# Static Schrödinger Bridge Approximation on SB Benchmark

Source: [Static Schrödinger Bridge Approximation on SB Benchmark](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark>)

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

Data updated: 2026-03-05T07:17:25.450Z

Evaluation of models performing Static Schrödinger Bridge Approximation on the SB Benchmark, measured by the $BW^2\_2$-UVP error across various noise levels (epsilon) and dimensions (D).

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 | Static Schrödinger Bridge Approximation |
| Dataset (including any stated split) | SB Benchmark |
| Metric | $BW^2\_2$-UVP (ε=0.1, D=2) Error |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

- [$BW^2\_2$-UVP (ε=0.1, D=2) Error](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark.md?metric=%24BW%5E2_2%24-UVP%20(%CE%B5%3D0.1%2C%20D%3D2)%20Error>): Lower is better; unit: PERCENT.

- [$BW^2\_2$-UVP (ε=0.1, D=16) Error](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark.md?metric=%24BW%5E2_2%24-UVP%20(%CE%B5%3D0.1%2C%20D%3D16)%20Error>): Lower is better; unit: PERCENT.

- [$BW^2\_2$-UVP (ε=0.1, D=64) Error](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark.md?metric=%24BW%5E2_2%24-UVP%20(%CE%B5%3D0.1%2C%20D%3D64)%20Error>): Lower is better; unit: PERCENT.

- [$BW^2\_2$-UVP (ε=0.1, D=128) Error](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark.md?metric=%24BW%5E2_2%24-UVP%20(%CE%B5%3D0.1%2C%20D%3D128)%20Error>): Lower is better; unit: PERCENT.

- [$BW^2\_2$-UVP (ε=1, D=2) Error](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark.md?metric=%24BW%5E2_2%24-UVP%20(%CE%B5%3D1%2C%20D%3D2)%20Error>): Lower is better; unit: PERCENT.

- [$BW^2\_2$-UVP (ε=1, D=16) Error](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark.md?metric=%24BW%5E2_2%24-UVP%20(%CE%B5%3D1%2C%20D%3D16)%20Error>): Lower is better; unit: PERCENT.

- [$BW^2\_2$-UVP (ε=1, D=64) Error](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark.md?metric=%24BW%5E2_2%24-UVP%20(%CE%B5%3D1%2C%20D%3D64)%20Error>): Lower is better; unit: PERCENT.

- [$BW^2\_2$-UVP (ε=1, D=128) Error](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark.md?metric=%24BW%5E2_2%24-UVP%20(%CE%B5%3D1%2C%20D%3D128)%20Error>): Lower is better; unit: PERCENT.

- [$BW^2\_2$-UVP (ε=10, D=2) Error](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark.md?metric=%24BW%5E2_2%24-UVP%20(%CE%B5%3D10%2C%20D%3D2)%20Error>): Lower is better; unit: PERCENT.

- [$BW^2\_2$-UVP (ε=10, D=16) Error](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark.md?metric=%24BW%5E2_2%24-UVP%20(%CE%B5%3D10%2C%20D%3D16)%20Error>): Lower is better; unit: PERCENT.

- [$BW^2\_2$-UVP (ε=10, D=64) Error](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark.md?metric=%24BW%5E2_2%24-UVP%20(%CE%B5%3D10%2C%20D%3D64)%20Error>): Lower is better; unit: PERCENT.

- [$BW^2\_2$-UVP (ε=10, D=128) Error](<https://www.sota2.com/research/sota/static-schr-dinger-bridge-approximation-on-sb-benchmark.md?metric=%24BW%5E2_2%24-UVP%20(%CE%B5%3D10%2C%20D%3D128)%20Error>): Lower is better; unit: PERCENT.

## Recorded results

| Method | $BW^2\_2$-UVP (ε=0.1, D=2) Error | Result date | Report paper |
| --- | --- | --- | --- |
| Best algorithm on benchmark | 1.6 | Not recorded | 68fa79821e209131cea7de26 |
| ASBM-IMF | 1.6 | Not recorded | 68fa79821e209131cea7de26 |
| SF2M-Sink | 4 | Not recorded | 68fa79821e209131cea7de26 |
| ASBM-IPF | 5 | Not recorded | 68fa79821e209131cea7de26 |
| DSBM-IMF | 10 | Not recorded | 68fa79821e209131cea7de26 |
| ASBM-Identity | 12 | Not recorded | 68fa79821e209131cea7de26 |
| DSBM-Identity | 13 | Not recorded | 68fa79821e209131cea7de26 |
| DSBM-IPF | 35 | Not recorded | 68fa79821e209131cea7de26 |

### Best algorithm on benchmark

$BW^2\_2$-UVP (ε=0.1, D=2) Error: 1.6. Result ID: 69a92d136dbb7075b9521c6d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71111e209131cea4f0ae.md>)

Recorded evaluation configuration: {"Algorithm Type":"Varies"}. This record does not assert independent reproduction.

### ASBM-IMF

$BW^2\_2$-UVP (ε=0.1, D=2) Error: 1.6. Result ID: 69a92d136dbb7075b9521c71.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

Recorded evaluation configuration: {"Algorithm Type":"IPMF"}. This record does not assert independent reproduction.

### SF2M-Sink

$BW^2\_2$-UVP (ε=0.1, D=2) Error: 4. Result ID: 69a92d136dbb7075b9521c74.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71111e209131cea4f0ae.md>)

Recorded evaluation configuration: {"Algorithm Type":"Bridge Matching"}. This record does not assert independent reproduction.

### ASBM-IPF

$BW^2\_2$-UVP (ε=0.1, D=2) Error: 5. Result ID: 69a92d136dbb7075b9521c72.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

Recorded evaluation configuration: {"Algorithm Type":"IPMF"}. This record does not assert independent reproduction.

### DSBM-IMF

$BW^2\_2$-UVP (ε=0.1, D=2) Error: 10. Result ID: 69a92d136dbb7075b9521c6e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

Recorded evaluation configuration: {"Algorithm Type":"IPMF"}. This record does not assert independent reproduction.

### ASBM-Identity

$BW^2\_2$-UVP (ε=0.1, D=2) Error: 12. Result ID: 69a92d136dbb7075b9521c73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

Recorded evaluation configuration: {"Algorithm Type":"IPMF"}. This record does not assert independent reproduction.

### DSBM-Identity

$BW^2\_2$-UVP (ε=0.1, D=2) Error: 13. Result ID: 69a92d136dbb7075b9521c70.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

Recorded evaluation configuration: {"Algorithm Type":"IPMF"}. This record does not assert independent reproduction.

### DSBM-IPF

$BW^2\_2$-UVP (ε=0.1, D=2) Error: 35. Result ID: 69a92d136dbb7075b9521c6f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79821e209131cea7de26.md>)

Recorded evaluation configuration: {"Algorithm Type":"IPMF"}. This record does not assert independent reproduction.

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