# Sister Tasks on extended tau-Bench Airline domain

Source: [Sister Tasks on extended tau-Bench Airline domain](<https://www.sota2.com/research/sota/sister-tasks-on-extended-tau-bench-airline-domain>)

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

Data updated: 2026-04-20T06:55:05.676Z

Evaluation of model performance on 'Sister Tasks' within the extended Airline domain subset of tau-Bench, measured by multi-step pass rates (pass^1 to pass^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 | Sister Tasks |
| Dataset (including any stated split) | extended tau-Bench Airline domain |
| Metric | Pass@1 Rate |
| 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 Rate](<https://www.sota2.com/research/sota/sister-tasks-on-extended-tau-bench-airline-domain.md?metric=Pass%401%20Rate>): Higher is better; unit: PERCENT.

- [Pass@2 Rate](<https://www.sota2.com/research/sota/sister-tasks-on-extended-tau-bench-airline-domain.md?metric=Pass%402%20Rate>): Higher is better; unit: PERCENT.

- [Pass@3 Rate](<https://www.sota2.com/research/sota/sister-tasks-on-extended-tau-bench-airline-domain.md?metric=Pass%403%20Rate>): Higher is better; unit: PERCENT.

- [Pass@4 Rate](<https://www.sota2.com/research/sota/sister-tasks-on-extended-tau-bench-airline-domain.md?metric=Pass%404%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@1 Rate | Result date | Report paper |
| --- | --- | --- | --- |
| PolicyBank | 74 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| PolicyBank | 72 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| ReasoningBank | 45 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| Synapse | 33 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| AWM | 31 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| No memory | 30 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| ReasoningBank | 23 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| Synapse | 2 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| No memory | 1 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| AWM | 1 | Not recorded | 69e5b30a7d0172140ec7dfa4 |

### PolicyBank

Pass@1 Rate: 74. Result ID: 69e5cdab47f34ce924cb7287.

[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.

### PolicyBank

Pass@1 Rate: 72. Result ID: 69e5cdab47f34ce924cb728c.

[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 Rate: 45. Result ID: 69e5cdab47f34ce924cb728b.

[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.

### Synapse

Pass@1 Rate: 33. Result ID: 69e5cdab47f34ce924cb7289.

[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.

### AWM

Pass@1 Rate: 31. Result ID: 69e5cdab47f34ce924cb728a.

[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.

### No memory

Pass@1 Rate: 30. Result ID: 69e5cdab47f34ce924cb7288.

[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.

### ReasoningBank

Pass@1 Rate: 23. Result ID: 69e5cdab47f34ce924cb7286.

[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.

### Synapse

Pass@1 Rate: 2. Result ID: 69e5cdab47f34ce924cb7284.

[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.

### No memory

Pass@1 Rate: 1. Result ID: 69e5cdab47f34ce924cb7283.

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

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

### AWM

Pass@1 Rate: 1. Result ID: 69e5cdab47f34ce924cb7285.

[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.

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