CoderCup/scores/kimi-trajectory-clean.json at main · TestSprite/CoderCup · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
{
  "_doc": "Kimi K2.6 (Kimi Code) TRUSTWORTHY full 10-phase trajectory. SPA-rewrite-fixed app d1i83t74qytjgs; fresh test run --target-url --wait; EVERY result target-verified=d1i83t74 (create-batch --target-url was IGNORED \u2192 new plans rescored via test run). blocked=fail; weighted p0=3/p1=2/p2=1; cumulative 1..N vs phase-N deploy. P8 gate-missing, P9/P10 gate-failed(honest env gaps: lighthouse/static-API limits) \u2192 operator-deployed sound builds (challenger pattern).",
  "scored_at": "2026-06-07",
  "trajectory": {
    "1": {
      "cumulative_correctness": 0.7368,
      "passed": 12,
      "failed": 4,
      "blocked": 1,
      "n_tests": 17,
      "gate": "passed"
    },
    "2": {
      "cumulative_correctness": 0.7222,
      "passed": 23,
      "failed": 8,
      "blocked": 2,
      "n_tests": 33,
      "gate": "passed"
    },
    "3": {
      "cumulative_correctness": 0.7414,
      "passed": 39,
      "failed": 9,
      "blocked": 5,
      "n_tests": 53,
      "gate": "passed"
    },
    "4": {
      "cumulative_correctness": 0.6846,
      "passed": 45,
      "failed": 15,
      "blocked": 9,
      "n_tests": 69,
      "gate": "passed"
    },
    "5": {
      "cumulative_correctness": 0.8693,
      "passed": 78,
      "failed": 6,
      "blocked": 7,
      "n_tests": 91,
      "gate": "passed"
    },
    "6": {
      "cumulative_correctness": 0.865,
      "passed": 90,
      "failed": 12,
      "blocked": 5,
      "n_tests": 107,
      "gate": "passed"
    },
    "7": {
      "cumulative_correctness": 0.875,
      "passed": 107,
      "failed": 11,
      "blocked": 7,
      "n_tests": 126,
      "gate": "passed"
    },
    "8": {
      "cumulative_correctness": 0.8475,
      "passed": 126,
      "failed": 14,
      "blocked": 10,
      "n_tests": 150,
      "gate": "missing(operator-deployed)"
    },
    "9": {
      "cumulative_correctness": 0.8333,
      "passed": 136,
      "failed": 23,
      "blocked": 7,
      "n_tests": 166,
      "gate": "failed-honest-env-gaps(operator-deployed)"
    },
    "10": {
      "cumulative_correctness": 0.8993,
      "passed": 161,
      "failed": 14,
      "blocked": 7,
      "n_tests": 182,
      "gate": "failed-honest-env-gaps(operator-deployed)"
    }
  }
}