# MGT detection on TLDR

Source: [MGT detection on TLDR](<https://www.sota2.com/research/sota/mgt-detection-on-tldr>)

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

Data updated: 2026-06-04T11:49:41.939Z

Evaluation of Machine-Generated Text (MGT) detection performance on the TLDR dataset, typically measured using Accuracy and 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 | MGT detection |
| Dataset (including any stated split) | TLDR |
| 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/mgt-detection-on-tldr.md?metric=Accuracy>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LRR | 72.81 | Not recorded | 690988943ef7ccd74e5e5e45 |
| DEER | 72.63 | Not recorded | 690988943ef7ccd74e5e5e45 |
| Binoculars | 72.31 | Not recorded | 690988943ef7ccd74e5e5e45 |
| Log-Likelihood | 71.85 | Not recorded | 690988943ef7ccd74e5e5e45 |
| MoSEs | 71.63 | Not recorded | 690988943ef7ccd74e5e5e45 |
| Fast-DetectGPT | 71.44 | Not recorded | 690988943ef7ccd74e5e5e45 |
| MGT-Prism | 70.53 | Not recorded | 690988943ef7ccd74e5e5e45 |
| MSCL | 69.13 | Not recorded | 690988943ef7ccd74e5e5e45 |
| Roberta | 69.05 | Not recorded | 690988943ef7ccd74e5e5e45 |
| Entropy | 67.73 | Not recorded | 690988943ef7ccd74e5e5e45 |
| PeCoLA | 67.73 | Not recorded | 690988943ef7ccd74e5e5e45 |
| EAGLE | 65.85 | Not recorded | 690988943ef7ccd74e5e5e45 |
| Ghostbuster | 65.06 | Not recorded | 690988943ef7ccd74e5e5e45 |
| TACIT | 64.73 | Not recorded | 690988943ef7ccd74e5e5e45 |
| Rank | 61 | Not recorded | 690988943ef7ccd74e5e5e45 |
| ImBD | 54.66 | Not recorded | 690988943ef7ccd74e5e5e45 |

### LRR

Accuracy: 72.81. Result ID: 6a21654cfbc373592c1e4222.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

Recorded evaluation configuration: {"Method Category":"Metric-based methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### DEER

Accuracy: 72.63. Result ID: 6a21654cfbc373592c1e422e.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

Recorded evaluation configuration: {"Method Category":"Domain generalization methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### Binoculars

Accuracy: 72.31. Result ID: 6a21654cfbc373592c1e4224.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75371e209131cea667f1.md>)

Recorded evaluation configuration: {"Method Category":"Metric-based methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### Log-Likelihood

Accuracy: 71.85. Result ID: 6a21654cfbc373592c1e4221.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

Recorded evaluation configuration: {"Method Category":"Metric-based methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### MoSEs

Accuracy: 71.63. Result ID: 6a21654cfbc373592c1e422a.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b2e1e209131cea8714d.md>)

Recorded evaluation configuration: {"Method Category":"Model-based methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### Fast-DetectGPT

Accuracy: 71.44. Result ID: 6a21654cfbc373592c1e4223.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76341e209131cea6bcf2.md>)

Recorded evaluation configuration: {"Method Category":"Metric-based methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### MGT-Prism

Accuracy: 70.53. Result ID: 6a21654cfbc373592c1e422d.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7acf1e209131cea853e2.md>)

Recorded evaluation configuration: {"Method Category":"Domain generalization methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### MSCL

Accuracy: 69.13. Result ID: 6a21654cfbc373592c1e422b.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

Recorded evaluation configuration: {"Method Category":"Domain generalization methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### Roberta

Accuracy: 69.05. Result ID: 6a21654cfbc373592c1e4225.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

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

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

Recorded evaluation configuration: {"Method Category":"Model-based methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### Entropy

Accuracy: 67.73. Result ID: 6a21654cfbc373592c1e421f.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

Recorded evaluation configuration: {"Method Category":"Metric-based methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### PeCoLA

Accuracy: 67.73. Result ID: 6a21654cfbc373592c1e4227.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f0f0.md>)

[Implementation](<https://github.com/lsc-1/Pecola>)

Recorded evaluation configuration: {"Method Category":"Model-based methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### EAGLE

Accuracy: 65.85. Result ID: 6a21654cfbc373592c1e4228.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729b1e209131cea5776d.md>)

Recorded evaluation configuration: {"Method Category":"Model-based methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### Ghostbuster

Accuracy: 65.06. Result ID: 6a21654cfbc373592c1e4226.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d61e209131cea58d2e.md>)

[Implementation](<https://github.com/vivek3141/ghostbuster>)

Recorded evaluation configuration: {"Method Category":"Model-based methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### TACIT

Accuracy: 64.73. Result ID: 6a21654cfbc373592c1e422c.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71a41e209131cea52437.md>)

Recorded evaluation configuration: {"Method Category":"Domain generalization methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### Rank

Accuracy: 61. Result ID: 6a21654cfbc373592c1e4220.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

Recorded evaluation configuration: {"Method Category":"Metric-based methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

### ImBD

Accuracy: 54.66. Result ID: 6a21654cfbc373592c1e4229.

[Reporting paper](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765a1e209131cea6c945.md>)

Recorded evaluation configuration: {"Method Category":"Model-based methods","Evaluation Scenario":"DG-MGT"}. This record does not assert independent reproduction.

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