# Lane Count on RoadSceneBench Source: [Lane Count on RoadSceneBench]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:47.393Z Evaluation of model performance on counting the number of lanes using the RoadSceneBench dataset, measured by Precision and Recall. 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 | Lane Count | | Dataset (including any stated split) | RoadSceneBench | | Metric | Precision (%) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Precision (%)](): Higher is better; unit: PERCENT. - [Recall (%)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Precision (%) | Result date | Report paper | | --- | --- | --- | --- | | MapVLM | 66.02 | Not recorded | 692d217bd6b0dd3342931cba | | MapVLM | 63.37 | Not recorded | 692d217bd6b0dd3342931cba | | Qwen3-VL-8B | 54.99 | Not recorded | 692d217bd6b0dd3342931cba | | InternVL3-78B | 53.42 | Not recorded | 692d217bd6b0dd3342931cba | | Gemini-2.5-pro | 52.78 | Not recorded | 692d217bd6b0dd3342931cba | | GPT-4o | 51.02 | Not recorded | 692d217bd6b0dd3342931cba | | Qwen3-VL-32B | 50.3 | Not recorded | 692d217bd6b0dd3342931cba | | LLaVA-Onevision / Next-7B | 37.75 | Not recorded | 692d217bd6b0dd3342931cba | | Qwen3-VL-2B | 36.01 | Not recorded | 692d217bd6b0dd3342931cba | | Qwen2.5-VL-32B | 33.2 | Not recorded | 692d217bd6b0dd3342931cba | | ERNIE-4.5-VL-28B-A3B | 32.25 | Not recorded | 692d217bd6b0dd3342931cba | | Qwen2.5-VL-72B | 30.23 | Not recorded | 692d217bd6b0dd3342931cba | | InternVL3-8B | 29.8 | Not recorded | 692d217bd6b0dd3342931cba | | Qwen2.5-VL-3B | 29.65 | Not recorded | 692d217bd6b0dd3342931cba | | Claude-3.7V Sonnet | 28.64 | Not recorded | 692d217bd6b0dd3342931cba | | InternVL3-1B | 22.06 | Not recorded | 692d217bd6b0dd3342931cba | | Qwen2.5-VL-7B | 12.81 | Not recorded | 692d217bd6b0dd3342931cba | | DeepSeek-VL2 | 9.8 | Not recorded | 692d217bd6b0dd3342931cba | ### MapVLM Precision (%): 66.02. Result ID: 6995e2ba3badfaffe6ea5e74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Strategy":"SFT"}. This record does not assert independent reproduction. ### MapVLM Precision (%): 63.37. Result ID: 6995e2ba3badfaffe6ea5e75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Strategy":"SFT+HRRP-T"}. This record does not assert independent reproduction. ### Qwen3-VL-8B Precision (%): 54.99. Result ID: 6995e2ba3badfaffe6ea5e72. [Reporting paper]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. ### InternVL3-78B Precision (%): 53.42. Result ID: 6995e2ba3badfaffe6ea5e6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. ### Gemini-2.5-pro Precision (%): 52.78. Result ID: 6995e2ba3badfaffe6ea5e65. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Access":"Closed-Source"}. This record does not assert independent reproduction. ### GPT-4o Precision (%): 51.02. Result ID: 6995e2ba3badfaffe6ea5e64. [Reporting paper]() Recorded evaluation configuration: {"Access":"Closed-Source"}. This record does not assert independent reproduction. ### Qwen3-VL-32B Precision (%): 50.3. Result ID: 6995e2ba3badfaffe6ea5e73. [Reporting paper]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. ### LLaVA-Onevision / Next-7B Precision (%): 37.75. Result ID: 6995e2ba3badfaffe6ea5e69. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. ### Qwen3-VL-2B Precision (%): 36.01. Result ID: 6995e2ba3badfaffe6ea5e71. [Reporting paper]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. ### Qwen2.5-VL-32B Precision (%): 33.2. Result ID: 6995e2ba3badfaffe6ea5e6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. ### ERNIE-4.5-VL-28B-A3B Precision (%): 32.25. Result ID: 6995e2ba3badfaffe6ea5e67. [Reporting paper]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. ### Qwen2.5-VL-72B Precision (%): 30.23. Result ID: 6995e2ba3badfaffe6ea5e70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. ### InternVL3-8B Precision (%): 29.8. Result ID: 6995e2ba3badfaffe6ea5e6b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. ### Qwen2.5-VL-3B Precision (%): 29.65. Result ID: 6995e2ba3badfaffe6ea5e6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. ### Claude-3.7V Sonnet Precision (%): 28.64. Result ID: 6995e2ba3badfaffe6ea5e66. [Reporting paper]() Recorded evaluation configuration: {"Access":"Closed-Source"}. This record does not assert independent reproduction. ### InternVL3-1B Precision (%): 22.06. Result ID: 6995e2ba3badfaffe6ea5e6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Precision (%): 12.81. Result ID: 6995e2ba3badfaffe6ea5e6e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. ### DeepSeek-VL2 Precision (%): 9.8. Result ID: 6995e2ba3badfaffe6ea5e68. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Access":"Open-Source"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.