# Original Tasks on extended tau-Bench Retail domain

Source: [Original Tasks on extended tau-Bench Retail domain](<https://www.sota2.com/research/sota/original-tasks-on-extended-tau-bench-retail-domain>)

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

Data updated: 2026-04-20T06:55:05.746Z

Evaluation of model performance on the Original Tasks defined within the extended Retail domain subset of the tau-Bench dataset, measured by pass rates at thresholds 1 through 4.

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 | Original Tasks |
| Dataset (including any stated split) | extended tau-Bench Retail domain |
| Metric | Pass@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Pass@1](<https://www.sota2.com/research/sota/original-tasks-on-extended-tau-bench-retail-domain.md?metric=Pass%401>): Higher is better; unit: PERCENT.

- [Pass@2](<https://www.sota2.com/research/sota/original-tasks-on-extended-tau-bench-retail-domain.md?metric=Pass%402>): Higher is better; unit: PERCENT.

- [Pass@3](<https://www.sota2.com/research/sota/original-tasks-on-extended-tau-bench-retail-domain.md?metric=Pass%403>): Higher is better; unit: PERCENT.

- [Pass@4](<https://www.sota2.com/research/sota/original-tasks-on-extended-tau-bench-retail-domain.md?metric=Pass%404>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@1 | Result date | Report paper |
| --- | --- | --- | --- |
| ReasoningBank | 90 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| PolicyBank | 89 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| ReasoningBank | 87 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| No memory | 87 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| AWM | 87 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| AWM | 85 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| PolicyBank | 85 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| Synapse | 85 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| No memory | 82 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| Synapse | 81 | Not recorded | 69e5b30a7d0172140ec7dfa4 |

### ReasoningBank

Pass@1: 90. Result ID: 69e5cdab47f34ce924cb72a9.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7dfa4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7baf1e209131cea89df5.md>)

Recorded evaluation configuration: {"Model":"Claude-4.5-Opus"}. This record does not assert independent reproduction.

### PolicyBank

Pass@1: 89. Result ID: 69e5cdab47f34ce924cb72aa.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7dfa4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7dfa4.md>)

Recorded evaluation configuration: {"Model":"Claude-4.5-Opus"}. This record does not assert independent reproduction.

### ReasoningBank

Pass@1: 87. Result ID: 69e5cdab47f34ce924cb72a4.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7dfa4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7baf1e209131cea89df5.md>)

Recorded evaluation configuration: {"Model":"Gemini-3-Pro"}. This record does not assert independent reproduction.

### No memory

Pass@1: 87. Result ID: 69e5cdab47f34ce924cb72a6.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7dfa4.md>)

Recorded evaluation configuration: {"Model":"Claude-4.5-Opus"}. This record does not assert independent reproduction.

### AWM

Pass@1: 87. Result ID: 69e5cdab47f34ce924cb72a8.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7dfa4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74cb1e209131cea63e3b.md>)

Recorded evaluation configuration: {"Model":"Claude-4.5-Opus"}. This record does not assert independent reproduction.

### AWM

Pass@1: 85. Result ID: 69e5cdab47f34ce924cb72a3.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7dfa4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74cb1e209131cea63e3b.md>)

Recorded evaluation configuration: {"Model":"Gemini-3-Pro"}. This record does not assert independent reproduction.

### PolicyBank

Pass@1: 85. Result ID: 69e5cdab47f34ce924cb72a5.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7dfa4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7dfa4.md>)

Recorded evaluation configuration: {"Model":"Gemini-3-Pro"}. This record does not assert independent reproduction.

### Synapse

Pass@1: 85. Result ID: 69e5cdab47f34ce924cb72a7.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7dfa4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d71e209131cea534a8.md>)

Recorded evaluation configuration: {"Model":"Claude-4.5-Opus"}. This record does not assert independent reproduction.

### No memory

Pass@1: 82. Result ID: 69e5cdab47f34ce924cb72a1.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7dfa4.md>)

Recorded evaluation configuration: {"Model":"Gemini-3-Pro"}. This record does not assert independent reproduction.

### Synapse

Pass@1: 81. Result ID: 69e5cdab47f34ce924cb72a2.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7dfa4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d71e209131cea534a8.md>)

Recorded evaluation configuration: {"Model":"Gemini-3-Pro"}. This record does not assert independent reproduction.

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