Test Run
agent-raven-v1-20251216T000312895941
Completed
Test Suite:
agent-raven-v1 - Raven
Started
Dec 16, 2025 00:03
Completed
Dec 16, 2025 00:03
Model Results
| Model | Performance | Status | Actions |
|---|---|---|---|
|
meta-llama/llama-3.1-8b-instruct
AI Language Model
|
0.605
|
Completed | |
|
mistralai/mistral-7b-instruct
AI Language Model
|
0.728
|
Completed | |
|
qwen/qwen-2.5-7b-instruct
AI Language Model
|
0.693
|
Completed | |
|
qwen/qwen3-14b
AI Language Model
|
0.819
|
Completed | |
|
qwen/qwen3-8b
AI Language Model
|
0.684
|
Completed |
Run Details
Judge Model
openai/gpt-5-mini
Generator Models (5)
qwen/qwen-2.5-7b-in…
qwen/qwen3-14b
qwen/qwen3-8b
mistralai/mistral-7…
meta-llama/llama-3.…
Execution Time
0 minutes
Quick Stats
5
Models Tested
0
Scenes Executed
Average Performance
0.61
Scene Results
| Scene | Name | Score | Result | Model |
|---|---|---|---|---|
|
No scene results found |
||||