# Image Classification on NATS-Bench ImageNet16-120 TSS (test)

Source: [Image Classification on NATS-Bench ImageNet16-120 TSS (test)](<https://www.sota2.com/research/sota/image-classification-on-nats-bench-imagenet16-120-tss-test>)

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

Data updated: 2026-03-04T08:57:34.099Z

Evaluation of Image Classification performance on the test split of the NATS-Bench ImageNet-16-120 benchmark using the TSS protocol, reporting accuracy and time metrics.

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) | NATS-Bench ImageNet16-120 TSS (test) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-nats-bench-imagenet16-120-tss-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Time (s)](<https://www.sota2.com/research/sota/image-classification-on-nats-bench-imagenet16-120-tss-test.md?metric=Time%20(s)>): Lower is better; unit: TIME.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FreeREA | 46.34 | Not recorded | 69a66bdc2d603e6de3e3cc9a |
| FreeREA + Latency | 46.34 | Not recorded | 69a66bdc2d603e6de3e3cc9a |
| GA-NINASWOT | 45.18 | Not recorded | 69a66bdc2d603e6de3e3cc9a |
| NASWOT (1000) | 45.08 | Not recorded | 69a66bdc2d603e6de3e3cc9a |
| NASI | 44.84 | Not recorded | 69a66bdc2d603e6de3e3cc9a |
| TENAS | 42.38 | Not recorded | 69a66bdc2d603e6de3e3cc9a |
| EPE-NAS | 41.84 | Not recorded | 69a66bdc2d603e6de3e3cc9a |
| FreeREA + Memory | 19.66 | Not recorded | 69a66bdc2d603e6de3e3cc9a |

### FreeREA

Accuracy: 46.34. Result ID: 69a7f3f36dbb7075b94cf0d5.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bdc2d603e6de3e3cc9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f431e209131cea449c2.md>)

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

### FreeREA + Latency

Accuracy: 46.34. Result ID: 69a7f3f36dbb7075b94cf0d6.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bdc2d603e6de3e3cc9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66bdc2d603e6de3e3cc9a.md>)

Recorded evaluation configuration: {"Constraint":"Latency","Evaluator":"SEval-NAS"}. This record does not assert independent reproduction.

### GA-NINASWOT

Accuracy: 45.18. Result ID: 69a7f3f36dbb7075b94cf0d3.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bdc2d603e6de3e3cc9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f431e209131cea449c2.md>)

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

### NASWOT (1000)

Accuracy: 45.08. Result ID: 69a7f3f36dbb7075b94cf0d0.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bdc2d603e6de3e3cc9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1f1e209131cea261b2.md>)

[Implementation](<https://github.com/BayesWatch/nas-without-training>)

Recorded evaluation configuration: {"Trials":"1000"}. This record does not assert independent reproduction.

### NASI

Accuracy: 44.84. Result ID: 69a7f3f36dbb7075b94cf0d2.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bdc2d603e6de3e3cc9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f431e209131cea449c2.md>)

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

### TENAS

Accuracy: 42.38. Result ID: 69a7f3f36dbb7075b94cf0d1.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bdc2d603e6de3e3cc9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f431e209131cea449c2.md>)

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

### EPE-NAS

Accuracy: 41.84. Result ID: 69a7f3f36dbb7075b94cf0d4.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bdc2d603e6de3e3cc9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f431e209131cea449c2.md>)

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

### FreeREA + Memory

Accuracy: 19.66. Result ID: 69a7f3f36dbb7075b94cf0d7.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bdc2d603e6de3e3cc9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66bdc2d603e6de3e3cc9a.md>)

Recorded evaluation configuration: {"Constraint":"Memory","Evaluator":"SEval-NAS"}. This record does not assert independent reproduction.

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