# Numeric Planning on IPC Numeric & Custom Planning Domains 2023 (Evaluation set)

Source: [Numeric Planning on IPC Numeric & Custom Planning Domains 2023 (Evaluation set)](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set>)

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

Data updated: 2026-07-09T06:39:41.576Z

Evaluation of Numeric Planning performance on the specific 2023 evaluation set, reporting scores across various specialized domains like Block Grouping, Counters, and Drone tasks.

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 | Numeric Planning |
| Dataset (including any stated split) | IPC Numeric & Custom Planning Domains 2023 (Evaluation set) |
| Metric | Block Grouping Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [Block Grouping Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Block%20Grouping%20Score>): Higher is better; unit: SCALAR.

- [Overall Coverage](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Overall%20Coverage>): Higher is better; unit: SCALAR.

- [Counters Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Counters%20Score>): Higher is better; unit: SCALAR.

- [Delivery Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Delivery%20Score>): Higher is better; unit: SCALAR.

- [Drone Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Drone%20Score>): Higher is better; unit: SCALAR.

- [Expedition Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Expedition%20Score>): Higher is better; unit: SCALAR.

- [Farming Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Farming%20Score>): Higher is better; unit: SCALAR.

- [FO-Counters Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=FO-Counters%20Score>): Higher is better; unit: SCALAR.

- [FO-Farming Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=FO-Farming%20Score>): Higher is better; unit: SCALAR.

- [FO-Sailing Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=FO-Sailing%20Score>): Higher is better; unit: SCALAR.

- [Hydropower Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Hydropower%20Score>): Higher is better; unit: SCALAR.

- [Market Trader Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Market%20Trader%20Score>): Higher is better; unit: SCALAR.

- [Pathways Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Pathways%20Score>): Higher is better; unit: SCALAR.

- [Plant Watering Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Plant%20Watering%20Score>): Higher is better; unit: SCALAR.

- [Rover Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Rover%20Score>): Higher is better; unit: SCALAR.

- [Sailing Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Sailing%20Score>): Higher is better; unit: SCALAR.

- [Settlers Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Settlers%20Score>): Higher is better; unit: SCALAR.

- [TPP Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=TPP%20Score>): Higher is better; unit: SCALAR.

- [Zenotravel Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Zenotravel%20Score>): Higher is better; unit: SCALAR.

- [Twin Prime Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Twin%20Prime%20Score>): Higher is better; unit: SCALAR.

- [Pacman Score](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Pacman%20Score>): Higher is better; unit: SCALAR.

- [Total Coverage (Sum 360)](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Total%20Coverage%20(Sum%20360)>): Higher is better; unit: SCALAR.

- [Total Coverage (Sum 400)](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md?metric=Total%20Coverage%20(Sum%20400)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Block Grouping Score | Result date | Report paper |
| --- | --- | --- | --- |
| ENHSP-20 Portfolio | 20 | Not recorded | 68fa7a601e209131cea82b60 |
| UNTILSUCCESS GPT 4.1 | 19 | Not recorded | 68fa7a601e209131cea82b60 |
| SELFPORTFOLIO-10 GPT 4.1 | 19 | Not recorded | 68fa7a601e209131cea82b60 |
| ENHSP-20 | 18 | Not recorded | 68fa7a601e209131cea82b60 |
| UNTILSUCCESS Claude Sonnet 4.5† | 18 | Not recorded | 68fa7a601e209131cea82b60 |
| SELFPORTFOLIO-10 GPT 5.1† | 18 | Not recorded | 68fa7a601e209131cea82b60 |
| SELFPORTFOLIO-10 Claude Sonnet 4.5† | 18 | Not recorded | 68fa7a601e209131cea82b60 |
| UNTILSUCCESS GPT 5.1† | 17 | Not recorded | 68fa7a601e209131cea82b60 |
| FIRSTCOMPILATION GPT 4.1 | 16 | Not recorded | 68fa7a601e209131cea82b60 |
| Baseline Rust h\_add\_md | 15 | Not recorded | 68fa7a601e209131cea82b60 |
| FIRSTCOMPILATION Claude Sonnet 4.5† | 15 | Not recorded | 68fa7a601e209131cea82b60 |
| FIRSTCOMPILATION GPT 5.1† | 11 | Not recorded | 68fa7a601e209131cea82b60 |
| Baseline Rust h\_md | 9 | Not recorded | 68fa7a601e209131cea82b60 |
| MFF | 2 | Not recorded | 68fa7a601e209131cea82b60 |
| Baseline Rust BFS | 0 | Not recorded | 68fa7a601e209131cea82b60 |
| NFD | 0 | Not recorded | 68fa7a601e209131cea82b60 |

### ENHSP-20 Portfolio

Block Grouping Score: 20. Result ID: 6a4f421f60b88bb339e421e2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756e1e209131cea67dbc.md>)

Recorded evaluation configuration: {"Configuration":"P(3h\|\|3n)‡"}. This record does not assert independent reproduction.

