ladderbench / eval_results /thinkingcap.json
icecubesaad's picture
Upload eval_results/thinkingcap.json with huggingface_hub
979c6d9 verified
Raw History Blame Contribute Delete
29.5 kB
{
"schema": "ladderbench.report/v1",
"generated_at": "2026-09-29T12:17:59.114016+00:00",
"ladderbench_version": "0.1.0",
"model": "hf:bottlecapai/ThinkingCap-Qwen3.8-27B",
"endpoint": "vllm-offline",
"probe_set": "all@v1",
"levels_ordered": [
"xhigh",
"medium",
"low"
],
"summary": {
"levels": [
"xhigh",
"medium",
"low"
],
"accuracy": [
0.8823529411764706,
0.8970588235294118,
0.9264705882352942
],
"median_thinking_tokens": [
33.5,
39.5,
40.5
],
"spearman_tokens_vs_effort": -0.9999999999999998,
"spearman_accuracy_vs_effort": -0.9999999999999998,
"top_level": {
"level": "xhigh",
"accuracy": 0.8823529411764706,
"median_thinking_tokens": 33.5,
"empty_trace_rate": 0.0
},
"token_spread_max_over_min": 1.208955223880597
},
"ladder_integrity": "degraded",
"findings": [
"inverted dial: tokens vs effort rho=-1.00",
"misaligned: accuracy vs effort rho=-1.00"
],
"calibration_delta": [
{
"level": "xhigh",
"d_accuracy": 0.0,
"d_thinking_tokens": -31.5
},
{
"level": "medium",
"d_accuracy": 0.0147,
"d_thinking_tokens": -8.0
},
{
"level": "low",
"d_accuracy": 0.0294,
"d_thinking_tokens": -4.5
}
],
"per_level": {
"xhigh": {
"n": 68,
"accuracy": 0.8824,
"median_thinking_tokens": 33.5,
"empty_trace_rate": 0.0,
"responses": [
{
"id": "e01",
"correct": true,
"predicted": "43",
"trace_chars": 70
},
{
"id": "e02",
"correct": true,
"predicted": "62",
"trace_chars": 76
},
{
"id": "e03",
"correct": true,
"predicted": "12",
"trace_chars": 70
},
{
"id": "e04",
"correct": true,
"predicted": "12",
"trace_chars": 85
},
{
"id": "e05",
"correct": true,
"predicted": "150",
"trace_chars": 79
},
{
"id": "e06",
"correct": true,
"predicted": "5.75",
"trace_chars": 162
},
{
"id": "e07",
"correct": true,
"predicted": "33",
"trace_chars": 99
},
{
"id": "e08",
"correct": true,
"predicted": "1024",
"trace_chars": 41
},
{
"id": "e09",
"correct": true,
"predicted": "210",
"trace_chars": 95
},
{
"id": "e10",
"correct": true,
"predicted": "495",
"trace_chars": 70
},
{
"id": "e11",
"correct": true,
"predicted": "28",
"trace_chars": 211
},
{
"id": "e12",
"correct": true,
"predicted": "63",
"trace_chars": 70
},
{
"id": "e13",
"correct": true,
"predicted": "64",
"trace_chars": 100
},
{
"id": "e14",
"correct": true,
"predicted": "144",
"trace_chars": 70
},
{
"id": "e15",
"correct": true,
"predicted": "7",
"trace_chars": 190
},
{
"id": "e16",
"correct": true,
"predicted": "8",
"trace_chars": 86
},
{
"id": "e17",
"correct": true,
"predicted": "12",
"trace_chars": 218
},
{
"id": "e18",
"correct": true,
"predicted": "100",
"trace_chars": 87
},
{
"id": "e19",
"correct": true,
"predicted": "90",
"trace_chars": 93
},
{
"id": "e20",
"correct": true,
"predicted": "125",
"trace_chars": 41
},
{
"id": "m01",
"correct": true,
"predicted": "1081",
"trace_chars": 98
},
{
"id": "m02",
"correct": true,
"predicted": "32768",
"trace_chars": 73
},
{
"id": "m03",
"correct": true,
"predicted": "5050",
"trace_chars": 71
},
{
"id": "m04",
"correct": true,
"predicted": "5",
"trace_chars": 311
},
{
"id": "m05",
"correct": true,
"predicted": "36",
"trace_chars": 107
},
{
"id": "m06",
"correct": true,
"predicted": "12",
"trace_chars": 111
},
{
"id": "m07",
"correct": true,
"predicted": "300",
"trace_chars": 101
},
{
"id": "m08",
"correct": true,
"predicted": "204",
"trace_chars": 187
},
{
"id": "m09",
"correct": true,
"predicted": "72",
"trace_chars": 203
},
{
"id": "m10",
"correct": true,
"predicted": "1210",
"trace_chars": 155
},
{
"id": "m11",
"correct": true,
"predicted": "8",
"trace_chars": 204
},
{
"id": "m12",
"correct": true,
"predicted": "28",
"trace_chars": 207
},
{
"id": "m13",
"correct": true,
"predicted": "154",
"trace_chars": 147
},
{
"id": "m14",
"correct": true,
"predicted": "13",
"trace_chars": 194
},
