# Benign Workflow Completion on 82 stress-test suite (26 benign tasks)

Source: [Benign Workflow Completion on 82 stress-test suite (26 benign tasks)](<https://www.sota2.com/research/sota/benign-workflow-completion-on-82-stress-test-suite-26-benign-tasks>)

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

Data updated: 2026-05-27T08:30:36.656Z

Evaluation of model performance on completing benign workflows within the 82 stress-test suite, measured by the Benign completion rate.

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 | Benign Workflow Completion |
| Dataset (including any stated split) | 82 stress-test suite (26 benign tasks) |
| Metric | Benign Completion 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

- [Benign Completion Rate](<https://www.sota2.com/research/sota/benign-workflow-completion-on-82-stress-test-suite-26-benign-tasks.md?metric=Benign%20Completion%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Benign Completion Rate | Result date | Report paper |
| --- | --- | --- | --- |
| Sonnet 4 | 100 | Not recorded | 6a167ab1dbd7150506f8012a |
| ChainCaps | 100 | Not recorded | 6a167ab1dbd7150506f8012a |
| Sonnet 4.6 | 100 | Not recorded | 6a167ab1dbd7150506f8012a |
| ChainCaps | 100 | Not recorded | 6a167ab1dbd7150506f8012a |
| Opus 4.6 | 100 | Not recorded | 6a167ab1dbd7150506f8012a |
| GPT-5.1 | 100 | Not recorded | 6a167ab1dbd7150506f8012a |
| ChainCaps | 100 | Not recorded | 6a167ab1dbd7150506f8012a |
| Qwen 3.5 | 100 | Not recorded | 6a167ab1dbd7150506f8012a |
| ChainCaps | 96 | Not recorded | 6a167ab1dbd7150506f8012a |
| ChainCaps | 96 | Not recorded | 6a167ab1dbd7150506f8012a |

### Sonnet 4

Benign Completion Rate: 100. Result ID: 6a16aaa4fbc373592c0fc759.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

Recorded evaluation configuration: {"ChainCaps":"false"}. This record does not assert independent reproduction.

### ChainCaps

Benign Completion Rate: 100. Result ID: 6a16aaa4fbc373592c0fc75a.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

Recorded evaluation configuration: {"Model":"Sonnet 4","ChainCaps":"true"}. This record does not assert independent reproduction.

### Sonnet 4.6

Benign Completion Rate: 100. Result ID: 6a16aaa4fbc373592c0fc75b.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

Recorded evaluation configuration: {"ChainCaps":"false"}. This record does not assert independent reproduction.

### ChainCaps

Benign Completion Rate: 100. Result ID: 6a16aaa4fbc373592c0fc75c.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

Recorded evaluation configuration: {"Model":"Sonnet 4.6","ChainCaps":"true"}. This record does not assert independent reproduction.

### Opus 4.6

Benign Completion Rate: 100. Result ID: 6a16aaa4fbc373592c0fc75d.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

Recorded evaluation configuration: {"ChainCaps":"false"}. This record does not assert independent reproduction.

### GPT-5.1

Benign Completion Rate: 100. Result ID: 6a16aaa4fbc373592c0fc75f.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

Recorded evaluation configuration: {"ChainCaps":"false"}. This record does not assert independent reproduction.

### ChainCaps

Benign Completion Rate: 100. Result ID: 6a16aaa4fbc373592c0fc760.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

Recorded evaluation configuration: {"Model":"GPT-5.1","ChainCaps":"true"}. This record does not assert independent reproduction.

### Qwen 3.5

Benign Completion Rate: 100. Result ID: 6a16aaa4fbc373592c0fc761.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

Recorded evaluation configuration: {"ChainCaps":"false"}. This record does not assert independent reproduction.

### ChainCaps

Benign Completion Rate: 96. Result ID: 6a16aaa4fbc373592c0fc75e.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

Recorded evaluation configuration: {"Model":"Opus 4.6","ChainCaps":"true"}. This record does not assert independent reproduction.

### ChainCaps

Benign Completion Rate: 96. Result ID: 6a16aaa4fbc373592c0fc762.

[Reporting paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167ab1dbd7150506f8012a.md>)

Recorded evaluation configuration: {"Model":"Qwen 3.5","ChainCaps":"true"}. This record does not assert independent reproduction.

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