# Affordance Grounding on HANDAL hard (test) Source: [Affordance Grounding on HANDAL hard (test)]() Collection index: [llms.txt]() Data updated: 2026-05-04T07:54:06.961Z Evaluation of Affordance Grounding performance on the test split of the HANDAL hard dataset, measured using gIoU and cIoU. 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 | Affordance Grounding | | Dataset (including any stated split) | HANDAL hard (test) | | Metric | gIoU | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [gIoU](): Higher is better; unit: PERCENT. - [cIoU](): Higher is better; unit: PERCENT. ## Recorded results | Method | gIoU | Result date | Report paper | | --- | --- | --- | --- | | A-Harness | 62.8 | Not recorded | 69f827e7c0f56ed8430888ed | | A-Harness | 60.6 | Not recorded | 69f827e7c0f56ed8430888ed | | A-Harness | 59.4 | Not recorded | 69f827e7c0f56ed8430888ed | | AffordanceVLM | 58.2 | Not recorded | 69f827e7c0f56ed8430888ed | | A-Harness | 57.9 | Not recorded | 69f827e7c0f56ed8430888ed | | A-Harness | 55.3 | Not recorded | 69f827e7c0f56ed8430888ed | | A-Harness | 55.2 | Not recorded | 69f827e7c0f56ed8430888ed | | A-Harness | 49.8 | Not recorded | 69f827e7c0f56ed8430888ed | | A-Harness | 48 | Not recorded | 69f827e7c0f56ed8430888ed | | Affordance-R1 | 40.7 | Not recorded | 69f827e7c0f56ed8430888ed | | Vision-Reasoner | 27.7 | Not recorded | 69f827e7c0f56ed8430888ed | | LISA | 12.3 | Not recorded | 69f827e7c0f56ed8430888ed | | GLaMM | 5 | Not recorded | 69f827e7c0f56ed8430888ed | | G-DINO | 3.4 | Not recorded | 69f827e7c0f56ed8430888ed | ### A-Harness gIoU: 62.8. Result ID: 69f84fef47f34ce924dbc486. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MCS Setting":"w/ MCS-c (1:1 mixture)"}. This record does not assert independent reproduction. ### A-Harness gIoU: 60.6. Result ID: 69f84fef47f34ce924dbc485. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MCS Setting":"w/ MCS-b (RAGNet bank)"}. This record does not assert independent reproduction. ### A-Harness gIoU: 59.4. Result ID: 69f84fef47f34ce924dbc48a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MCS Setting":"w/ MCS-g (HANDAL-hard exemplars, Claude-Sonnet-4.6)"}. This record does not assert independent reproduction. ### AffordanceVLM gIoU: 58.2. Result ID: 69f84fef47f34ce924dbc482. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### A-Harness gIoU: 57.9. Result ID: 69f84fef47f34ce924dbc488. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MCS Setting":"w/ MCS-e (HANDAL-hard exemplars, GPT-4o)"}. This record does not assert independent reproduction. ### A-Harness gIoU: 55.3. Result ID: 69f84fef47f34ce924dbc483. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MCS Setting":"w/o MCS"}. This record does not assert independent reproduction. ### A-Harness gIoU: 55.2. Result ID: 69f84fef47f34ce924dbc489. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MCS Setting":"w/ MCS-f (HANDAL-easy exemplars, Claude-Sonnet-4.6)"}. This record does not assert independent reproduction. ### A-Harness gIoU: 49.8. Result ID: 69f84fef47f34ce924dbc484. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MCS Setting":"w/ MCS-a (UMD bank)"}. This record does not assert independent reproduction. ### A-Harness gIoU: 48. Result ID: 69f84fef47f34ce924dbc487. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MCS Setting":"w/ MCS-d (HANDAL-easy exemplars, GPT-4o)"}. This record does not assert independent reproduction. ### Affordance-R1 gIoU: 40.7. Result ID: 69f84fef47f34ce924dbc481. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Vision-Reasoner gIoU: 27.7. Result ID: 69f84fef47f34ce924dbc480. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### LISA gIoU: 12.3. Result ID: 69f84fef47f34ce924dbc47e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### GLaMM gIoU: 5. Result ID: 69f84fef47f34ce924dbc47f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### G-DINO gIoU: 3.4. Result ID: 69f84fef47f34ce924dbc47d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.