# Tooth Partitioning on Dental Arch Dataset Source: [Tooth Partitioning on Dental Arch Dataset]() Collection index: [llms.txt]() Data updated: 2026-04-07T07:35:51.445Z Evaluation of tooth partitioning performance on the Dental Arch Dataset, reporting Macro-F1 and component-specific F1 scores for maxillary and mandibular regions. 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 | Tooth Partitioning | | Dataset (including any stated split) | Dental Arch Dataset | | Metric | Macro-F1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [Macro-F1](): Higher is better; unit: PERCENT. - [Maxillary Ant F1](): Higher is better; unit: PERCENT. - [Maxillary Pre F1](): Higher is better; unit: PERCENT. - [Maxillary Mol F1](): Higher is better; unit: PERCENT. - [Mandibular Ant F1](): Higher is better; unit: PERCENT. - [Mandibular Pre F1](): Higher is better; unit: PERCENT. - [Mandibular Mol F1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Macro-F1 | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-VL-235B-A22B | 78.237 | Not recorded | 691d4f1ad6b0dd334292d7d6 | | Qwen3-VL-30B-A3B | 77.463 | Not recorded | 691d4f1ad6b0dd334292d7d6 | | VLM Aggregate (4 models) | 77.183 | Not recorded | 691d4f1ad6b0dd334292d7d6 | | Qwen3-VL-235B-A22B | 77.103 | Not recorded | 691d4f1ad6b0dd334292d7d6 | | GLM-4.5V | 76.789 | Not recorded | 691d4f1ad6b0dd334292d7d6 | | Qwen3-VL-30B-A3B | 76.379 | Not recorded | 691d4f1ad6b0dd334292d7d6 | | doubao-seed-1-6 (vision) | 76.243 | Not recorded | 691d4f1ad6b0dd334292d7d6 | | VLM Aggregate (4 models) | 76.052 | Not recorded | 691d4f1ad6b0dd334292d7d6 | | GLM-4.5V | 75.684 | Not recorded | 691d4f1ad6b0dd334292d7d6 | | doubao-seed-1-6 (vision) | 75.042 | Not recorded | 691d4f1ad6b0dd334292d7d6 | | YOLOv5 | 71.582 | Not recorded | 691d4f1ad6b0dd334292d7d6 | | Prompted VLM | 69.133 | Not recorded | 691d4f1ad6b0dd334292d7d6 | | Demirjian staging pipeline | 63.422 | Not recorded | 691d4f1ad6b0dd334292d7d6 | ### Qwen3-VL-235B-A22B Macro-F1: 78.237. Result ID: 69d4b2b247f34ce924bc2495. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category(Mode)":"Thinking"}. This record does not assert independent reproduction. ### Qwen3-VL-30B-A3B Macro-F1: 77.463. Result ID: 69d4b2b247f34ce924bc2497. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category(Mode)":"Thinking"}. This record does not assert independent reproduction. ### VLM Aggregate (4 models) Macro-F1: 77.183. Result ID: 69d4b2b247f34ce924bc249d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category(Mode)":"Thinking"}. This record does not assert independent reproduction. ### Qwen3-VL-235B-A22B Macro-F1: 77.103. Result ID: 69d4b2b247f34ce924bc2496. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category(Mode)":"Non-Thinking"}. This record does not assert independent reproduction. ### GLM-4.5V Macro-F1: 76.789. Result ID: 69d4b2b247f34ce924bc2499. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category(Mode)":"Thinking"}. This record does not assert independent reproduction. ### Qwen3-VL-30B-A3B Macro-F1: 76.379. Result ID: 69d4b2b247f34ce924bc2498. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category(Mode)":"Non-Thinking"}. This record does not assert independent reproduction. ### doubao-seed-1-6 (vision) Macro-F1: 76.243. Result ID: 69d4b2b247f34ce924bc249b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category(Mode)":"Thinking"}. This record does not assert independent reproduction. ### VLM Aggregate (4 models) Macro-F1: 76.052. Result ID: 69d4b2b247f34ce924bc249e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category(Mode)":"Non-Thinking"}. This record does not assert independent reproduction. ### GLM-4.5V Macro-F1: 75.684. Result ID: 69d4b2b247f34ce924bc249a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category(Mode)":"Non-Thinking"}. This record does not assert independent reproduction. ### doubao-seed-1-6 (vision) Macro-F1: 75.042. Result ID: 69d4b2b247f34ce924bc249c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category(Mode)":"Non-Thinking"}. This record does not assert independent reproduction. ### YOLOv5 Macro-F1: 71.582. Result ID: 69d4b2b247f34ce924bc2492. [Reporting paper]() Recorded evaluation configuration: {"Category(Mode)":"Supervised Det./Seg."}. This record does not assert independent reproduction. ### Prompted VLM Macro-F1: 69.133. Result ID: 69d4b2b247f34ce924bc2494. [Reporting paper]() Recorded evaluation configuration: {"Category(Mode)":"VLM-based Reasoning"}. This record does not assert independent reproduction. ### Demirjian staging pipeline Macro-F1: 63.422. Result ID: 69d4b2b247f34ce924bc2493. [Reporting paper]() Recorded evaluation configuration: {"Category(Mode)":"Deep Stage Class."}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.