# Detection generation on Gold-standard detections

Source: [Detection generation on Gold-standard detections](<https://www.sota2.com/research/sota/detection-generation-on-gold-standard-detections>)

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

Data updated: 2026-03-30T06:51:51.947Z

Evaluation of model performance for detection generation tasks using the Gold-standard detections dataset, reporting Mean and Median 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 | Detection generation |
| Dataset (including any stated split) | Gold-standard detections |
| Metric | Mean Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Mean Score](<https://www.sota2.com/research/sota/detection-generation-on-gold-standard-detections.md?metric=Mean%20Score>): Higher is better; unit: SCALAR.

- [Median Score](<https://www.sota2.com/research/sota/detection-generation-on-gold-standard-detections.md?metric=Median%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Mean Score | Result date | Report paper |
| --- | --- | --- | --- |
| gpt-5 | 0.578 | Not recorded | 69ca039d0636e5bf4afc941e |
| gpt-5.1 | 0.575 | Not recorded | 69ca039d0636e5bf4afc941e |
| gpt-5-mini | 0.553 | Not recorded | 69ca039d0636e5bf4afc941e |
| gpt-5.1 | 0.547 | Not recorded | 69ca039d0636e5bf4afc941e |
| gpt-5 | 0.545 | Not recorded | 69ca039d0636e5bf4afc941e |

### gpt-5

Mean Score: 0.578. Result ID: 69ca1d7c47f34ce924b229d3.

[Reporting paper](<https://www.sota2.com/research/paper/69ca039d0636e5bf4afc941e.md>)

Recorded evaluation configuration: {"Tier":"medium","Approach":"Agentic"}. This record does not assert independent reproduction.

### gpt-5.1

Mean Score: 0.575. Result ID: 69ca1d7c47f34ce924b229d4.

[Reporting paper](<https://www.sota2.com/research/paper/69ca039d0636e5bf4afc941e.md>)

Recorded evaluation configuration: {"Tier":"high","Approach":"Agentic"}. This record does not assert independent reproduction.

### gpt-5-mini

Mean Score: 0.553. Result ID: 69ca1d7c47f34ce924b229d5.

[Reporting paper](<https://www.sota2.com/research/paper/69ca039d0636e5bf4afc941e.md>)

Recorded evaluation configuration: {"Tier":"high","Approach":"Agentic"}. This record does not assert independent reproduction.

### gpt-5.1

Mean Score: 0.547. Result ID: 69ca1d7c47f34ce924b229d6.

[Reporting paper](<https://www.sota2.com/research/paper/69ca039d0636e5bf4afc941e.md>)

Recorded evaluation configuration: {"Tier":"medium","Approach":"Agentic"}. This record does not assert independent reproduction.

### gpt-5

Mean Score: 0.545. Result ID: 69ca1d7c47f34ce924b229d7.

[Reporting paper](<https://www.sota2.com/research/paper/69ca039d0636e5bf4afc941e.md>)

Recorded evaluation configuration: {"Tier":"high","Approach":"Agentic"}. This record does not assert independent reproduction.

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