# Image Classification on GTSRB (Accuracy, Frequency of teacher queries)

Source: [Image Classification on GTSRB (Accuracy, Frequency of teacher queries)](<https://www.sota2.com/research/sota/image-classification-on-gtsrb-accuracy-frequency-of-teacher-queries>)

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

Data updated: 2026-04-08T09:12:47.123Z

Evaluation of standard Image Classification performance on the GTSRB dataset, reporting overall Accuracy and the frequency of teacher queries used during evaluation.

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 | Image Classification |
| Dataset (including any stated split) | GTSRB |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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/image-classification-on-gtsrb-accuracy-frequency-of-teacher-queries.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Teacher Query Frequency (T(x))](<https://www.sota2.com/research/sota/image-classification-on-gtsrb-accuracy-frequency-of-teacher-queries.md?metric=Teacher%20Query%20Frequency%20(T(x))>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Offline ICD | 72.6 | Not recorded | 68fa7c501e209131cea8d824 |
| ICD | 70.8 | Not recorded | 68fa7c501e209131cea8d824 |
| GPT-4o | 68.1 | Not recorded | 68fa7c501e209131cea8d824 |
| Offline ICD | 66.1 | Not recorded | 68fa7c501e209131cea8d824 |
| ICD | 61.9 | Not recorded | 68fa7c501e209131cea8d824 |
| BestofN | 50.4 | Not recorded | 68fa7c501e209131cea8d824 |
| Self-labeling | 47.7 | Not recorded | 68fa7c501e209131cea8d824 |
| 0-shot | 47.2 | Not recorded | 68fa7c501e209131cea8d824 |
| BestofN | 44.2 | Not recorded | 68fa7c501e209131cea8d824 |
| 0-shot | 42.6 | Not recorded | 68fa7c501e209131cea8d824 |
| Self-labeling | 41.6 | Not recorded | 68fa7c501e209131cea8d824 |
| CoT | 41 | Not recorded | 68fa7c501e209131cea8d824 |
| CoT | 32.1 | Not recorded | 68fa7c501e209131cea8d824 |

### Offline ICD

Accuracy: 72.6. Result ID: 69d61bfd47f34ce924bee5ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-OneVision"}. This record does not assert independent reproduction.

### ICD

Accuracy: 70.8. Result ID: 69d61bfd47f34ce924bee5b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-OneVision"}. This record does not assert independent reproduction.

### GPT-4o

Accuracy: 68.1. Result ID: 69d61bfd47f34ce924bee5bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

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

### Offline ICD

Accuracy: 66.1. Result ID: 69d61bfd47f34ce924bee5bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5"}. This record does not assert independent reproduction.

### ICD

Accuracy: 61.9. Result ID: 69d61bfd47f34ce924bee5b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5"}. This record does not assert independent reproduction.

### BestofN

Accuracy: 50.4. Result ID: 69d61bfd47f34ce924bee5b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa766a1e209131cea6cd40.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5"}. This record does not assert independent reproduction.

### Self-labeling

Accuracy: 47.7. Result ID: 69d61bfd47f34ce924bee5b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e483.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5"}. This record does not assert independent reproduction.

### 0-shot

Accuracy: 47.2. Result ID: 69d61bfd47f34ce924bee5b1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5"}. This record does not assert independent reproduction.

### BestofN

Accuracy: 44.2. Result ID: 69d61bfd47f34ce924bee5b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa766a1e209131cea6cd40.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-OneVision"}. This record does not assert independent reproduction.

### 0-shot

Accuracy: 42.6. Result ID: 69d61bfd47f34ce924bee5b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-OneVision"}. This record does not assert independent reproduction.

### Self-labeling

Accuracy: 41.6. Result ID: 69d61bfd47f34ce924bee5b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e483.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-OneVision"}. This record does not assert independent reproduction.

### CoT

Accuracy: 41. Result ID: 69d61bfd47f34ce924bee5b3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5"}. This record does not assert independent reproduction.

### CoT

Accuracy: 32.1. Result ID: 69d61bfd47f34ce924bee5b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c501e209131cea8d824.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-OneVision"}. This record does not assert independent reproduction.

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