# Traveling Salesman Problem on TSP Uniform-200

Source: [Traveling Salesman Problem on TSP Uniform-200](<https://www.sota2.com/research/sota/traveling-salesman-problem-on-tsp-uniform-200>)

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

Data updated: 2026-05-08T10:09:25.471Z

Evaluation of algorithms solving the Traveling Salesman Problem on the TSP Uniform-200 instances, reporting the performance gap relative to the optimum.

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 | Traveling Salesman Problem |
| Dataset (including any stated split) | TSP Uniform-200 |
| Metric | Performance Gap (%) |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 14 of 14 |
| 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

- [Performance Gap (%)](<https://www.sota2.com/research/sota/traveling-salesman-problem-on-tsp-uniform-200.md?metric=Performance%20Gap%20(%25)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Performance Gap (%) | Result date | Report paper |
| --- | --- | --- | --- |
| ReEvo TD & BU | 3.96 | Not recorded | 69fd6e175497b3b670c8942c |
| EoH-S | 4.12 | Not recorded | 69fd6e175497b3b670c8942c |
| EoH-S | 4.15 | Not recorded | 69fd6e175497b3b670c8942c |
| ReEvo TD & BU | 4.19 | Not recorded | 69fd6e175497b3b670c8942c |
| ReEvo TD | 4.2 | Not recorded | 69fd6e175497b3b670c8942c |
| ReEvo BU | 4.41 | Not recorded | 69fd6e175497b3b670c8942c |
| POMO | 4.65 | Not recorded | 69fd6e175497b3b670c8942c |
| ReEvo TD & BU | 6.8 | Not recorded | 69fd6e175497b3b670c8942c |
| ReEvo TD & BU | 7.27 | Not recorded | 69fd6e175497b3b670c8942c |
| EoH-S | 7.37 | Not recorded | 69fd6e175497b3b670c8942c |
| EoH-S | 7.46 | Not recorded | 69fd6e175497b3b670c8942c |
| ReEvo BU | 7.49 | Not recorded | 69fd6e175497b3b670c8942c |
| ReEvo TD | 8.57 | Not recorded | 69fd6e175497b3b670c8942c |
| DIFUSCO + LS | 9.62 | Not recorded | 69fd6e175497b3b670c8942c |

### ReEvo TD & BU

Performance Gap (%): 3.96. Result ID: 69fdb64f47f34ce924e133a8.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

Recorded evaluation configuration: {"Type":"White-Box","Variant":"Node","Setting":"Multi-task"}. This record does not assert independent reproduction.

### EoH-S

Performance Gap (%): 4.12. Result ID: 69fdb64f47f34ce924e133a7.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ac31e209131cea850fd.md>)

Recorded evaluation configuration: {"Type":"White-Box","Variant":"Node","Setting":"Multi-task"}. This record does not assert independent reproduction.

### EoH-S

Performance Gap (%): 4.15. Result ID: 69fdb64f47f34ce924e133ae.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ac31e209131cea850fd.md>)

Recorded evaluation configuration: {"Type":"Black-Box","Variant":"Node","Setting":"Multi-task"}. This record does not assert independent reproduction.

### ReEvo TD & BU

Performance Gap (%): 4.19. Result ID: 69fdb64f47f34ce924e133af.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

Recorded evaluation configuration: {"Type":"Black-Box","Variant":"Node","Setting":"Multi-task"}. This record does not assert independent reproduction.

### ReEvo TD

Performance Gap (%): 4.2. Result ID: 69fdb64f47f34ce924e133a6.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

Recorded evaluation configuration: {"Type":"White-Box","Variant":"Node","Setting":"Single-task"}. This record does not assert independent reproduction.

### ReEvo BU

Performance Gap (%): 4.41. Result ID: 69fdb64f47f34ce924e133a5.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75371e209131cea667f9.md>)

[Implementation](<https://github.com/ai4co/LLM-as-HH>)

Recorded evaluation configuration: {"Type":"White-Box","Variant":"Node","Setting":"Single-task"}. This record does not assert independent reproduction.

### POMO

Performance Gap (%): 4.65. Result ID: 69fdb64f47f34ce924e133a4.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

Recorded evaluation configuration: {"Type":"White-Box","Variant":"Node","Setting":"Single-task"}. This record does not assert independent reproduction.

### ReEvo TD & BU

Performance Gap (%): 6.8. Result ID: 69fdb64f47f34ce924e133b1.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

Recorded evaluation configuration: {"Type":"Black-Box","Variant":"Edge","Setting":"Multi-task"}. This record does not assert independent reproduction.

### ReEvo TD & BU

Performance Gap (%): 7.27. Result ID: 69fdb64f47f34ce924e133ad.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

Recorded evaluation configuration: {"Type":"White-Box","Variant":"Edge","Setting":"Multi-task"}. This record does not assert independent reproduction.

### EoH-S

Performance Gap (%): 7.37. Result ID: 69fdb64f47f34ce924e133b0.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ac31e209131cea850fd.md>)

Recorded evaluation configuration: {"Type":"Black-Box","Variant":"Edge","Setting":"Multi-task"}. This record does not assert independent reproduction.

### EoH-S

Performance Gap (%): 7.46. Result ID: 69fdb64f47f34ce924e133ac.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ac31e209131cea850fd.md>)

Recorded evaluation configuration: {"Type":"White-Box","Variant":"Edge","Setting":"Multi-task"}. This record does not assert independent reproduction.

### ReEvo BU

Performance Gap (%): 7.49. Result ID: 69fdb64f47f34ce924e133aa.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75371e209131cea667f9.md>)

[Implementation](<https://github.com/ai4co/LLM-as-HH>)

Recorded evaluation configuration: {"Type":"White-Box","Variant":"Edge","Setting":"Single-task"}. This record does not assert independent reproduction.

### ReEvo TD

Performance Gap (%): 8.57. Result ID: 69fdb64f47f34ce924e133ab.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

Recorded evaluation configuration: {"Type":"White-Box","Variant":"Edge","Setting":"Single-task"}. This record does not assert independent reproduction.

### DIFUSCO + LS

Performance Gap (%): 9.62. Result ID: 69fdb64f47f34ce924e133a9.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e175497b3b670c8942c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71551e209131cea50914.md>)

[Implementation](<https://github.com/Edward-Sun/DIFUSCO>)

Recorded evaluation configuration: {"Type":"White-Box","Variant":"Edge","Setting":"Single-task"}. This record does not assert independent reproduction.

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