# Multi-target Search on Complex Instruction Tasks Multi-target

Source: [Multi-target Search on Complex Instruction Tasks Multi-target](<https://www.sota2.com/research/sota/multi-target-search-on-complex-instruction-tasks-multi-target>)

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

Data updated: 2026-03-04T20:57:12.131Z

Evaluation of agent performance on Multi-target Search tasks using the Complex Instruction Tasks Multi-target dataset, measured by Navigation Error (NE), Trajectory Length (TL), Success Rate (SR), and Success weighted by Path Length (SPL).

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 | Multi-target Search |
| Dataset (including any stated split) | Complex Instruction Tasks Multi-target |
| Metric | Navigation Error (NE) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| 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

- [Navigation Error (NE)](<https://www.sota2.com/research/sota/multi-target-search-on-complex-instruction-tasks-multi-target.md?metric=Navigation%20Error%20(NE)>): Lower is better; unit: SCALAR.

- [Trajectory Length (TL)](<https://www.sota2.com/research/sota/multi-target-search-on-complex-instruction-tasks-multi-target.md?metric=Trajectory%20Length%20(TL)>): Lower is better; unit: SCALAR.

- [Success Rate (SR)](<https://www.sota2.com/research/sota/multi-target-search-on-complex-instruction-tasks-multi-target.md?metric=Success%20Rate%20(SR)>): Higher is better; unit: PERCENT.

- [Success weighted by Path Length (SPL)](<https://www.sota2.com/research/sota/multi-target-search-on-complex-instruction-tasks-multi-target.md?metric=Success%20weighted%20by%20Path%20Length%20(SPL)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Navigation Error (NE) | Result date | Report paper |
| --- | --- | --- | --- |
| BrainNav | 2.95 | Not recorded | 68fa77eb1e209131cea76011 |
| MapGPT | 3.78 | Not recorded | 68fa77eb1e209131cea76011 |

### BrainNav

Navigation Error (NE): 2.95. Result ID: 69a89c546dbb7075b95181c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77eb1e209131cea76011.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77eb1e209131cea76011.md>)

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

### MapGPT

Navigation Error (NE): 3.78. Result ID: 69a89c546dbb7075b95181c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77eb1e209131cea76011.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73bd1e209131cea5e2e4.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.
