Admin › Evaluation › Feedback

Feedback Records
Each row is one evaluation.| Column | Description |
|---|---|
| User | User who left the evaluation |
| Model | Evaluated model (in Arena comparisons, multiple models are shown together — and N more) |
| Result | Win or Loss |
| Updated at | Last update time |
⋯ menu to manage individual records. The list is paginated.
Export and Share
| Feature | Location |
|---|---|
| Export | Download icon at the top right |
| Community share | The Share to OpenWebUI Community button at the bottom |
Community share sends feedback records to the external OpenWebUI community leaderboard. Because internal data leaves your organization, check your organization’s policy before sharing.
Use Cases
Comparing Model Quality
Comparing Model Quality
- Identify models/agents with many losses in the feedback records
- Check the evaluation rankings across models in the Leaderboard
- Analyze the cause of low-rated responses with Tracing
- After improving the prompt and Knowledge Base, check the score change in Auto-Evaluations
Related Pages
Evaluation
Full overview and guide to evaluation methods
Auto-Evaluations
Automatic quality scoring by a judge LLM
Tracing
Follow the trace of an evaluated response
