# Intent Detection on BANKING 10-shot (test)

Source: [Intent Detection on BANKING 10-shot (test)](<https://www.sota2.com/research/sota/intent-detection-on-banking-10-shot-test>)

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

Data updated: 2026-02-26T05:28:43.791Z

Evaluation of Intent Detection performance on the 10-shot test split of the BANKING dataset, measured using Accuracy.

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 | Intent Detection |
| Dataset (including any stated split) | BANKING 10-shot (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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](<https://www.sota2.com/research/sota/intent-detection-on-banking-10-shot-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ROBERTa-Large + Classifier + ICDA | 89.79 | Not recorded | 68fa6e8f1e209131cea409b4 |
| ROBERTa-Large + Classifier + ICDA | 89.12 | Not recorded | 68fa6e8f1e209131cea409b4 |
| ROBERTa-Large + Classifier + ICDA | 88.64 | Not recorded | 68fa6e8f1e209131cea409b4 |
| ROBERTa-Large + Classifier + ICDA | 87.37 | Not recorded | 68fa6e8f1e209131cea409b4 |
| CPFT | 87.2 | Not recorded | 68fa6e8f1e209131cea409b4 |
| ROBERTa-Large + Classifier + ICDA | 86.72 | Not recorded | 68fa6e8f1e209131cea409b4 |
| DNNC | 86.71 | Not recorded | 68fa6e8f1e209131cea409b4 |
| ROBERTa-Large + Classifier | 86.08 | Not recorded | 68fa6e8f1e209131cea409b4 |
| CONVBERT | 85.95 | Not recorded | 68fa6e8f1e209131cea409b4 |
| USE+CONVERT | 85.19 | Not recorded | 68fa6e8f1e209131cea409b4 |
| ROBERTa-Base + Classifier | 84.27 | Not recorded | 68fa6e8f1e209131cea409b4 |
| USE | 84.23 | Not recorded | 68fa6e8f1e209131cea409b4 |
| CONVBERT | 84.09 | Not recorded | 68fa6e8f1e209131cea409b4 |
| CONVBERT | 83.99 | Not recorded | 68fa6e8f1e209131cea409b4 |
| CONVBERT | 83.63 | Not recorded | 68fa6e8f1e209131cea409b4 |
| CONVERT | 83.32 | Not recorded | 68fa6e8f1e209131cea409b4 |

### ROBERTa-Large + Classifier + ICDA

Accuracy: 89.79. Result ID: 6990349f3a6c314849fee56c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

Recorded evaluation configuration: {"Augmentation Size":"XL"}. This record does not assert independent reproduction.

### ROBERTa-Large + Classifier + ICDA

Accuracy: 89.12. Result ID: 6990349f3a6c314849fee56b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

Recorded evaluation configuration: {"Augmentation Size":"L"}. This record does not assert independent reproduction.

### ROBERTa-Large + Classifier + ICDA

Accuracy: 88.64. Result ID: 6990349f3a6c314849fee56a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

Recorded evaluation configuration: {"Augmentation Size":"M"}. This record does not assert independent reproduction.

### ROBERTa-Large + Classifier + ICDA

Accuracy: 87.37. Result ID: 6990349f3a6c314849fee569.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

Recorded evaluation configuration: {"Augmentation Size":"S"}. This record does not assert independent reproduction.

### CPFT

Accuracy: 87.2. Result ID: 6990349f3a6c314849fee566.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ad01e209131cea2a762.md>)

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

### ROBERTa-Large + Classifier + ICDA

Accuracy: 86.72. Result ID: 6990349f3a6c314849fee568.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

Recorded evaluation configuration: {"Augmentation Size":"XS"}. This record does not assert independent reproduction.

### DNNC

Accuracy: 86.71. Result ID: 6990349f3a6c314849fee565.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a31e209131cea1d58c.md>)

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

### ROBERTa-Large + Classifier

Accuracy: 86.08. Result ID: 6990349f3a6c314849fee567.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

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

### CONVBERT

Accuracy: 85.95. Result ID: 6990349f3a6c314849fee564.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686d1e209131cea1c1b9.md>)

Recorded evaluation configuration: {"Augmentation":"+ Combined"}. This record does not assert independent reproduction.

### USE+CONVERT

Accuracy: 85.19. Result ID: 6990349f3a6c314849fee560.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686d1e209131cea1c1b9.md>)

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

### ROBERTa-Base + Classifier

Accuracy: 84.27. Result ID: 6990349f3a6c314849fee55d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

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

### USE

Accuracy: 84.23. Result ID: 6990349f3a6c314849fee55e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fa1e209131cea0d9e7.md>)

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

### CONVBERT

Accuracy: 84.09. Result ID: 6990349f3a6c314849fee563.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686d1e209131cea1c1b9.md>)

Recorded evaluation configuration: {"Augmentation":"+ MLM + Example"}. This record does not assert independent reproduction.

### CONVBERT

Accuracy: 83.99. Result ID: 6990349f3a6c314849fee562.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686d1e209131cea1c1b9.md>)

Recorded evaluation configuration: {"Augmentation":"+ MLM"}. This record does not assert independent reproduction.

### CONVBERT

Accuracy: 83.63. Result ID: 6990349f3a6c314849fee561.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686d1e209131cea1c1b9.md>)

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

### CONVERT

Accuracy: 83.32. Result ID: 6990349f3a6c314849fee55f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e8f1e209131cea409b4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676e1e209131cea1624e.md>)

[Implementation](<https://www.sota2.com/github.com/PolyAI-LDN/polyai-models>)

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.
