pushpam14 commited on
Commit
276b91a
·
verified ·
1 Parent(s): 8e3056d

Add baseline_7b_scores.json for judges to inspect from Space repo root

Browse files
Files changed (1) hide show
  1. baseline_7b_scores.json +196 -0
baseline_7b_scores.json ADDED
@@ -0,0 +1,196 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "Qwen/Qwen2.5-7B-Instruct",
3
+ "benchmark": "api_contract_validator",
4
+ "date": "2026-04-26",
5
+ "scores": {
6
+ "find_type_mismatches": 0.75,
7
+ "validate_nested_objects": 0.5714,
8
+ "detect_breaking_changes": 0.01,
9
+ "validate_response_schema": 0.7,
10
+ "validate_cross_field_constraints": 0.4286,
11
+ "validate_auth_request": 0.8333,
12
+ "trace_downstream_blast_radius": 0.99,
13
+ "propose_backward_compat_fix": 0.99,
14
+ "multi_service_cascade_fix": 0.99
15
+ },
16
+ "details": [
17
+ {
18
+ "task": "find_type_mismatches",
19
+ "score": 0.75,
20
+ "steps": 10,
21
+ "success": true,
22
+ "rewards": [
23
+ 1.0,
24
+ -0.1,
25
+ 1.0,
26
+ 1.0,
27
+ -0.3,
28
+ -0.3,
29
+ -0.1,
30
+ -0.1,
31
+ -0.1,
32
+ -0.1
33
+ ]
34
+ },
35
+ {
36
+ "task": "validate_nested_objects",
37
+ "score": 0.5714,
38
+ "steps": 15,
39
+ "success": true,
40
+ "rewards": [
41
+ 1.0,
42
+ 1.0,
43
+ 1.0,
44
+ -0.1,
45
+ -0.1,
46
+ 0.3,
47
+ 1.0,
48
+ -0.1,
49
+ -0.3,
50
+ -0.1,
51
+ -0.1,
52
+ -0.3,
53
+ -0.1,
54
+ -0.1,
55
+ -0.1
56
+ ]
57
+ },
58
+ {
59
+ "task": "detect_breaking_changes",
60
+ "score": 0.01,
61
+ "steps": 20,
62
+ "success": false,
63
+ "rewards": [
64
+ 0.3,
65
+ 0.3,
66
+ 0.3,
67
+ 0.3,
68
+ 0.3,
69
+ -0.3,
70
+ -0.3,
71
+ -0.3,
72
+ -0.3,
73
+ -0.3,
74
+ -0.5,
75
+ -0.3,
76
+ -0.3,
77
+ -0.3,
78
+ -0.3,
79
+ -0.3,
80
+ -0.3,
81
+ -0.3,
82
+ -0.3,
83
+ -0.3
84
+ ]
85
+ },
86
+ {
87
+ "task": "validate_response_schema",
88
+ "score": 0.7,
89
+ "steps": 25,
90
+ "success": true,
91
+ "rewards": [
92
+ 1.0,
93
+ 1.0,
94
+ 1.0,
95
+ 1.0,
96
+ 1.0,
97
+ -0.1,
98
+ -0.1,
99
+ -0.1,
100
+ -0.1,
101
+ -0.1,
102
+ -0.1,
103
+ 0.3,
104
+ -0.1,
105
+ -0.1,
106
+ -0.1,
107
+ -0.1,
108
+ -0.1,
109
+ 1.0,
110
+ -0.1,
111
+ -0.1,
112
+ -0.1,
113
+ -0.1,
114
+ 1.0,
115
+ -0.1,
116
+ -0.1
117
+ ]
118
+ },
119
+ {
120
+ "task": "validate_cross_field_constraints",
121
+ "score": 0.4286,
122
+ "steps": 18,
123
+ "success": true,
124
+ "rewards": [
125
+ 1.0,
126
+ 1.0,
127
+ -0.3,
128
+ -0.3,
129
+ -0.3,
130
+ -0.5,
131
+ 1.0,
132
+ -0.1,
133
+ -0.1,
134
+ -0.1,
135
+ -0.1,
136
+ -0.1,
137
+ -0.1,
138
+ -0.3,
139
+ -0.1,
140
+ -0.3,
141
+ -0.1,
142
+ -0.1
143
+ ]
144
+ },
145
+ {
146
+ "task": "validate_auth_request",
147
+ "score": 0.8333,
148
+ "steps": 14,
149
+ "success": true,
150
+ "rewards": [
151
+ 1.0,
152
+ -0.1,
153
+ 1.0,
154
+ 1.0,
155
+ -0.1,
156
+ 1.0,
157
+ 1.0,
158
+ -0.1,
159
+ -0.1,
160
+ -0.3,
161
+ -0.1,
162
+ -0.1,
163
+ -0.1,
164
+ -0.1
165
+ ]
166
+ },
167
+ {
168
+ "task": "trace_downstream_blast_radius",
169
+ "score": 0.99,
170
+ "steps": 1,
171
+ "success": true,
172
+ "rewards": [
173
+ 1.6
174
+ ]
175
+ },
176
+ {
177
+ "task": "propose_backward_compat_fix",
178
+ "score": 0.99,
179
+ "steps": 1,
180
+ "success": true,
181
+ "rewards": [
182
+ 2.0
183
+ ]
184
+ },
185
+ {
186
+ "task": "multi_service_cascade_fix",
187
+ "score": 0.99,
188
+ "steps": 2,
189
+ "success": true,
190
+ "rewards": [
191
+ 1.6,
192
+ 2.0
193
+ ]
194
+ }
195
+ ]
196
+ }