Project overview
·
Total runs
49
6 this week
Pass rate
91%
Avg 87% · +4 pts
Score
0.94
Avg 0.89 · +0.05
Active test plans
3
1 awaiting review
Pass rate trend
Last 10 completed runs · ,
Metric scores
Latest run · ,
Recent test runs
Across all test plans in this project
| Run | Dataset | Method | Score | Verdict | Date |
|---|
Workspaces
Projects
VerdictThirdAct Labs
BS
New project
VerdictThirdAct Labs
BS
New workspace
VerdictThirdAct Labs
BS
1 Dataset
2 Metric
3 Rubric
4 Test plan
5 Score & log
·
Dataset
VerdictThirdAct Labs
BS
1 Dataset
2 Metric
3 Rubric
4 Test plan
5 Score & log
·
Metric
VerdictThirdAct Labs
BS
1 Dataset
2 Metric
3 Rubric
4 Test plan
5 Score & log
·
Rubric
VerdictThirdAct Labs
BS
1 Dataset
2 Metric
3 Rubric
4 Test plan
5 Score & log
·
Test plan
Estimates assume the dataset and methods above; actual cost and time vary with response length.
Custom run configuration
Dataset sample
LLM judge passes (default)
Passes are aggregated via majority vote (Pass/Fail metrics) or averaged (numeric scores).
Per-metric overrides
Leave a metric on Default to use the passes setting above.
1 Dataset
2 Metric
3 Rubric
4 Test plan
5 Score & log
·
Run
Results by metric
Every metric assigned to this test plan, and how it scored
| Metric | Category | Method | Score | Verdict |
|---|
Case log
A sample of individual cases from this run
| Case | Metric | Score | Verdict |
|---|
·
Datasets
VerdictThirdAct Labs
BS
workspace library
New dataset
1 Upload
2 Features
3 Generate
Generate from
Document .pdf, .docx, .md, .txt
Verdict reads the uploaded file and proposes the distinct features it finds worth testing for — you'll review and adjust them next.
Extracted features
Feature summary
Test cases per feature
·
Metrics
VerdictThirdAct Labs
BS
workspace library
New metric
·
Test plans
·
Test runs
| Run | Dataset | Method | Score | Verdict | Date |
|---|
1 Dataset
2 Metric
3 Rubric
4 Test plan
5 Score & log
·
Run
Running — 0% complete
0 / 0 cases
Results by metric
Updating as the run progresses
| Metric | Category | Method | Score | Verdict |
|---|
Case log
A sample of cases as they resolve
| Case | Metric | Score | Verdict |
|---|