# Phase recognition on AutoLaparo (test)

Source: [Phase recognition on AutoLaparo (test)](<https://www.sota2.com/research/sota/phase-recognition-on-autolaparo-test>)

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

Data updated: 2026-07-01T07:31:41.366Z

Evaluation of phase recognition performance on the test split of the AutoLaparo dataset, assessed using metrics such as F1 score.

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 | Phase recognition |
| Dataset (including any stated split) | AutoLaparo (test) |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 30 of 30 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/phase-recognition-on-autolaparo-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/phase-recognition-on-autolaparo-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| AutoLaparo SSL | 70.7 | Not recorded | 68fa7a121e209131cea80f22 |
| ImageNet Supervised | 70.1 | Not recorded | 68fa7a121e209131cea80f22 |
| EndoFM | 68.9 | Not recorded | 68fa7a121e209131cea80f22 |
| ImageNet Supervised | 68.6 | Not recorded | 68fa7a121e209131cea80f22 |
| AutoLaparo SSL | 64.4 | Not recorded | 68fa7a121e209131cea80f22 |
| ImageNet Supervised | 62.3 | Not recorded | 68fa7a121e209131cea80f22 |
| Cholec80 SSL | 61.5 | Not recorded | 68fa7a121e209131cea80f22 |
| AutoLaparo SSL | 59.5 | Not recorded | 68fa7a121e209131cea80f22 |
| EndoFM | 59.3 | Not recorded | 68fa7a121e209131cea80f22 |
| ImageNet Supervised | 58.5 | Not recorded | 68fa7a121e209131cea80f22 |
| Cholec80 SSL | 58.3 | Not recorded | 68fa7a121e209131cea80f22 |
| ImageNet Supervised | 57.6 | Not recorded | 68fa7a121e209131cea80f22 |
| EndoFM | 56.6 | Not recorded | 68fa7a121e209131cea80f22 |
| ImageNet Supervised | 50.8 | Not recorded | 68fa7a121e209131cea80f22 |
| Cholec80 SSL | 47.7 | Not recorded | 68fa7a121e209131cea80f22 |
| HyperVLP | 32.9 | Not recorded | 6a449eeee0224bd4f4992db6 |
| PeskaVLP | 23.6 | Not recorded | 68fa77691e209131cea731fe |
| PeskaVLP | 23.6 | Not recorded | 6a449eeee0224bd4f4992db6 |
| HecVL | 18.9 | Not recorded | 68fa77691e209131cea731fe |
| HecVL | 18.9 | Not recorded | 6a449eeee0224bd4f4992db6 |
| SurgVLP | 16.6 | Not recorded | 68fa77691e209131cea731fe |
| SurgVLP | 16.6 | Not recorded | 6a449eeee0224bd4f4992db6 |
| CLIP | 16.2 | Not recorded | 68fa77691e209131cea731fe |
| CLIP | 16.2 | Not recorded | 6a449eeee0224bd4f4992db6 |
| CLIP | 10.9 | Not recorded | 68fa77691e209131cea731fe |
| CLIP | 10.9 | Not recorded | 6a449eeee0224bd4f4992db6 |
| CLIP | 9.1 | Not recorded | 68fa77691e209131cea731fe |
| CLIP | 9.1 | Not recorded | 6a449eeee0224bd4f4992db6 |
| MIL-NCE | 7.9 | Not recorded | 68fa77691e209131cea731fe |
| MIL-NCE | 7.9 | Not recorded | 6a449eeee0224bd4f4992db6 |

### AutoLaparo SSL

F1 Score: 70.7. Result ID: 698b6c3f7a967eddb76e74c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Implementation](<https://github.com/CAMMA-public/ScalingSurgicalSSL/>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Labeled Videos":"10"}. This record does not assert independent reproduction.

### ImageNet Supervised

F1 Score: 70.1. Result ID: 698b6c3f7a967eddb76e74c9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Labeled Videos":"10"}. This record does not assert independent reproduction.

### EndoFM

F1 Score: 68.9. Result ID: 698b6c3f7a967eddb76e74c6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d01e209131cea531b5.md>)

[Implementation](<https://github.com/med-air/Endo-FM>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Number of Labeled Videos":"10"}. This record does not assert independent reproduction.

### ImageNet Supervised

F1 Score: 68.6. Result ID: 698b6c3f7a967eddb76e74cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Number of Labeled Videos":"10"}. This record does not assert independent reproduction.

### AutoLaparo SSL

F1 Score: 64.4. Result ID: 698b6c3f7a967eddb76e74c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Implementation](<https://github.com/CAMMA-public/ScalingSurgicalSSL/>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Labeled Videos":"5"}. This record does not assert independent reproduction.

### ImageNet Supervised

F1 Score: 62.3. Result ID: 698b6c3f7a967eddb76e74cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Number of Labeled Videos":"5"}. This record does not assert independent reproduction.

### Cholec80 SSL

F1 Score: 61.5. Result ID: 698b6c3f7a967eddb76e74c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Implementation](<https://github.com/CAMMA-public/ScalingSurgicalSSL/>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Labeled Videos":"10"}. This record does not assert independent reproduction.

### AutoLaparo SSL

F1 Score: 59.5. Result ID: 698b6c3f7a967eddb76e74c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Implementation](<https://github.com/CAMMA-public/ScalingSurgicalSSL/>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Labeled Videos":"3"}. This record does not assert independent reproduction.

### EndoFM

F1 Score: 59.3. Result ID: 698b6c3f7a967eddb76e74c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d01e209131cea531b5.md>)

[Implementation](<https://github.com/med-air/Endo-FM>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Number of Labeled Videos":"5"}. This record does not assert independent reproduction.

