# Taxi Domain on Taxi Standard Source: [Taxi Domain on Taxi Standard]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:49.223Z Evaluation of models performing Taxi Domain tasks on the Taxi Standard dataset, measured using 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 | Taxi Domain | | Dataset (including any stated split) | Taxi 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 | | --- | --- | --- | --- | | OpenAI o4-mini | 83.98 | Not recorded | 692d2147d6b0dd3342931901 | | OpenAI o3 | 72.66 | Not recorded | 692d2147d6b0dd3342931901 | | Claude 4.5 Sonnet | 66.41 | Not recorded | 692d2147d6b0dd3342931901 | | WMAct | 62.16 | Not recorded | 692d2147d6b0dd3342931901 | | PPO - Interactive | 39.16 | Not recorded | 692d2147d6b0dd3342931901 | | PPO - EntirePlan | 38.92 | Not recorded | 692d2147d6b0dd3342931901 | | GPT-5 | 36.72 | Not recorded | 692d2147d6b0dd3342931901 | | Gemini 2.5 Pro | 17.97 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen3-8B | 9.38 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen3-14B | 6.64 | Not recorded | 692d2147d6b0dd3342931901 | | GPT-4o | 6.25 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen3-8B-Own | 5.6 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen2.5-32B-Instruct | 2.34 | Not recorded | 692d2147d6b0dd3342931901 | | Qwen2.5-7B-Instruct | 1.17 | Not recorded | 692d2147d6b0dd3342931901 | ### OpenAI o4-mini Accuracy: 83.98. Result ID: 699635875698665ec477e7cf. [Reporting paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### OpenAI o3 Accuracy: 72.66. Result ID: 699635875698665ec477e7ce. [Reporting paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### Claude 4.5 Sonnet Accuracy: 66.41. Result ID: 699635875698665ec477e7d1. [Reporting paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### WMAct Accuracy: 62.16. Result ID: 699635875698665ec477e7d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PPO - Interactive Accuracy: 39.16. Result ID: 699635875698665ec477e7d8. [Reporting paper]() Recorded evaluation configuration: {"mode":"interactive"}. This record does not assert independent reproduction. ### PPO - EntirePlan Accuracy: 38.92. Result ID: 699635875698665ec477e7d7. [Reporting paper]() Recorded evaluation configuration: {"mode":"single-turn output"}. This record does not assert independent reproduction. ### GPT-5 Accuracy: 36.72. Result ID: 699635875698665ec477e7cd. [Reporting paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### Gemini 2.5 Pro Accuracy: 17.97. Result ID: 699635875698665ec477e7d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### Qwen3-8B Accuracy: 9.38. Result ID: 699635875698665ec477e7d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Opensource Models"}. This record does not assert independent reproduction. ### Qwen3-14B Accuracy: 6.64. Result ID: 699635875698665ec477e7d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Opensource Models"}. This record does not assert independent reproduction. ### GPT-4o Accuracy: 6.25. Result ID: 699635875698665ec477e7cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Proprietary Models"}. This record does not assert independent reproduction. ### Qwen3-8B-Own Accuracy: 5.6. Result ID: 699635875698665ec477e7d6. [Reporting paper]() Recorded evaluation configuration: {"backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Qwen2.5-32B-Instruct Accuracy: 2.34. Result ID: 699635875698665ec477e7d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"category":"Opensource Models"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Accuracy: 1.17. Result ID: 699635875698665ec477e7d2. [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.