# Task Routing on OlympusBench chain-of-action setting

Source: [Task Routing on OlympusBench chain-of-action setting](<https://www.sota2.com/research/sota/task-routing-on-olympusbench-chain-of-action-setting>)

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

Data updated: 2026-02-26T05:42:25.871Z

Evaluation of Task Routing performance on the OlympusBench chain-of-action setting, measured using Exact Difference (ED), Precision, Recall, and F1 scores.

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 | Task Routing |
| Dataset (including any stated split) | OlympusBench chain-of-action setting |
| Metric | Exact Difference (ED) |
| Unit | PERCENT |
| Direction | Lower 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

- [Exact Difference (ED)](<https://www.sota2.com/research/sota/task-routing-on-olympusbench-chain-of-action-setting.md?metric=Exact%20Difference%20(ED)>): Lower is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/task-routing-on-olympusbench-chain-of-action-setting.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/task-routing-on-olympusbench-chain-of-action-setting.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/task-routing-on-olympusbench-chain-of-action-setting.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Exact Difference (ED) | Result date | Report paper |
| --- | --- | --- | --- |
| Olympus | 18 | Not recorded | 68fa77c11e209131cea751a4 |
| HuggingGPT | 35 | Not recorded | 68fa77c11e209131cea751a4 |
| HuggingGPT | 45 | Not recorded | 68fa77c11e209131cea751a4 |

### Olympus

Exact Difference (ED): 18. Result ID: 699565543badfaffe658740c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77c11e209131cea751a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77c11e209131cea751a4.md>)

[Implementation](<http://yuanze-lin.me/Olympus_page/>)

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

### HuggingGPT

Exact Difference (ED): 35. Result ID: 699565543badfaffe658740b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77c11e209131cea751a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71551e209131cea5091f.md>)

[Implementation](<https://github.com/microsoft/JARVIS>)

Recorded evaluation configuration: {"backbone":"GPT-4o"}. This record does not assert independent reproduction.

### HuggingGPT

Exact Difference (ED): 45. Result ID: 699565543badfaffe658740a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77c11e209131cea751a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71551e209131cea5091f.md>)

[Implementation](<https://github.com/microsoft/JARVIS>)

Recorded evaluation configuration: {"backbone":"GPT-4o mini"}. This record does not assert independent reproduction.

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