# Puzzle Solving on Sudoku Out Of Distribution Source: [Puzzle Solving on Sudoku Out Of Distribution]() Collection index: [llms.txt]() Data updated: 2026-03-23T11:44:27.121Z Evaluation of model performance on solving Sudoku puzzles drawn from the 'Out Of Distribution' set, measured using Avg@128 and Pass@128 metrics. 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 | Puzzle Solving | | Dataset (including any stated split) | Sudoku Out Of Distribution | | Metric | Average @128 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Average @128](): Higher is better; unit: PERCENT. - [Pass Rate @128](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average @128 | Result date | Report paper | | --- | --- | --- | --- | | Markov | 77.8 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | State-action-sequence | 71.2 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Action-sequence | 69.2 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | State-action-sequence | 57.1 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Markov | 56.4 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Markov | 8.7 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Action-sequence | 3.1 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Markov | 2.9 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | State-action-sequence | 2.4 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | State-action-sequence | 1.9 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Action-sequence | 0 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Action-sequence | 0 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | ### Markov Average @128: 77.8. Result ID: 69c1272247f34ce924a9b3f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Training Stage":"RL post-training"}. This record does not assert independent reproduction. ### State-action-sequence Average @128: 71.2. Result ID: 69c1272247f34ce924a9b3f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Training Stage":"RL post-training"}. This record does not assert independent reproduction. ### Action-sequence Average @128: 69.2. Result ID: 69c1272247f34ce924a9b3f5. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Training Stage":"RL post-training"}. This record does not assert independent reproduction. ### State-action-sequence Average @128: 57.1. Result ID: 69c1272247f34ce924a9b3ff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-3B-It","Training Stage":"RL post-training"}. This record does not assert independent reproduction. ### Markov Average @128: 56.4. Result ID: 69c1272247f34ce924a9b3fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-3B-It","Training Stage":"RL post-training"}. This record does not assert independent reproduction. ### Markov Average @128: 8.7. Result ID: 69c1272247f34ce924a9b3f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Training Stage":"SFT Warm-up"}. This record does not assert independent reproduction. ### Action-sequence Average @128: 3.1. Result ID: 69c1272247f34ce924a9b3f4. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Training Stage":"SFT Warm-up"}. This record does not assert independent reproduction. ### Markov Average @128: 2.9. Result ID: 69c1272247f34ce924a9b3fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-3B-It","Training Stage":"SFT Warm-up"}. This record does not assert independent reproduction. ### State-action-sequence Average @128: 2.4. Result ID: 69c1272247f34ce924a9b3fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-3B-It","Training Stage":"SFT Warm-up"}. This record does not assert independent reproduction. ### State-action-sequence Average @128: 1.9. Result ID: 69c1272247f34ce924a9b3f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Training Stage":"SFT Warm-up"}. This record does not assert independent reproduction. ### Action-sequence Average @128: 0. Result ID: 69c1272247f34ce924a9b3fa. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-3B-It","Training Stage":"SFT Warm-up"}. This record does not assert independent reproduction. ### Action-sequence Average @128: 0. Result ID: 69c1272247f34ce924a9b3fb. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-3B-It","Training Stage":"RL post-training"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.