# Puzzle Solving on Sudoku In Distribution Source: [Puzzle Solving on Sudoku In Distribution]() Collection index: [llms.txt]() Data updated: 2026-03-23T11:44:27.028Z Evaluation of model performance on solving Sudoku puzzles drawn from the 'In 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 In Distribution | | Metric | Average Score @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 Score @128](): Higher is better; unit: PERCENT. - [Pass Rate @128](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Score @128 | Result date | Report paper | | --- | --- | --- | --- | | Markov | 97.1 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Action-sequence | 93.5 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | State-action-sequence | 91.1 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Markov | 86 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | State-action-sequence | 83 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Markov | 34.2 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | State-action-sequence | 22.4 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Markov | 20 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Action-sequence | 16.1 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | State-action-sequence | 8.6 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Action-sequence | 0.3 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | | Action-sequence | 0 | Not recorded | 69c0c8ed0636e5bf4afc3aaa | ### Markov Average Score @128: 97.1. Result ID: 69c1272247f34ce924a9b3d3. [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 Score @128: 93.5. Result ID: 69c1272247f34ce924a9b3d1. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Training Stage":"RL post-training"}. This record does not assert independent reproduction. ### State-action-sequence Average Score @128: 91.1. Result ID: 69c1272247f34ce924a9b3d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Training Stage":"RL post-training"}. This record does not assert independent reproduction. ### Markov Average Score @128: 86. Result ID: 69c1272247f34ce924a9b3d9. [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. ### State-action-sequence Average Score @128: 83. Result ID: 69c1272247f34ce924a9b3db. [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 Score @128: 34.2. Result ID: 69c1272247f34ce924a9b3d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Training Stage":"SFT Warm-up"}. This record does not assert independent reproduction. ### State-action-sequence Average Score @128: 22.4. Result ID: 69c1272247f34ce924a9b3da. [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. ### Markov Average Score @128: 20. Result ID: 69c1272247f34ce924a9b3d8. [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. ### Action-sequence Average Score @128: 16.1. Result ID: 69c1272247f34ce924a9b3d0. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B","Training Stage":"SFT Warm-up"}. This record does not assert independent reproduction. ### State-action-sequence Average Score @128: 8.6. Result ID: 69c1272247f34ce924a9b3d4. [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 Score @128: 0.3. Result ID: 69c1272247f34ce924a9b3d6. [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 Score @128: 0. Result ID: 69c1272247f34ce924a9b3d7. [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.