41 lines
898 B
Markdown
41 lines
898 B
Markdown
# Web URL Support Test Results
|
|
|
|
## Highscores
|
|
|
|
### Performance Rankings (Duration)
|
|
|
|
| Test | Model | Duration (ms) | Duration (s) |
|
|
|------|-------|--------------|--------------|
|
|
| web_wikipedia | openai/gpt-3.5-turbo | 771 | 0.77 |
|
|
| web_json | openai/gpt-3.5-turbo | 623 | 0.62 |
|
|
|
|
## Summary
|
|
|
|
- Total Tests: 2
|
|
- Passed: 1
|
|
- Failed: 1
|
|
- Success Rate: 50.00%
|
|
- Average Duration: 697ms (0.70s)
|
|
|
|
## Failed Tests
|
|
|
|
### web_wikipedia - openai/gpt-3.5-turbo
|
|
|
|
- Prompt: `Does the content have information about Kenya? Answer with only "yes" or "no".`
|
|
- Expected: `yes`
|
|
- Actual: ``
|
|
- Duration: 771ms (0.77s)
|
|
- Reason: Model returned empty response
|
|
- Timestamp: 6/5/2025, 8:46:07 PM
|
|
|
|
## Passed Tests
|
|
|
|
### web_json - openai/gpt-3.5-turbo
|
|
|
|
- Prompt: `Is this data in JSON format? Answer with only "yes" or "no".`
|
|
- Expected: `yes`
|
|
- Actual: `Yes`
|
|
- Duration: 623ms (0.62s)
|
|
- Timestamp: 6/5/2025, 8:46:09 PM
|
|
|