# Ball Tracking on Ball Tracking Source: [Ball Tracking on Ball Tracking]() Collection index: [llms.txt]() Data updated: 2026-06-12T07:14:05.217Z Evaluation of ball tracking performance on the Ball Tracking dataset, reporting 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 | Ball Tracking | | Dataset (including any stated split) | Ball Tracking | | 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 | | --- | --- | --- | --- | | Gemini-2.5-Pro | 28.3 | Not recorded | 6a2b92b3d33dfb23e783b109 | | GPT-5 | 25.9 | Not recorded | 6a2b92b3d33dfb23e783b109 | | Gemini-2.5-Flash | 22.7 | Not recorded | 6a2b92b3d33dfb23e783b109 | | Qwen3-235B | 20.9 | Not recorded | 6a2b92b3d33dfb23e783b109 | | Qwen3-32B | 20.3 | Not recorded | 6a2b92b3d33dfb23e783b109 | | w/o Tool | 19.6 | Not recorded | 6a2b92b3d33dfb23e783b109 | | Qwen3-30B | 19.5 | Not recorded | 6a2b92b3d33dfb23e783b109 | | PERIA-8B | 18.8 | Not recorded | 6a2b92b3d33dfb23e783b109 | | w/o RL | 18.1 | Not recorded | 6a2b92b3d33dfb23e783b109 | | VTool-R1-7B | 18 | Not recorded | 6a2b92b3d33dfb23e783b109 | | InternVL3.5-8B | 17.9 | Not recorded | 6a2b92b3d33dfb23e783b109 | | Qwen3-8B | 17.8 | Not recorded | 6a2b92b3d33dfb23e783b109 | | Mini-o3 | 16.8 | Not recorded | 6a2b92b3d33dfb23e783b109 | | InternVL3.5-14B | 16.2 | Not recorded | 6a2b92b3d33dfb23e783b109 | | R1-OneVision-7B | 15.7 | Not recorded | 6a2b92b3d33dfb23e783b109 | | w/o SFT | 12.4 | Not recorded | 6a2b92b3d33dfb23e783b109 | ### Gemini-2.5-Pro Accuracy: 28.3. Result ID: 6a2bb1b3fbc373592c299ac3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Commercial"}. This record does not assert independent reproduction. ### GPT-5 Accuracy: 25.9. Result ID: 6a2bb1b3fbc373592c299ac1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Commercial"}. This record does not assert independent reproduction. ### Gemini-2.5-Flash Accuracy: 22.7. Result ID: 6a2bb1b3fbc373592c299ac2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Commercial"}. This record does not assert independent reproduction. ### Qwen3-235B Accuracy: 20.9. Result ID: 6a2bb1b3fbc373592c299acb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-Source"}. This record does not assert independent reproduction. ### Qwen3-32B Accuracy: 20.3. Result ID: 6a2bb1b3fbc373592c299aca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-Source"}. This record does not assert independent reproduction. ### w/o Tool Accuracy: 19.6. Result ID: 6a2bb1b3fbc373592c299ad0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Ablation"}. This record does not assert independent reproduction. ### Qwen3-30B Accuracy: 19.5. Result ID: 6a2bb1b3fbc373592c299ac9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-Source"}. This record does not assert independent reproduction. ### PERIA-8B Accuracy: 18.8. Result ID: 6a2bb1b3fbc373592c299acd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Proposed"}. This record does not assert independent reproduction. ### w/o RL Accuracy: 18.1. Result ID: 6a2bb1b3fbc373592c299ace. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Ablation"}. This record does not assert independent reproduction. ### VTool-R1-7B Accuracy: 18. Result ID: 6a2bb1b3fbc373592c299ac5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Tool-Augmented"}. This record does not assert independent reproduction. ### InternVL3.5-8B Accuracy: 17.9. Result ID: 6a2bb1b3fbc373592c299ac4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-Source"}. This record does not assert independent reproduction. ### Qwen3-8B Accuracy: 17.8. Result ID: 6a2bb1b3fbc373592c299acc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Backbone Baseline"}. This record does not assert independent reproduction. ### Mini-o3 Accuracy: 16.8. Result ID: 6a2bb1b3fbc373592c299ac7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Tool-Augmented"}. This record does not assert independent reproduction. ### InternVL3.5-14B Accuracy: 16.2. Result ID: 6a2bb1b3fbc373592c299ac8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Open-Source"}. This record does not assert independent reproduction. ### R1-OneVision-7B Accuracy: 15.7. Result ID: 6a2bb1b3fbc373592c299ac6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Tool-Augmented"}. This record does not assert independent reproduction. ### w/o SFT Accuracy: 12.4. Result ID: 6a2bb1b3fbc373592c299acf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Type":"Ablation"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.