Test Run
courtroom-drama-defense-and-prosecution-teams-characters-thurgood-marshall-20251029T114849485359
Completed
Started
Oct 29, 2025 11:48
Completed
Oct 29, 2025 11:50
Model Results
| Model | Performance | Status | Actions |
|---|---|---|---|
|
[email protected]/Qwen3-8B-b0d7af1f
AI Language Model
|
0.596
|
Completed |
Run Details
Judge Model
meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
Generator Models (1)
Execution Time
0 minutes
Quick Stats
1
Models Tested
6
Scenes Executed
Average Performance
0.60
Scene Results
| Scene | Name | Score | Result | Model |
|---|---|---|---|---|
client-intro
|
First meeting with new client
Test scenario
|
0.552
|
Failed
|
[email protected]/Qwe… |
discovery-dispute
|
Discovery standoff with prosecutor
Test scenario
|
0.777
|
Failed
|
[email protected]/Qwe… |
plea-offer
|
Evaluating a plea bargain
Test scenario
|
0.621
|
Failed
|
[email protected]/Qwe… |
opening-statement
|
Courtroom opening statement (long-form)
Test scenario
|
0.526
|
Failed
|
[email protected]/Qwe… |
case-journal
|
End-of-day journal reflection (long-form)
Test scenario
|
0.501
|
Failed
|
[email protected]/Qwe… |
rights-explainer
|
Public question on Miranda rights
Test scenario
|
0.602
|
Failed
|
[email protected]/Qwe… |
Performance Matrix 6×1
| Scene | onteripaul@gma… |
|---|---|
client-intro
First meeting with new client
|
0.552
Details |
discovery-dispute
Discovery standoff with prose…
|
0.777
Details |
plea-offer
Evaluating a plea bargain
|
0.621
Details |
opening-statement
Courtroom opening statement (…
|
0.526
Details |
case-journal
End-of-day journal reflection…
|
0.501
Details |
rights-explainer
Public question on Miranda ri…
|
0.602
Details |