# Fine-grained multi-label classification on ICLR gold-labeled (test)

Source: [Fine-grained multi-label classification on ICLR gold-labeled (test)](<https://www.sota2.com/research/sota/fine-grained-multi-label-classification-on-iclr-gold-labeled-test>)

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

Data updated: 2026-05-27T09:41:42.677Z

Evaluation of fine-grained multi-label classification performance on the test split of the ICLR gold-labeled dataset, reporting Jaccard similarity and Micro/Macro/Weighted F1 scores.

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 | Fine-grained multi-label classification |
| Dataset (including any stated split) | ICLR gold-labeled (test) |
| Metric | Jaccard Similarity |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Jaccard Similarity](<https://www.sota2.com/research/sota/fine-grained-multi-label-classification-on-iclr-gold-labeled-test.md?metric=Jaccard%20Similarity>): Higher is better; unit: PERCENT.

- [Micro F1 Score](<https://www.sota2.com/research/sota/fine-grained-multi-label-classification-on-iclr-gold-labeled-test.md?metric=Micro%20F1%20Score>): Higher is better; unit: PERCENT.

- [Macro F1 Score](<https://www.sota2.com/research/sota/fine-grained-multi-label-classification-on-iclr-gold-labeled-test.md?metric=Macro%20F1%20Score>): Higher is better; unit: PERCENT.

- [Weighted F1 Score](<https://www.sota2.com/research/sota/fine-grained-multi-label-classification-on-iclr-gold-labeled-test.md?metric=Weighted%20F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Jaccard Similarity | Result date | Report paper |
| --- | --- | --- | --- |
| TADDLE | 74.24 | Not recorded | 6a167ac4dbd7150506f8016f |
| Longformer-base-4096 | 71.11 | Not recorded | 6a167ac4dbd7150506f8016f |
| BERT-base-uncased | 66.67 | Not recorded | 6a167ac4dbd7150506f8016f |
| DeepSeek V3.2 | 40.3 | Not recorded | 6a167ac4dbd7150506f8016f |
| GLM 4.7 | 40.22 | Not recorded | 6a167ac4dbd7150506f8016f |
| Qwen3.5-Plus | 39.54 | Not recorded | 6a167ac4dbd7150506f8016f |
| Qwen3-30B | 35.65 | Not recorded | 6a167ac4dbd7150506f8016f |
| BigBird-RoBERTa-base | 30.68 | Not recorded | 6a167ac4dbd7150506f8016f |

### TADDLE

Jaccard Similarity: 74.24. Result ID: 6a16bc43fbc373592c104ac7.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ac4dbd7150506f8016f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167ac4dbd7150506f8016f.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Longformer-base-4096

Jaccard Similarity: 71.11. Result ID: 6a16bc43fbc373592c104ac2.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ac4dbd7150506f8016f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68d41e209131cea1e701.md>)

[Implementation](<https://github.com/allenai/longformer>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### BERT-base-uncased

Jaccard Similarity: 66.67. Result ID: 6a16bc43fbc373592c104ac0.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ac4dbd7150506f8016f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DeepSeek V3.2

Jaccard Similarity: 40.3. Result ID: 6a16bc43fbc373592c104ac3.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ac4dbd7150506f8016f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692fc410d6b0dd33429332f4.md>)

Recorded evaluation configuration: {"few-shot":"true"}. This record does not assert independent reproduction.

### GLM 4.7

Jaccard Similarity: 40.22. Result ID: 6a16bc43fbc373592c104ac6.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ac4dbd7150506f8016f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a891e209131cea83c41.md>)

Recorded evaluation configuration: {"few-shot":"true"}. This record does not assert independent reproduction.

### Qwen3.5-Plus

Jaccard Similarity: 39.54. Result ID: 6a16bc43fbc373592c104ac4.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ac4dbd7150506f8016f.md>)

Recorded evaluation configuration: {"few-shot":"true"}. This record does not assert independent reproduction.

### Qwen3-30B

Jaccard Similarity: 35.65. Result ID: 6a16bc43fbc373592c104ac5.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ac4dbd7150506f8016f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"few-shot":"true"}. This record does not assert independent reproduction.

### BigBird-RoBERTa-base

Jaccard Similarity: 30.68. Result ID: 6a16bc43fbc373592c104ac1.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ac4dbd7150506f8016f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690b1e209131cea1faf6.md>)

[Implementation](<http://goo.gle/bigbird-transformer>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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