api-contract-validator / baseline_72b_v2_scores.json
pushpam14's picture
Add baseline_72b_v2_scores.json for judges to inspect from Space repo root
9c794e4 verified
Raw
History Blame Contribute Delete
2.74 kB
{
"model": "Qwen/Qwen2.5-72B-Instruct",
"benchmark": "api_contract_validator",
"date": "2026-04-26",
"scores": {
"find_type_mismatches": 0.75,
"validate_nested_objects": 0.99,
"detect_breaking_changes": 0.01,
"validate_response_schema": 0.99,
"validate_cross_field_constraints": 0.99,
"validate_auth_request": 0.99,
"trace_downstream_blast_radius": 0.6667,
"propose_backward_compat_fix": 0.99,
"multi_service_cascade_fix": 0.99
},
"details": [
{
"task": "find_type_mismatches",
"score": 0.75,
"steps": 5,
"success": true,
"rewards": [
1.0,
1.0,
1.0,
-0.1,
0.375
]
},
{
"task": "validate_nested_objects",
"score": 0.99,
"steps": 12,
"success": true,
"rewards": [
1.0,
1.0,
1.0,
1.0,
1.0,
-0.3,
1.0,
-0.3,
-0.3,
-0.3,
-0.5,
1.0
]
},
{
"task": "detect_breaking_changes",
"score": 0.01,
"steps": 20,
"success": false,
"rewards": [
0.3,
0.3,
0.3,
0.3,
0.3,
0.3,
-0.3,
-0.3,
-0.3,
-0.3,
-0.3,
-0.3,
-0.3,
-0.3,
-0.3,
-0.3,
-0.3,
-0.3,
-0.3,
-0.3
]
},
{
"task": "validate_response_schema",
"score": 0.99,
"steps": 10,
"success": true,
"rewards": [
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0
]
},
{
"task": "validate_cross_field_constraints",
"score": 0.99,
"steps": 8,
"success": true,
"rewards": [
1.0,
1.0,
-0.3,
1.0,
1.0,
1.0,
1.0,
1.0
]
},
{
"task": "validate_auth_request",
"score": 0.99,
"steps": 10,
"success": true,
"rewards": [
1.0,
1.0,
1.0,
1.0,
1.0,
-0.3,
-0.3,
-0.3,
-0.5,
1.0
]
},
{
"task": "trace_downstream_blast_radius",
"score": 0.6667,
"steps": 1,
"success": true,
"rewards": [
0.1
]
},
{
"task": "propose_backward_compat_fix",
"score": 0.99,
"steps": 1,
"success": true,
"rewards": [
2.0
]
},
{
"task": "multi_service_cascade_fix",
"score": 0.99,
"steps": 3,
"success": true,
"rewards": [
1.6,
-2.0,
2.0
]
}
]
}