### UNTILSUCCESS GPT 4.1

Block Grouping Score: 19. Result ID: 6a4f421f60b88bb339e421e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

Recorded evaluation configuration: {"Strategy":"UNTILSUCCESS","Backbone":"GPT 4.1","Search":"GBFS"}. This record does not assert independent reproduction.

### SELFPORTFOLIO-10 GPT 4.1

Block Grouping Score: 19. Result ID: 6a4f421f60b88bb339e421eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

Recorded evaluation configuration: {"Strategy":"SELFPORTFOLIO-10","Backbone":"GPT 4.1","Search":"GBFS"}. This record does not assert independent reproduction.

### ENHSP-20

Block Grouping Score: 18. Result ID: 6a4f421f60b88bb339e421e1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756e1e209131cea67dbc.md>)

Recorded evaluation configuration: {"Configuration":"⟨B, QB⟩"}. This record does not assert independent reproduction.

### UNTILSUCCESS Claude Sonnet 4.5†

Block Grouping Score: 18. Result ID: 6a4f421f60b88bb339e421ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

Recorded evaluation configuration: {"Strategy":"UNTILSUCCESS","Backbone":"Claude Sonnet 4.5","Reasoning":"true","Search":"GBFS"}. This record does not assert independent reproduction.

### SELFPORTFOLIO-10 GPT 5.1†

Block Grouping Score: 18. Result ID: 6a4f421f60b88bb339e421ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

Recorded evaluation configuration: {"Strategy":"SELFPORTFOLIO-10","Backbone":"GPT 5.1","Reasoning":"true","Search":"GBFS"}. This record does not assert independent reproduction.

### SELFPORTFOLIO-10 Claude Sonnet 4.5†

Block Grouping Score: 18. Result ID: 6a4f421f60b88bb339e421ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

Recorded evaluation configuration: {"Strategy":"SELFPORTFOLIO-10","Backbone":"Claude Sonnet 4.5","Reasoning":"true","Search":"GBFS"}. This record does not assert independent reproduction.

### UNTILSUCCESS GPT 5.1†

Block Grouping Score: 17. Result ID: 6a4f421f60b88bb339e421e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

Recorded evaluation configuration: {"Strategy":"UNTILSUCCESS","Backbone":"GPT 5.1","Reasoning":"true","Search":"GBFS"}. This record does not assert independent reproduction.

### FIRSTCOMPILATION GPT 4.1

Block Grouping Score: 16. Result ID: 6a4f421f60b88bb339e421e5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

Recorded evaluation configuration: {"Strategy":"FIRSTCOMPILATION","Backbone":"GPT 4.1","Search":"GBFS"}. This record does not assert independent reproduction.

### Baseline Rust h\_add\_md

Block Grouping Score: 15. Result ID: 6a4f421f60b88bb339e421e0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756e1e209131cea67dbc.md>)

Recorded evaluation configuration: {"Heuristic":"h\_add\_md","Search":"GBFS"}. This record does not assert independent reproduction.

### FIRSTCOMPILATION Claude Sonnet 4.5†

Block Grouping Score: 15. Result ID: 6a4f421f60b88bb339e421e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

Recorded evaluation configuration: {"Strategy":"FIRSTCOMPILATION","Backbone":"Claude Sonnet 4.5","Reasoning":"true","Search":"GBFS"}. This record does not assert independent reproduction.

### FIRSTCOMPILATION GPT 5.1†

Block Grouping Score: 11. Result ID: 6a4f421f60b88bb339e421e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

Recorded evaluation configuration: {"Strategy":"FIRSTCOMPILATION","Backbone":"GPT 5.1","Reasoning":"true","Search":"GBFS"}. This record does not assert independent reproduction.

### Baseline Rust h\_md

Block Grouping Score: 9. Result ID: 6a4f421f60b88bb339e421df.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756e1e209131cea67dbc.md>)

Recorded evaluation configuration: {"Heuristic":"h\_md","Search":"GBFS"}. This record does not assert independent reproduction.

### MFF

Block Grouping Score: 2. Result ID: 6a4f421f60b88bb339e421e4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa60511e209131ce9ee9b1.md>)

Recorded evaluation configuration: {"Heuristic":"hFF","Search":"EHCS"}. This record does not assert independent reproduction.

### Baseline Rust BFS

Block Grouping Score: 0. Result ID: 6a4f421f60b88bb339e421de.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

Recorded evaluation configuration: {"Search":"BFS"}. This record does not assert independent reproduction.

### NFD

Block Grouping Score: 0. Result ID: 6a4f421f60b88bb339e421e3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60.md>)

Recorded evaluation configuration: {"Heuristic":"hLMC","Search":"GBFS"}. This record does not assert independent reproduction.

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