65 lines
2.1 KiB
JSON
65 lines
2.1 KiB
JSON
{
|
|
"results": [
|
|
{
|
|
"test": "cad-research",
|
|
"prompt": "List popular open source CAD software. Return as JSON array.",
|
|
"result": [],
|
|
"expected": "[\"freecad\"]",
|
|
"model": "perplexity/sonar-deep-research",
|
|
"router": "perplexity/sonar-deep-research",
|
|
"timestamp": "2025-04-06T14:46:55.097Z",
|
|
"passed": false,
|
|
"duration": 30014,
|
|
"error": {
|
|
"message": "API call timed out",
|
|
"code": "UNKNOWN",
|
|
"type": "Error",
|
|
"details": {
|
|
"stack": "Error: API call timed out\n at Timeout._onTimeout (C:\\Users\\zx\\Desktop\\polymech\\polymech-mono\\packages\\kbot\\tests\\unit\\commons.ts:211:33)\n at listOnTimeout (node:internal/timers:594:17)\n at processTimers (node:internal/timers:529:7)",
|
|
"message": "API call timed out"
|
|
}
|
|
},
|
|
"reason": "API call timed out",
|
|
"category": "research"
|
|
},
|
|
{
|
|
"test": "cad-research",
|
|
"prompt": "List popular open source CAD software. Return as JSON array.",
|
|
"result": [],
|
|
"expected": "{\"software\":[\"freecad\"]}",
|
|
"model": "perplexity/sonar-deep-research",
|
|
"router": "perplexity/sonar-deep-research",
|
|
"timestamp": "2025-04-06T14:48:25.213Z",
|
|
"passed": false,
|
|
"duration": 45812,
|
|
"reason": "Model returned empty response",
|
|
"category": "research"
|
|
},
|
|
{
|
|
"test": "cad-research",
|
|
"prompt": "List at least 3 popular open source CAD software. Include FreeCAD in your answer. Return as JSON.",
|
|
"result": [],
|
|
"expected": "{\"software\":[\"freecad\"]}",
|
|
"model": "perplexity/sonar-deep-research",
|
|
"router": "perplexity/sonar-deep-research",
|
|
"timestamp": "2025-04-06T14:49:47.076Z",
|
|
"passed": false,
|
|
"duration": 47027,
|
|
"reason": "Model returned empty response",
|
|
"category": "research"
|
|
}
|
|
],
|
|
"highscores": [
|
|
{
|
|
"test": "cad-research",
|
|
"rankings": [
|
|
{
|
|
"model": "perplexity/sonar-deep-research",
|
|
"duration": 47027,
|
|
"duration_secs": 47.027
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"lastUpdated": "2025-04-06T14:49:47.077Z"
|
|
} |