# PDE Rollout Prediction on PDEBench Aggregate All time-dependent families

Source: [PDE Rollout Prediction on PDEBench Aggregate All time-dependent families](<https://www.sota2.com/research/sota/pde-rollout-prediction-on-pdebench-aggregate-all-time-dependent-families>)

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

Data updated: 2026-04-01T07:13:29.224Z

Evaluation of models performing PDE Rollout Prediction across all time-dependent families included in the PDEBench dataset, reporting performance using metrics like nRMSE, final relative error, detail generation error, and success count.

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 | PDE Rollout Prediction |
| Dataset (including any stated split) | PDEBench Aggregate All time-dependent families |
| Metric | Mean nRMSE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 7 of 7 |
| 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

- [Mean nRMSE](<https://www.sota2.com/research/sota/pde-rollout-prediction-on-pdebench-aggregate-all-time-dependent-families.md?metric=Mean%20nRMSE>): Lower is better; unit: SCALAR.

- [Mean Final Relative Error](<https://www.sota2.com/research/sota/pde-rollout-prediction-on-pdebench-aggregate-all-time-dependent-families.md?metric=Mean%20Final%20Relative%20Error>): Lower is better; unit: SCALAR.

- [Mean Detail Generation Error (T^gen)](<https://www.sota2.com/research/sota/pde-rollout-prediction-on-pdebench-aggregate-all-time-dependent-families.md?metric=Mean%20Detail%20Generation%20Error%20(T%5Egen)>): Lower is better; unit: SCALAR.

- [Success Count](<https://www.sota2.com/research/sota/pde-rollout-prediction-on-pdebench-aggregate-all-time-dependent-families.md?metric=Success%20Count>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Mean nRMSE | Result date | Report paper |
| --- | --- | --- | --- |
| DerivOpt | 0.074 | Not recorded | 69cca6840636e5bf4afcbb8d |
| ArchMulti | 0.075 | Not recorded | 69cca6840636e5bf4afcbb8d |
| LatentAE-Hyper | 0.076 | Not recorded | 69cca6840636e5bf4afcbb8d |
| DerivBase | 0.082 | Not recorded | 69cca6840636e5bf4afcbb8d |
| RolloutMulti | 0.085 | Not recorded | 69cca6840636e5bf4afcbb8d |
| BestSingleDerived | 0.088 | Not recorded | 69cca6840636e5bf4afcbb8d |
| Primitive | 0.097 | Not recorded | 69cca6840636e5bf4afcbb8d |

### DerivOpt

Mean nRMSE: 0.074. Result ID: 69ccc59047f34ce924b60888.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6840636e5bf4afcbb8d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cca6840636e5bf4afcbb8d.md>)

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

### ArchMulti

Mean nRMSE: 0.075. Result ID: 69ccc59047f34ce924b60889.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6840636e5bf4afcbb8d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f451e209131cea44aaa.md>)

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

### LatentAE-Hyper

Mean nRMSE: 0.076. Result ID: 69ccc59047f34ce924b6088a.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6840636e5bf4afcbb8d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65711e209131cea0a71a.md>)

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

### DerivBase

Mean nRMSE: 0.082. Result ID: 69ccc59047f34ce924b60887.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6840636e5bf4afcbb8d.md>)

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

### RolloutMulti

Mean nRMSE: 0.085. Result ID: 69ccc59047f34ce924b6088b.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6840636e5bf4afcbb8d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f31e209131cea4e4c0.md>)

[Implementation](<https://github.com/microsoft/pdearena>)

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

### BestSingleDerived

Mean nRMSE: 0.088. Result ID: 69ccc59047f34ce924b60886.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6840636e5bf4afcbb8d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa45e01e209131ce91c05c.md>)

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

### Primitive

Mean nRMSE: 0.097. Result ID: 69ccc59047f34ce924b60885.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6840636e5bf4afcbb8d.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.