# Map-based Language Modeling on MAPLM Source: [Map-based Language Modeling on MAPLM]() Collection index: [llms.txt]() Data updated: 2026-03-04T21:13:01.068Z Evaluation of map-based language modeling performance on the MAPLM 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 | Map-based Language Modeling | | Dataset (including any stated split) | MAPLM | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 | | --- | --- | --- | --- | | ACE-Brain-0-8B | 77.8 | Not recorded | 69a7bc892d603e6de3e3d5bf | | MiMo-Embodied-7B | 74.5 | Not recorded | 69a7bc892d603e6de3e3d5bf | | RoboBrain2.0-7B | 31.7 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Qwen3-VL-8B-Inst. | 31.5 | Not recorded | 69a7bc892d603e6de3e3d5bf | | MiMo-VL-7B | 31 | Not recorded | 69a7bc892d603e6de3e3d5bf | | InternVL3-8B | 31 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Vlaser-8B | 29.1 | Not recorded | 69a7bc892d603e6de3e3d5bf | | GPT-4o | 26.6 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Gemini2.5-pro | 26.1 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Qwen-VL-Max | 24.8 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Qwen2.5-VL-7B-Inst. | 24.8 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Pelican-VL-7B | 24.4 | Not recorded | 69a7bc892d603e6de3e3d5bf | | VeBrain-7B | 22.9 | Not recorded | 69a7bc892d603e6de3e3d5bf | | RoboBrain2.5-8B | 22.5 | Not recorded | 69a7bc892d603e6de3e3d5bf | | Qwen3-VL-2B-Inst. | 20.5 | Not recorded | 69a7bc892d603e6de3e3d5bf | | InternVL3.5-8B | 14.2 | Not recorded | 69a7bc892d603e6de3e3d5bf | ### ACE-Brain-0-8B Accuracy: 77.8. Result ID: 69a8a0566dbb7075b951958f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Embodied Brain MLLM"}. This record does not assert independent reproduction. ### MiMo-Embodied-7B Accuracy: 74.5. Result ID: 69a8a0566dbb7075b951958d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Type":"Embodied Brain MLLM"}. This record does not assert independent reproduction. ### RoboBrain2.0-7B Accuracy: 31.7. Result ID: 69a8a0566dbb7075b9519589. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Embodied Brain MLLM"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Inst. Accuracy: 31.5. Result ID: 69a8a0566dbb7075b9519588. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source general-purpose MLLM"}. This record does not assert independent reproduction. ### MiMo-VL-7B Accuracy: 31. Result ID: 69a8a0566dbb7075b9519583. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source general-purpose MLLM"}. This record does not assert independent reproduction. ### InternVL3-8B Accuracy: 31. Result ID: 69a8a0566dbb7075b9519585. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source general-purpose MLLM"}. This record does not assert independent reproduction. ### Vlaser-8B Accuracy: 29.1. Result ID: 69a8a0566dbb7075b951958e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Type":"Embodied Brain MLLM"}. This record does not assert independent reproduction. ### GPT-4o Accuracy: 26.6. Result ID: 69a8a0566dbb7075b9519580. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Closed-source MLLM"}. This record does not assert independent reproduction. ### Gemini2.5-pro Accuracy: 26.1. Result ID: 69a8a0566dbb7075b9519581. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Closed-source MLLM"}. This record does not assert independent reproduction. ### Qwen-VL-Max Accuracy: 24.8. Result ID: 69a8a0566dbb7075b9519582. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Closed-source MLLM"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B-Inst. Accuracy: 24.8. Result ID: 69a8a0566dbb7075b9519584. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source general-purpose MLLM"}. This record does not assert independent reproduction. ### Pelican-VL-7B Accuracy: 24.4. Result ID: 69a8a0566dbb7075b951958c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Embodied Brain MLLM"}. This record does not assert independent reproduction. ### VeBrain-7B Accuracy: 22.9. Result ID: 69a8a0566dbb7075b951958b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Embodied Brain MLLM"}. This record does not assert independent reproduction. ### RoboBrain2.5-8B Accuracy: 22.5. Result ID: 69a8a0566dbb7075b951958a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Embodied Brain MLLM"}. This record does not assert independent reproduction. ### Qwen3-VL-2B-Inst. Accuracy: 20.5. Result ID: 69a8a0566dbb7075b9519587. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source general-purpose MLLM"}. This record does not assert independent reproduction. ### InternVL3.5-8B Accuracy: 14.2. Result ID: 69a8a0566dbb7075b9519586. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-source general-purpose MLLM"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.