# Human-Centric Referring Expression Comprehension (HC-REC) on HC-RefLoCo (test) Source: [Human-Centric Referring Expression Comprehension (HC-REC) on HC-RefLoCo (test)]() Collection index: [llms.txt]() Data updated: 2026-03-13T08:28:28.721Z Evaluation of Human-Centric Referring Expression Comprehension (HC-REC) performance on the test split of the HC-RefLoCo dataset. 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 | Human-Centric Referring Expression Comprehension (HC-REC) | | Dataset (including any stated split) | HC-RefLoCo (test) | | Metric | Accuracy@0.5 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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@0.5](): Higher is better; unit: PERCENT. - [Mean Accuracy](): Higher is better; unit: PERCENT. - [Mean Accuracy Rank](): Lower is better; unit: SCALAR. - [CR Score](): Higher is better; unit: PERCENT. - [CR Rank](): Lower is better; unit: SCALAR. - [AccuracyE@0.5](): Higher is better; unit: PERCENT. - [Mean AccuracyE](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy@0.5 | Result date | Report paper | | --- | --- | --- | --- | | Qwen3.0-VL-8B | 94.18 | Not recorded | 69b399f90636e5bf4afbc9ee | | InternVL3.5-8B | 88.66 | Not recorded | 69b399f90636e5bf4afbc9ee | | Qwen2.0-VL-7B | 84.51 | Not recorded | 69b399f90636e5bf4afbc9ee | | InternVL2.0-8B | 75.34 | Not recorded | 69b399f90636e5bf4afbc9ee | | Qwen2.5-VL-7B | 75.22 | Not recorded | 69b399f90636e5bf4afbc9ee | | InternVL3.0-8B | 67.42 | Not recorded | 69b399f90636e5bf4afbc9ee | | InternVL2.5-8B | 49.7 | Not recorded | 69b399f90636e5bf4afbc9ee | | QwenVL-7B-Chat | 33.14 | Not recorded | 69b399f90636e5bf4afbc9ee | | LLaVA-1.5-13B | 19.57 | Not recorded | 69b399f90636e5bf4afbc9ee | | Gemma-3-12B | 9.2 | Not recorded | 69b399f90636e5bf4afbc9ee | | LLaVA-1.6-13B | 6.21 | Not recorded | 69b399f90636e5bf4afbc9ee | ### Qwen3.0-VL-8B Accuracy@0.5: 94.18. Result ID: 69b3c9d247f34ce9249dcd44. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### InternVL3.5-8B Accuracy@0.5: 88.66. Result ID: 69b3c9d247f34ce9249dcd3e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### Qwen2.0-VL-7B Accuracy@0.5: 84.51. Result ID: 69b3c9d247f34ce9249dcd42. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### InternVL2.0-8B Accuracy@0.5: 75.34. Result ID: 69b3c9d247f34ce9249dcd3b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Accuracy@0.5: 75.22. Result ID: 69b3c9d247f34ce9249dcd43. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### InternVL3.0-8B Accuracy@0.5: 67.42. Result ID: 69b3c9d247f34ce9249dcd3d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### InternVL2.5-8B Accuracy@0.5: 49.7. Result ID: 69b3c9d247f34ce9249dcd3c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### QwenVL-7B-Chat Accuracy@0.5: 33.14. Result ID: 69b3c9d247f34ce9249dcd41. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### LLaVA-1.5-13B Accuracy@0.5: 19.57. Result ID: 69b3c9d247f34ce9249dcd3f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"13B"}. This record does not assert independent reproduction. ### Gemma-3-12B Accuracy@0.5: 9.2. Result ID: 69b3c9d247f34ce9249dcd3a. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"12B"}. This record does not assert independent reproduction. ### LLaVA-1.6-13B Accuracy@0.5: 6.21. Result ID: 69b3c9d247f34ce9249dcd40. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"13B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.