# Task failure prediction and selective task completion on tau2-bench Telecom 1.0

Source: [Task failure prediction and selective task completion on tau2-bench Telecom 1.0](<https://www.sota2.com/research/sota/task-failure-prediction-and-selective-task-completion-on-tau2-bench-telecom-1-0>)

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

Data updated: 2026-02-26T05:26:04.418Z

Evaluation of model performance on predicting task failures and enabling selective task completion using AUROC and AUARC metrics on the tau2-bench Telecom 1.0 dataset.

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 failure prediction and selective task completion |
| Dataset (including any stated split) | tau2-bench Telecom 1.0 |
| Metric | AUROC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [AUROC](<https://www.sota2.com/research/sota/task-failure-prediction-and-selective-task-completion-on-tau2-bench-telecom-1-0.md?metric=AUROC>): Higher is better; unit: SCALAR.

- [AUARC](<https://www.sota2.com/research/sota/task-failure-prediction-and-selective-task-completion-on-tau2-bench-telecom-1-0.md?metric=AUARC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| TRACER | 0.809 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| TRACER | 0.765 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| TRACER | 0.691 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| Semantic Entropy | 0.686 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| Self-Assessed Confidence | 0.683 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| SAUP | 0.673 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| Semantic Entropy | 0.651 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| Normalized Entropy | 0.649 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| SAUP | 0.639 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| Semantic Entropy | 0.621 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| Normalized Entropy | 0.559 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| Normalized Entropy | 0.548 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| SAUP | 0.534 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| Self-Assessed Confidence | 0.507 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |
| Self-Assessed Confidence | 0.423 | Not recorded | 698eafe9c97a0b3e3b5e65a5 |

### TRACER

AUROC: 0.809. Result ID: 6995f42e5698665ec4277d35.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### TRACER

AUROC: 0.765. Result ID: 6995f42e5698665ec4277d3a.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gpt-4.1-mini"}. This record does not assert independent reproduction.

### TRACER

AUROC: 0.691. Result ID: 6995f42e5698665ec4277d30.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gemini-2.5-pro"}. This record does not assert independent reproduction.

### Semantic Entropy

AUROC: 0.686. Result ID: 6995f42e5698665ec4277d38.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gpt-4.1-mini"}. This record does not assert independent reproduction.

### Self-Assessed Confidence

AUROC: 0.683. Result ID: 6995f42e5698665ec4277d37.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gpt-4.1-mini"}. This record does not assert independent reproduction.

### SAUP

AUROC: 0.673. Result ID: 6995f42e5698665ec4277d34.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### Semantic Entropy

AUROC: 0.651. Result ID: 6995f42e5698665ec4277d2e.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gemini-2.5-pro"}. This record does not assert independent reproduction.

### Normalized Entropy

AUROC: 0.649. Result ID: 6995f42e5698665ec4277d2c.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gemini-2.5-pro"}. This record does not assert independent reproduction.

### SAUP

AUROC: 0.639. Result ID: 6995f42e5698665ec4277d2f.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gemini-2.5-pro"}. This record does not assert independent reproduction.

### Semantic Entropy

AUROC: 0.621. Result ID: 6995f42e5698665ec4277d33.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### Normalized Entropy

AUROC: 0.559. Result ID: 6995f42e5698665ec4277d31.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### Normalized Entropy

AUROC: 0.548. Result ID: 6995f42e5698665ec4277d36.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gpt-4.1-mini"}. This record does not assert independent reproduction.

### SAUP

AUROC: 0.534. Result ID: 6995f42e5698665ec4277d39.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gpt-4.1-mini"}. This record does not assert independent reproduction.

### Self-Assessed Confidence

AUROC: 0.507. Result ID: 6995f42e5698665ec4277d2d.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gemini-2.5-pro"}. This record does not assert independent reproduction.

### Self-Assessed Confidence

AUROC: 0.423. Result ID: 6995f42e5698665ec4277d32.

[Reporting paper](<https://www.sota2.com/research/paper/698eafe9c97a0b3e3b5e65a5.md>)

Recorded evaluation configuration: {"Model":"gemini-2.5-flash"}. This record does not assert independent reproduction.

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