# Open-set taxonomic classification on iNat Animal 2021 (test)

Source: [Open-set taxonomic classification on iNat Animal 2021 (test)](<https://www.sota2.com/research/sota/open-set-taxonomic-classification-on-inat-animal-2021-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:46:08.646Z

Evaluation of Open-set Taxonomic Classification performance on the test split of the iNat Animal 2021 dataset, measured using Hierarchical Classification Accuracy (HCA) and Leaf Accuracy (Acc\_leaf).

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 | Open-set taxonomic classification |
| Dataset (including any stated split) | iNat Animal 2021 (test) |
| Metric | HCA |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [HCA](<https://www.sota2.com/research/sota/open-set-taxonomic-classification-on-inat-animal-2021-test.md?metric=HCA>): Higher is better; unit: PERCENT.

- [Leaf Accuracy](<https://www.sota2.com/research/sota/open-set-taxonomic-classification-on-inat-animal-2021-test.md?metric=Leaf%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | HCA | Result date | Report paper |
| --- | --- | --- | --- |
| VL-Taxon | 1527 | Not recorded | 6971af05e25ad2fa9d1ed94a |
| Qwen2.5-VL-7B-SFT | 920 | Not recorded | 6971af05e25ad2fa9d1ed94a |
| Qwen2.5-VL-7B | 1 | Not recorded | 6971af05e25ad2fa9d1ed94a |

### VL-Taxon

HCA: 1527. Result ID: 6997a1565698665ec4f76334.

[Reporting paper](<https://www.sota2.com/research/paper/6971af05e25ad2fa9d1ed94a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6971af05e25ad2fa9d1ed94a.md>)

Recorded evaluation configuration: {"Parameters":"7B","Approach":"Hierarchical Reasoning"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B-SFT

HCA: 920. Result ID: 6997a1565698665ec4f76333.

[Reporting paper](<https://www.sota2.com/research/paper/6971af05e25ad2fa9d1ed94a.md>)

Recorded evaluation configuration: {"Parameters":"7B","Training":"Supervised Fine-Tuned (SFT)"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

HCA: 1. Result ID: 6997a1565698665ec4f76332.

[Reporting paper](<https://www.sota2.com/research/paper/6971af05e25ad2fa9d1ed94a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Parameters":"7B","Variant":"Original"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
