.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT5-mini

Overall Average Score: 45.44. Result ID: 6997a7bf5698665ec4fddbfa.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen3-VL-4B-I.

Overall Average Score: 44.76. Result ID: 6997a7bf5698665ec4fddbf4.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen3-VL-8B-I.

Overall Average Score: 43.53. Result ID: 6997a7bf5698665ec4fddbf5.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen3-VL-8B-T.

Overall Average Score: 42.65. Result ID: 6997a7bf5698665ec4fddbf6.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen3-VL-2B-I.

Overall Average Score: 40.6. Result ID: 6997a7bf5698665ec4fddbf3.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Spatial-MLLM

Overall Average Score: 40. Result ID: 6997a7bf5698665ec4fddbf0.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b58a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen2.5-VL-7B-I.

Overall Average Score: 39.61. Result ID: 6997a7bf5698665ec4fddbf2.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### LLaVAOneVision1.5-8B-I.

Overall Average Score: 34.62. Result ID: 6997a7bf5698665ec4fddbf1.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e58.md>)

[Implementation](<https://llava-vl.github.io/blog/llava-onevision>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Spatial-VLM

Overall Average Score: 33.5. Result ID: 6997a7bf5698665ec4fddbef.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71f91e209131cea53d86.md>)

[Implementation](<https://spatial-vlm.github.io/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Random

Overall Average Score: 28.6. Result ID: 6997a7bf5698665ec4fddbff.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddae25ad2fa9d1ed67a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
