# Sokoban on Sokoban (Standard) Source: [Sokoban on Sokoban (Standard)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:49.144Z Evaluation of model performance on the standard Sokoban environment, measured by Accuracy. 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 | Sokoban | | Dataset (including any stated split) | Sokoban (Standard) | | Metric | Accuracy | | Unit | SCALAR | | Direction | Higher 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 - [Accuracy](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | OpenAI o3 | 98.83 | Not recorded | 692d2147d6b0dd3342931901 | | GPT-5 | 96.88 | Not recorded | 692d2147d6b0dd3342931901 | | OpenAI o4-mini | 83.2 | Not recorded | 692d2147d6b0dd3342931901 | | WMAct | 78.57 | Not recorded | 692d2147d6b0dd3342931901 | | PPO - Interactive | 64.21 | Not recorded | 692d2147d6b0dd3342931901 | | Claude 4.5 Sonnet | 60.94 | Not recorded | 692d2147d6b0dd3342931901 | | PPO - EntirePlan | 49.12 | Not recorded | 692d2147d6b0dd3342931901 | | Gemini 2.5 Pro | 36.72 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen3-14B | 18.75 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen3-8B | 16.41 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen3-8B-Own | 3.29 | Not recorded | 692d2147d6b0dd3342931901 | | GPT-4o | 1.95 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen2.5-7B-Instruct | 0 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen2.5-32B-Instruct | 0 | Not recorded | 692d2147d6b0dd3342931901 | ### OpenAI o3 Accuracy: 98.83. Result ID: 699635875698665ec477e788. [Reporting paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### GPT-5 Accuracy: 96.88. Result ID: 699635875698665ec477e787. [Reporting paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### OpenAI o4-mini Accuracy: 83.2. Result ID: 699635875698665ec477e789. [Reporting paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### WMAct Accuracy: 78.57. Result ID: 699635875698665ec477e793. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PPO - Interactive Accuracy: 64.21. Result ID: 699635875698665ec477e792. [Reporting paper]() Recorded evaluation configuration: {"mode":"interactive"}. This record does not assert independent reproduction. ### Claude 4.5 Sonnet Accuracy: 60.94. Result ID: 699635875698665ec477e78b. [Reporting paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### PPO - EntirePlan Accuracy: 49.12. Result ID: 699635875698665ec477e791. [Reporting paper]() Recorded evaluation configuration: {"mode":"single-turn output"}. This record does not assert independent reproduction. ### Gemini 2.5 Pro Accuracy: 36.72. Result ID: 699635875698665ec477e78a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### Qwen3-14B Accuracy: 18.75. Result ID: 699635875698665ec477e78f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Opensource Models"}. This record does not assert independent reproduction. ### Qwen3-8B Accuracy: 16.41. Result ID: 699635875698665ec477e78e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Opensource Models"}. This record does not assert independent reproduction. ### Qwen3-8B-Own Accuracy: 3.29. Result ID: 699635875698665ec477e790. [Reporting paper]() Recorded evaluation configuration: {"backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### GPT-4o Accuracy: 1.95. Result ID: 699635875698665ec477e786. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Accuracy: 0. Result ID: 699635875698665ec477e78c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Opensource Models"}. This record does not assert independent reproduction. ### Qwen2.5-32B-Instruct Accuracy: 0. Result ID: 699635875698665ec477e78d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Opensource Models"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.