# Maze Navigation on Maze (Standard) Source: [Maze Navigation on Maze (Standard)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:49.193Z Evaluation of agent performance in navigating the standard configuration of the Maze environment, typically measured by accuracy or success rate. 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 | Maze Navigation | | Dataset (including any stated split) | Maze (Standard) | | Metric | Accuracy | | Unit | PERCENT | | 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: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | GPT-5 | 0.9961 | Not recorded | 692d2147d6b0dd3342931901 | | OpenAI o3 | 0.957 | Not recorded | 692d2147d6b0dd3342931901 | | Claude 4.5 Sonnet | 0.9414 | Not recorded | 692d2147d6b0dd3342931901 | | OpenAI o4-mini | 0.9375 | Not recorded | 692d2147d6b0dd3342931901 | | WMAct | 0.8814 | Not recorded | 692d2147d6b0dd3342931901 | | PPO - Interactive | 0.8374 | Not recorded | 692d2147d6b0dd3342931901 | | Gemini 2.5 Pro | 0.8359 | Not recorded | 692d2147d6b0dd3342931901 | | PPO - EntirePlan | 0.7504 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen3-14B | 0.7227 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen3-8B | 0.6367 | Not recorded | 692d2147d6b0dd3342931901 | | GPT-4o | 0.0469 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen3-8B-Own | 0.0195 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen2.5-32B-Instruct | 0.0068 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen2.5-7B-Instruct | 0 | Not recorded | 692d2147d6b0dd3342931901 | ### GPT-5 Accuracy: 0.9961. Result ID: 699635875698665ec477e7b1. [Reporting paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### OpenAI o3 Accuracy: 0.957. Result ID: 699635875698665ec477e7b2. [Reporting paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### Claude 4.5 Sonnet Accuracy: 0.9414. Result ID: 699635875698665ec477e7b5. [Reporting paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### OpenAI o4-mini Accuracy: 0.9375. Result ID: 699635875698665ec477e7b3. [Reporting paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### WMAct Accuracy: 0.8814. Result ID: 699635875698665ec477e7bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PPO - Interactive Accuracy: 0.8374. Result ID: 699635875698665ec477e7bc. [Reporting paper]() Recorded evaluation configuration: {"mode":"interactive"}. This record does not assert independent reproduction. ### Gemini 2.5 Pro Accuracy: 0.8359. Result ID: 699635875698665ec477e7b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### PPO - EntirePlan Accuracy: 0.7504. Result ID: 699635875698665ec477e7bb. [Reporting paper]() Recorded evaluation configuration: {"mode":"single-turn output"}. This record does not assert independent reproduction. ### Qwen3-14B Accuracy: 0.7227. Result ID: 699635875698665ec477e7b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Opensource Models"}. This record does not assert independent reproduction. ### Qwen3-8B Accuracy: 0.6367. Result ID: 699635875698665ec477e7b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Opensource Models"}. This record does not assert independent reproduction. ### GPT-4o Accuracy: 0.0469. Result ID: 699635875698665ec477e7b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### Qwen3-8B-Own Accuracy: 0.0195. Result ID: 699635875698665ec477e7ba. [Reporting paper]() Recorded evaluation configuration: {"backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Qwen2.5-32B-Instruct Accuracy: 0.0068. Result ID: 699635875698665ec477e7b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Opensource Models"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Accuracy: 0. Result ID: 699635875698665ec477e7b6. [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.