### ImageNet Supervised

F1 Score: 58.5. Result ID: 698b6c3f7a967eddb76e74ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Number of Labeled Videos":"3"}. This record does not assert independent reproduction.

### Cholec80 SSL

F1 Score: 58.3. Result ID: 698b6c3f7a967eddb76e74c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Implementation](<https://github.com/CAMMA-public/ScalingSurgicalSSL/>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Labeled Videos":"5"}. This record does not assert independent reproduction.

### ImageNet Supervised

F1 Score: 57.6. Result ID: 698b6c3f7a967eddb76e74ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Labeled Videos":"5"}. This record does not assert independent reproduction.

### EndoFM

F1 Score: 56.6. Result ID: 698b6c3f7a967eddb76e74c8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d01e209131cea531b5.md>)

[Implementation](<https://github.com/med-air/Endo-FM>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Number of Labeled Videos":"3"}. This record does not assert independent reproduction.

### ImageNet Supervised

F1 Score: 50.8. Result ID: 698b6c3f7a967eddb76e74cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Labeled Videos":"3"}. This record does not assert independent reproduction.

### Cholec80 SSL

F1 Score: 47.7. Result ID: 698b6c3f7a967eddb76e74c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a121e209131cea80f22.md>)

[Implementation](<https://github.com/CAMMA-public/ScalingSurgicalSSL/>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Number of Labeled Videos":"3"}. This record does not assert independent reproduction.

### HyperVLP

F1 Score: 32.9. Result ID: 6a44c25c73d097d845be723d.

[Reporting paper](<https://www.sota2.com/research/paper/6a449eeee0224bd4f4992db6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a449eeee0224bd4f4992db6.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"SVL","Zero-shot":"true"}. This record does not assert independent reproduction.

### PeskaVLP

F1 Score: 23.6. Result ID: 699488fe3a6c3148491ddbec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731fe.md>)

[Implementation](<https://github.com/CAMMA-public/SurgVLP>)

Recorded evaluation configuration: {"Pre-training Dataset":"SVL","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### PeskaVLP

F1 Score: 23.6. Result ID: 6a44c25c73d097d845be723c.

[Reporting paper](<https://www.sota2.com/research/paper/6a449eeee0224bd4f4992db6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731fe.md>)

[Implementation](<https://github.com/CAMMA-public/SurgVLP>)

Recorded evaluation configuration: {"Pre-training Dataset":"SVL","Zero-shot":"true"}. This record does not assert independent reproduction.

### HecVL

F1 Score: 18.9. Result ID: 699488fe3a6c3148491ddbeb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731d1.md>)

[Implementation](<https://github.com/CAMMA-public/SurgVLP>)

Recorded evaluation configuration: {"Pre-training Dataset":"SVL","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### HecVL

F1 Score: 18.9. Result ID: 6a44c25c73d097d845be723b.

[Reporting paper](<https://www.sota2.com/research/paper/6a449eeee0224bd4f4992db6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731d1.md>)

[Implementation](<https://github.com/CAMMA-public/SurgVLP>)

Recorded evaluation configuration: {"Pre-training Dataset":"SVL","Zero-shot":"true"}. This record does not assert independent reproduction.

### SurgVLP

F1 Score: 16.6. Result ID: 699488fe3a6c3148491ddbea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79841e209131cea7df69.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"SVL","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### SurgVLP

F1 Score: 16.6. Result ID: 6a44c25c73d097d845be723a.

[Reporting paper](<https://www.sota2.com/research/paper/6a449eeee0224bd4f4992db6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79841e209131cea7df69.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"SVL","Zero-shot":"true"}. This record does not assert independent reproduction.

### CLIP

F1 Score: 16.2. Result ID: 699488fe3a6c3148491ddbe9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Pre-training Dataset":"SVL","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### CLIP

F1 Score: 16.2. Result ID: 6a44c25c73d097d845be7239.

[Reporting paper](<https://www.sota2.com/research/paper/6a449eeee0224bd4f4992db6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Pre-training Dataset":"SVL","Zero-shot":"true"}. This record does not assert independent reproduction.

### CLIP

F1 Score: 10.9. Result ID: 699488fe3a6c3148491ddbe8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Pre-training Dataset":"Scratch","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### CLIP

F1 Score: 10.9. Result ID: 6a44c25c73d097d845be7238.

[Reporting paper](<https://www.sota2.com/research/paper/6a449eeee0224bd4f4992db6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Pre-training Dataset":"Scratch","Zero-shot":"true"}. This record does not assert independent reproduction.

### CLIP

F1 Score: 9.1. Result ID: 699488fe3a6c3148491ddbe7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Pre-training Dataset":"CLIP400M","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### CLIP

F1 Score: 9.1. Result ID: 6a44c25c73d097d845be7237.

[Reporting paper](<https://www.sota2.com/research/paper/6a449eeee0224bd4f4992db6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Pre-training Dataset":"CLIP400M","Zero-shot":"true"}. This record does not assert independent reproduction.

### MIL-NCE

F1 Score: 7.9. Result ID: 699488fe3a6c3148491ddbe6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68351e209131cea1ac99.md>)

[Implementation](<https://www.di.ens.fr/willow/research/mil-nce/>)

Recorded evaluation configuration: {"Pre-training Dataset":"Howto100M","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### MIL-NCE

F1 Score: 7.9. Result ID: 6a44c25c73d097d845be7236.

[Reporting paper](<https://www.sota2.com/research/paper/6a449eeee0224bd4f4992db6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa661f1e209131cea0e7d9.md>)

[Implementation](<https://www.di.ens.fr/willow/research/howto100m/>)

Recorded evaluation configuration: {"Pre-training Dataset":"HowTo100M","Zero-shot":"true"}. This record does not assert independent reproduction.

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