# Original Tasks on tau-Bench Airline domain extended

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

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

Data updated: 2026-04-20T06:55:05.703Z

Evaluation of model performance on the set of Original Tasks defined within the extended version of the tau-Bench Airline domain dataset, reporting pass rates at various thresholds (1, 2, 3, and 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) | tau-Bench Airline domain extended |
| Metric | Pass Rate @ Threshold 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 Rate @ Threshold 1](<https://www.sota2.com/research/sota/original-tasks-on-tau-bench-airline-domain-extended.md?metric=Pass%20Rate%20%40%20Threshold%201>): Higher is better; unit: PERCENT.

- [Pass Rate @ Threshold 2](<https://www.sota2.com/research/sota/original-tasks-on-tau-bench-airline-domain-extended.md?metric=Pass%20Rate%20%40%20Threshold%202>): Higher is better; unit: PERCENT.

- [Pass Rate @ Threshold 3](<https://www.sota2.com/research/sota/original-tasks-on-tau-bench-airline-domain-extended.md?metric=Pass%20Rate%20%40%20Threshold%203>): Higher is better; unit: PERCENT.

- [Pass Rate @ Threshold 4](<https://www.sota2.com/research/sota/original-tasks-on-tau-bench-airline-domain-extended.md?metric=Pass%20Rate%20%40%20Threshold%204>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass Rate @ Threshold 1 | Result date | Report paper |
| --- | --- | --- | --- |
| ReasoningBank | 70 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| PolicyBank | 70 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| ReasoningBank | 69 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| PolicyBank | 69 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| Synapse | 67 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| AWM | 67 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| AWM | 67 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| No memory | 66 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| No memory | 62 | Not recorded | 69e5b30a7d0172140ec7dfa4 |
| Synapse | 62 | Not recorded | 69e5b30a7d0172140ec7dfa4 |

### ReasoningBank

Pass Rate @ Threshold 1: 70. Result ID: 69e5cdab47f34ce924cb7290.

[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.

### PolicyBank

Pass Rate @ Threshold 1: 70. Result ID: 69e5cdab47f34ce924cb7291.

[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.

### ReasoningBank

Pass Rate @ Threshold 1: 69. Result ID: 69e5cdab47f34ce924cb7295.

[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 Rate @ Threshold 1: 69. Result ID: 69e5cdab47f34ce924cb7296.

[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.

### Synapse

Pass Rate @ Threshold 1: 67. Result ID: 69e5cdab47f34ce924cb728e.

[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.

### AWM

Pass Rate @ Threshold 1: 67. Result ID: 69e5cdab47f34ce924cb728f.

[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.

### AWM

Pass Rate @ Threshold 1: 67. Result ID: 69e5cdab47f34ce924cb7294.

[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 Rate @ Threshold 1: 66. Result ID: 69e5cdab47f34ce924cb728d.

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

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

### No memory

Pass Rate @ Threshold 1: 62. Result ID: 69e5cdab47f34ce924cb7292.

[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.

### Synapse

Pass Rate @ Threshold 1: 62. Result ID: 69e5cdab47f34ce924cb7293.

[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.

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