# Trajectory Prediction on Target-Bench

Source: [Trajectory Prediction on Target-Bench](<https://www.sota2.com/research/sota/trajectory-prediction-on-target-bench>)

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

Data updated: 2026-04-10T08:27:30.956Z

Evaluation of trajectory prediction models on the Target-Bench dataset, assessed using Average Displacement Error (ADE), Final Displacement Error (FDE), and Dynamic Time Warping (DTW).

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 | Trajectory Prediction |
| Dataset (including any stated split) | Target-Bench |
| Metric | ADE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 9 of 9 |
| 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

- [ADE](<https://www.sota2.com/research/sota/trajectory-prediction-on-target-bench.md?metric=ADE>): Lower is better; unit: SCALAR.

- [FDE](<https://www.sota2.com/research/sota/trajectory-prediction-on-target-bench.md?metric=FDE>): Lower is better; unit: SCALAR.

- [DTW](<https://www.sota2.com/research/sota/trajectory-prediction-on-target-bench.md?metric=DTW>): Lower is better; unit: SCALAR.

## Recorded results

| Method | ADE | Result date | Report paper |
| --- | --- | --- | --- |
| WorldMAP | 42.06 | Not recorded | 69d883fe7d0172140ec779c7 |
| Gemini-3-Pro | 51.27 | Not recorded | 69d883fe7d0172140ec779c7 |
| GPT-5.4 | 94.65 | Not recorded | 69d883fe7d0172140ec779c7 |
| o3 | 112.14 | Not recorded | 69d883fe7d0172140ec779c7 |
| InternVL3-14B | 123.33 | Not recorded | 69d883fe7d0172140ec779c7 |
| Qwen3-VL-4B | 140.42 | Not recorded | 69d883fe7d0172140ec779c7 |
| Qwen3-VL-32B | 151.21 | Not recorded | 69d883fe7d0172140ec779c7 |
| MindJourney | 152.41 | Not recorded | 69d883fe7d0172140ec779c7 |
| Qwen3-VL-8B | 183.93 | Not recorded | 69d883fe7d0172140ec779c7 |

### WorldMAP

ADE: 42.06. Result ID: 69d8b46f47f34ce924c185c4.

[Reporting paper](<https://www.sota2.com/research/paper/69d883fe7d0172140ec779c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d883fe7d0172140ec779c7.md>)

Recorded evaluation configuration: {"Method Family":"World-model augmented","Backbone":"Qwen3-VL-8B"}. This record does not assert independent reproduction.

### Gemini-3-Pro

ADE: 51.27. Result ID: 69d8b46f47f34ce924c185be.

[Reporting paper](<https://www.sota2.com/research/paper/69d883fe7d0172140ec779c7.md>)

Recorded evaluation configuration: {"Method Family":"Proprietary"}. This record does not assert independent reproduction.

### GPT-5.4

ADE: 94.65. Result ID: 69d8b46f47f34ce924c185bc.

[Reporting paper](<https://www.sota2.com/research/paper/69d883fe7d0172140ec779c7.md>)

Recorded evaluation configuration: {"Method Family":"Proprietary"}. This record does not assert independent reproduction.

### o3

ADE: 112.14. Result ID: 69d8b46f47f34ce924c185bd.

[Reporting paper](<https://www.sota2.com/research/paper/69d883fe7d0172140ec779c7.md>)

Recorded evaluation configuration: {"Method Family":"Proprietary"}. This record does not assert independent reproduction.

### InternVL3-14B

ADE: 123.33. Result ID: 69d8b46f47f34ce924c185c2.

[Reporting paper](<https://www.sota2.com/research/paper/69d883fe7d0172140ec779c7.md>)

Recorded evaluation configuration: {"Method Family":"Open-source"}. This record does not assert independent reproduction.

### Qwen3-VL-4B

ADE: 140.42. Result ID: 69d8b46f47f34ce924c185bf.

[Reporting paper](<https://www.sota2.com/research/paper/69d883fe7d0172140ec779c7.md>)

Recorded evaluation configuration: {"Method Family":"Open-source"}. This record does not assert independent reproduction.

### Qwen3-VL-32B

ADE: 151.21. Result ID: 69d8b46f47f34ce924c185c1.

[Reporting paper](<https://www.sota2.com/research/paper/69d883fe7d0172140ec779c7.md>)

Recorded evaluation configuration: {"Method Family":"Open-source"}. This record does not assert independent reproduction.

### MindJourney

ADE: 152.41. Result ID: 69d8b46f47f34ce924c185c3.

[Reporting paper](<https://www.sota2.com/research/paper/69d883fe7d0172140ec779c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a0a1e209131cea80bbb.md>)

Recorded evaluation configuration: {"Method Family":"World-model augmented","Configuration":"o-series reasoning model with SVC"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

ADE: 183.93. Result ID: 69d8b46f47f34ce924c185c0.

[Reporting paper](<https://www.sota2.com/research/paper/69d883fe7d0172140ec779c7.md>)

Recorded evaluation configuration: {"Method Family":"Open-source"}. This record does not assert independent reproduction.

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