# Insertion on Insertion Hard Positions

Source: [Insertion on Insertion Hard Positions](<https://www.sota2.com/research/sota/insertion-on-insertion-hard-positions>)

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

Data updated: 2026-03-05T08:40:51.829Z

Evaluation of the model's performance on the Insertion task using the Insertion Hard Positions dataset, focusing on success rates across specific in-distribution (ID) and out-of-distribution (OOD) hard scenarios.

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 | Insertion |
| Dataset (including any stated split) | Insertion Hard Positions |
| Metric | ID Hard Position 1 Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [ID Hard Position 1 Success Rate](<https://www.sota2.com/research/sota/insertion-on-insertion-hard-positions.md?metric=ID%20Hard%20Position%201%20Success%20Rate>): Higher is better; unit: PERCENT.

- [ID Hard Position 2 Success Rate](<https://www.sota2.com/research/sota/insertion-on-insertion-hard-positions.md?metric=ID%20Hard%20Position%202%20Success%20Rate>): Higher is better; unit: PERCENT.

- [ID Hard Position 3 Success Rate](<https://www.sota2.com/research/sota/insertion-on-insertion-hard-positions.md?metric=ID%20Hard%20Position%203%20Success%20Rate>): Higher is better; unit: PERCENT.

- [OOD Hard Position Success Rate](<https://www.sota2.com/research/sota/insertion-on-insertion-hard-positions.md?metric=OOD%20Hard%20Position%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Total Success Rate](<https://www.sota2.com/research/sota/insertion-on-insertion-hard-positions.md?metric=Total%20Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ID Hard Position 1 Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| FlowCorrect | 100 | Not recorded | 699fd39a2d603e6de3e3bfdd |
| RT | 80 | Not recorded | 699fd39a2d603e6de3e3bfdd |
| Base | 0 | Not recorded | 699fd39a2d603e6de3e3bfdd |

### FlowCorrect

ID Hard Position 1 Success Rate: 100. Result ID: 69a941806dbb7075b952bed6.

[Reporting paper](<https://www.sota2.com/research/paper/699fd39a2d603e6de3e3bfdd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699fd39a2d603e6de3e3bfdd.md>)

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

### RT

ID Hard Position 1 Success Rate: 80. Result ID: 69a941806dbb7075b952bed7.

[Reporting paper](<https://www.sota2.com/research/paper/699fd39a2d603e6de3e3bfdd.md>)

Recorded evaluation configuration: {"Description":"Retraining"}. This record does not assert independent reproduction.

### Base

ID Hard Position 1 Success Rate: 0. Result ID: 69a941806dbb7075b952bed5.

[Reporting paper](<https://www.sota2.com/research/paper/699fd39a2d603e6de3e3bfdd.md>)

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

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