Numeric Planning on IPC Numeric & Custom Planning Domains 2023 (Evaluation set)
20Block Grouping ScoreENHSP-20 Portfolio
Evaluation Results
| Method | Links | |||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ENHSP-20 PortfolioConfiguration=P(3h||3n)‡2025.01 | 20 | — | 20 | 18 | 20 | 6 | 20 | 15 | 20 | 3 | 20 | 20 | 13 | 20 | 14 | 20 | 8 | 20 | 18 | — | — | 295 | — | |
| UNTILSUCCESS GPT 4.1Strategy=UNTILSUCCESS, Backbone=GPT 4.1, Search=GBFS2025.01 | 19 | — | 10 | 20 | 16 | 3 | 19 | 4 | 20 | 20 | 12 | 20 | 1 | 20 | 4 | 20 | 1 | 16 | 20 | 18 | 9 | 245 | 272 | |
| SELFPORTFOLIO-10 GPT 4.1Strategy=SELFPORTFOLIO-10, Backbone=GPT 4.1, Search=GBFS2025.01 | 19 | — | 10 | 20 | 16 | 3 | 19 | 4 | 20 | 20 | 12 | 20 | 1 | 20 | 4 | 20 | 3 | 16 | 20 | 18 | 16 | 247 | 281 | |
| ENHSP-20Configuration=⟨B, QB⟩2025.01 | 18 | — | 11 | 12 | 15 | 6 | 20 | 15 | 20 | 1 | 20 | 20 | 2 | 19 | 6 | 17 | 0 | 4 | 11 | — | — | 217 | — | |
| UNTILSUCCESS Claude Sonnet 4.5†Strategy=UNTILSUCCESS, Backbone=Claude Sonnet 4.5, Reasoning=true, Search=GBFS2025.01 | 18 | — | 5 | 20 | 17 | 4 | 20 | 6 | 20 | 18 | 8 | 20 | 1 | 20 | 4 | 19 | 3 | 2 | 17 | 17 | 16 | 222 | 255 | |
| SELFPORTFOLIO-10 GPT 5.1†Strategy=SELFPORTFOLIO-10, Backbone=GPT 5.1, Reasoning=true, Search=GBFS2025.01 | 18 | — | 10 | 17 | 16 | 3 | 20 | 6 | 20 | 20 | 20 | 1 | 1 | 20 | 4 | 20 | 1 | 4 | 20 | 20 | 16 | 220 | 256 | |
| SELFPORTFOLIO-10 Claude Sonnet 4.5†Strategy=SELFPORTFOLIO-10, Backbone=Claude Sonnet 4.5, Reasoning=true, Search=GBFS2025.01 | 18 | — | 5 | 20 | 20 | 4 | 20 | 6 | 20 | 18 | 8 | 20 | 1 | 20 | 4 | 19 | 3 | 2 | 17 | 17 | 16 | 225 | 258 | |
| UNTILSUCCESS GPT 5.1†Strategy=UNTILSUCCESS, Backbone=GPT 5.1, Reasoning=true, Search=GBFS2025.01 | 17 | — | 10 | 16 | 16 | 3 | 20 | 6 | 20 | 20 | 12 | 1 | 1 | 20 | 4 | 20 | 1 | 4 | 20 | 17 | 14 | 211 | 242 | |
| FIRSTCOMPILATION GPT 4.1Strategy=FIRSTCOMPILATION, Backbone=GPT 4.1, Search=GBFS2025.01 | 16 | — | 10 | 16 | 15 | 3 | 18 | 4 | 20 | 20 | 8 | 20 | 0 | 9 | 3 | 11 | 1 | 13 | 20 | 18 | 9 | 207 | 234 | |
| Baseline Rust h_add_mdHeuristic=h_add_md, Search=GBFS2025.01 | 15 | — | 13 | 17 | 20 | 3 | 20 | 9 | 20 | 0 | 4 | 17 | 0 | 20 | 10 | 0 | 0 | 20 | 14 | — | — | 202 | — | |
| FIRSTCOMPILATION Claude Sonnet 4.5†Strategy=FIRSTCOMPILATION, Backbone=Claude Sonnet 4.5, Reasoning=true, Search=GBFS2025.01 | 15 | — | 5 | 16 | 16 | 2 | 20 | 6 | 20 | 11 | 8 | 0 | 0 | 6 | 4 | 19 | 3 | 0 | 14 | 17 | 10 | 165 | 192 | |
| FIRSTCOMPILATION GPT 5.1†Strategy=FIRSTCOMPILATION, Backbone=GPT 5.1, Reasoning=true, Search=GBFS2025.01 | 11 | — | 10 | 16 | 16 | 3 | 20 | 5 | 17 | 0 | 6 | 0 | 0 | 10 | 4 | 19 | 1 | 0 | 20 | 17 | 13 | 158 | 188 | |
| Baseline Rust h_mdHeuristic=h_md, Search=GBFS2025.01 | 9 | — | 10 | 9 | 16 | 5 | 20 | 7 | 20 | 0 | 4 | 7 | 1 | 1 | 4 | 0 | 1 | 16 | 11 | 20 | 14 | 141 | 175 | |
| MFFHeuristic=hFF, Search=EHCS2025.01 | 2 | — | 15 | 20 | 16 | 5 | 9 | 20 | 16 | 11 | 1 | 0 | 13 | 13 | 10 | 2 | 6 | 4 | 0 | — | — | 163 | — | |
| Baseline Rust BFSSearch=BFS2025.01 | 0 | — | 3 | 1 | 3 | 3 | 3 | 3 | 3 | 0 | 8 | 0 | 0 | 0 | 2 | 0 | 0 | 1 | 4 | 4 | 1 | 34 | 39 | |
| NFDHeuristic=hLMC, Search=GBFS2025.01 | 0 | — | 12 | 9 | 16 | 5 | 15 | 6 | 11 | 16 | 6 | 0 | 2 | 20 | 4 | 10 | 0 | 2 | 10 | — | — | 144 | — |