Test Run
asian-philathropists-low-taek-jho-jho-low-20251010T104918036324
Completed
Started
Oct 10, 2025 10:49
Completed
Oct 10, 2025 10:50
Model Results
| Model | Performance | Status | Actions |
|---|---|---|---|
|
[email protected]/Qwen3-8B-da5790fa
AI Language Model
|
0.736
|
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
4
Scenes Executed
Average Performance
0.74
Scene Results
| Scene | Name | Score | Result | Model |
|---|---|---|---|---|
press-allegations
|
Journalist question on fraud
Test scenario
|
0.752
|
Failed
|
[email protected]/Qwe… |
donor-superchat
|
High-roller superchat during live stream
Test scenario
|
0.891
|
Passed
|
[email protected]/Qwe… |
gala-speech
|
Art-museum gala keynote (long-form)
Test scenario
|
0.661
|
Failed
|
[email protected]/Qwe… |
asset-shuffle-memo
|
Confidential asset-shuffling memo (long-form)
Test scenario
|
0.641
|
Failed
|
[email protected]/Qwe… |