glayguo's picture
Publish verified EvalArc 19ac9d8a5cb8
6c4b387 verified
Raw History Blame Contribute Delete
2.53 kB
{
"schema": "evalarc.skill-context-results.v1",
"trials": [
{
"path": "relevant/01-mcp-17",
"condition": "mcp",
"seed": 17,
"status": "finished",
"error": null,
"evaluation": {
"valid": true,
"resolved": false,
"score": 0.875,
"status": "failed"
},
"elapsed_seconds": 129.58972599398112,
"completion_tokens": 2761,
"skill_loads": 1,
"context_condition": "relevant"
},
{
"path": "neutral/02-mcp-17",
"condition": "mcp",
"seed": 17,
"status": "finished",
"error": null,
"evaluation": {
"valid": true,
"resolved": false,
"score": 0.0,
"status": "failed"
},
"elapsed_seconds": 4.846057314018253,
"completion_tokens": 54,
"skill_loads": 1,
"context_condition": "neutral"
},
{
"path": "neutral/03-mcp-41",
"condition": "mcp",
"seed": 41,
"status": "finished",
"error": null,
"evaluation": {
"valid": true,
"resolved": false,
"score": 0.0,
"status": "failed"
},
"elapsed_seconds": 4.803827599971555,
"completion_tokens": 54,
"skill_loads": 1,
"context_condition": "neutral"
},
{
"path": "relevant/04-mcp-41",
"condition": "mcp",
"seed": 41,
"status": "finished",
"error": null,
"evaluation": {
"valid": true,
"resolved": false,
"score": 0.875,
"status": "failed"
},
"elapsed_seconds": 130.9857094649924,
"completion_tokens": 2761,
"skill_loads": 1,
"context_condition": "relevant"
},
{
"path": "relevant/05-mcp-97",
"condition": "mcp",
"seed": 97,
"status": "finished",
"error": null,
"evaluation": {
"valid": true,
"resolved": false,
"score": 0.875,
"status": "failed"
},
"elapsed_seconds": 123.34076337999431,
"completion_tokens": 2631,
"skill_loads": 1,
"context_condition": "relevant"
},
{
"path": "neutral/06-mcp-97",
"condition": "mcp",
"seed": 97,
"status": "finished",
"error": null,
"evaluation": {
"valid": true,
"resolved": false,
"score": 0.0,
"status": "failed"
},
"elapsed_seconds": 4.8277259189635515,
"completion_tokens": 54,
"skill_loads": 1,
"context_condition": "neutral"
}
]
}