# Multi-turn Enterprise IT Support Diagnosis on 150 Enterprise IT Support Scenarios (test)

Source: [Multi-turn Enterprise IT Support Diagnosis on 150 Enterprise IT Support Scenarios (test)](<https://www.sota2.com/research/sota/multi-turn-enterprise-it-support-diagnosis-on-150-enterprise-it-support-scenarios-test>)

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

Data updated: 2026-04-08T08:08:29.133Z

Evaluation of model performance on diagnosing and resolving multi-turn enterprise IT support issues using the test split of the 150 enterprise IT support scenarios dataset. Metrics focus on success rate, diagnosis/resolution completeness, and interaction efficiency.

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 | Multi-turn enterprise IT support diagnosis |
| Dataset (including any stated split) | 150 enterprise IT support scenarios (test) |
| Metric | Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Success Rate](<https://www.sota2.com/research/sota/multi-turn-enterprise-it-support-diagnosis-on-150-enterprise-it-support-scenarios-test.md?metric=Success%20Rate>): Higher is better; unit: PERCENT.

- [Diagnosis Completeness](<https://www.sota2.com/research/sota/multi-turn-enterprise-it-support-diagnosis-on-150-enterprise-it-support-scenarios-test.md?metric=Diagnosis%20Completeness>): Higher is better; unit: PERCENT.

- [Resolution Completeness](<https://www.sota2.com/research/sota/multi-turn-enterprise-it-support-diagnosis-on-150-enterprise-it-support-scenarios-test.md?metric=Resolution%20Completeness>): Higher is better; unit: PERCENT.

- [Avg Interaction Turns](<https://www.sota2.com/research/sota/multi-turn-enterprise-it-support-diagnosis-on-150-enterprise-it-support-scenarios-test.md?metric=Avg%20Interaction%20Turns>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| DQA | 78.7 | Not recorded | 69d5e0e97d0172140ec758e1 |
| RAG + Clustering | 53.8 | Not recorded | 69d5e0e97d0172140ec758e1 |
| RAG (baseline) | 41.3 | Not recorded | 69d5e0e97d0172140ec758e1 |
| RAG (no CQR) | 40.4 | Not recorded | 69d5e0e97d0172140ec758e1 |

### DQA

Success Rate: 78.7. Result ID: 69d60cf347f34ce924be7766.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0e97d0172140ec758e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d5e0e97d0172140ec758e1.md>)

Recorded evaluation configuration: {"System configuration":"Full DQA system with persistent state"}. This record does not assert independent reproduction.

### RAG + Clustering

Success Rate: 53.8. Result ID: 69d60cf347f34ce924be7765.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0e97d0172140ec758e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b91e209131cea23c26.md>)

[Implementation](<https://github.com/huggingface/transformers/blob/master/examples/rag/>)

Recorded evaluation configuration: {"System configuration":"Retrieval aggregation via clustering"}. This record does not assert independent reproduction.

### RAG (baseline)

Success Rate: 41.3. Result ID: 69d60cf347f34ce924be7764.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0e97d0172140ec758e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b91e209131cea23c26.md>)

[Implementation](<https://github.com/huggingface/transformers/blob/master/examples/rag/>)

Recorded evaluation configuration: {"System configuration":"Baseline RAG"}. This record does not assert independent reproduction.

### RAG (no CQR)

Success Rate: 40.4. Result ID: 69d60cf347f34ce924be7763.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0e97d0172140ec758e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b91e209131cea23c26.md>)

[Implementation](<https://github.com/huggingface/transformers/blob/master/examples/rag/>)

Recorded evaluation configuration: {"System configuration":"No CQR"}. This record does not assert independent reproduction.

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