{
"id": "m15",
"correct": true,
"predicted": "75",
"trace_chars": 70
},
{
"id": "m16",
"correct": true,
"predicted": "6",
"trace_chars": 248
},
{
"id": "m17",
"correct": true,
"predicted": "48",
"trace_chars": 101
},
{
"id": "m18",
"correct": true,
"predicted": "18",
"trace_chars": 256
},
{
"id": "m19",
"correct": true,
"predicted": "0.5",
"trace_chars": 166
},
{
"id": "m20",
"correct": true,
"predicted": "216",
"trace_chars": 102
},
{
"id": "h01",
"correct": true,
"predicted": "42",
"trace_chars": 200
},
{
"id": "h02",
"correct": true,
"predicted": "1048576",
"trace_chars": 77
},
{
"id": "h03",
"correct": true,
"predicted": "10",
"trace_chars": 84
},
{
"id": "h04",
"correct": true,
"predicted": "8",
"trace_chars": 158
},
{
"id": "h05",
"correct": true,
"predicted": "100",
"trace_chars": 107
},
{
"id": "h06",
"correct": true,
"predicted": "56",
"trace_chars": 213
},
{
"id": "h07",
"correct": true,
"predicted": "20",
"trace_chars": 195
},
{
"id": "h08",
"correct": true,
"predicted": "10",
"trace_chars": 191
},
{
"id": "h09",
"correct": true,
"predicted": "12",
"trace_chars": 96
},
{
"id": "h10",
"correct": true,
"predicted": "13",
"trace_chars": 154
},
{
"id": "h11",
"correct": true,
"predicted": "17",
"trace_chars": 173
},
{
"id": "h12",
"correct": true,
"predicted": "25",
"trace_chars": 96
},
{
"id": "h13",
"correct": true,
"predicted": "30",
"trace_chars": 209
},
{
"id": "h14",
"correct": true,
"predicted": "132",
"trace_chars": 95
},
{
"id": "h15",
"correct": true,
"predicted": "12",
"trace_chars": 81
},
{
"id": "h16",
"correct": true,
"predicted": "720",
"trace_chars": 93
},
{
"id": "h17",
"correct": true,
"predicted": "1",
"trace_chars": 164
},
{
"id": "h18",
"correct": true,
"predicted": "60",
"trace_chars": 127
},
{
"id": "h19",
"correct": true,
"predicted": "0.375",
"trace_chars": 227
},
{
"id": "h20",
"correct": true,
"predicted": "55",
"trace_chars": 137
},
{
"id": "i01",
"correct": false,
"predicted": null,
"trace_chars": 321
},
{
"id": "i02",
"correct": false,
"predicted": null,
"trace_chars": 612
},
{
"id": "i03",
"correct": false,
"predicted": null,
"trace_chars": 650
},
{
"id": "i04",
"correct": false,
"predicted": null,
"trace_chars": 375
},
{
"id": "i05",
"correct": false,
"predicted": null,
"trace_chars": 1425
},
{
"id": "i06",
"correct": false,
"predicted": null,
"trace_chars": 524
},
{
"id": "i07",
"correct": false,
"predicted": null,
"trace_chars": 388
},
{
"id": "i08",
"correct": false,
"predicted": null,
"trace_chars": 708
}
]
},
"medium": {
"n": 68,
"accuracy": 0.8971,
"median_thinking_tokens": 39.5,
"empty_trace_rate": 0.0,
"responses": [
{
"id": "e01",
"correct": true,
"predicted": "43",
"trace_chars": 68
},
{
"id": "e02",
"correct": true,
"predicted": "62",
"trace_chars": 168
},
{
"id": "e03",
"correct": true,
"predicted": "12",
"trace_chars": 109
},
{
"id": "e04",
"correct": true,
"predicted": "12",
"trace_chars": 56
},
{
"id": "e05",
"correct": true,
"predicted": "150",
"trace_chars": 88
},
{
"id": "e06",
"correct": true,
"predicted": "5.75",
"trace_chars": 61
},
{
"id": "e07",
"correct": true,
"predicted": "33",
"trace_chars": 68
},
{
"id": "e08",
"correct": true,
"predicted": "1024",
"trace_chars": 174
},
{
"id": "e09",
"correct": true,
"predicted": "210",
"trace_chars": 164
},
{
"id": "e10",
"correct": true,
"predicted": "495",
"trace_chars": 88
},
{
"id": "e11",
"correct": true,
"predicted": "28",
"trace_chars": 145
},
{
"id": "e12",
"correct": true,
"predicted": "63",
"trace_chars": 73
},
{
"id": "e13",
"correct": true,
"predicted": "64",
"trace_chars": 103
},
{
"id": "e14",
"correct": true,
"predicted": "144",
"trace_chars": 76
},
{
"id": "e15",
"correct": true,
"predicted": "7",
"trace_chars": 120
},
{
"id": "e16",
"correct": true,
"predicted": "8",
"trace_chars": 92
},
{
"id": "e17",
"correct": true,
"predicted": "12",
"trace_chars": 145
},
{
"id": "e18",
"correct": true,
"predicted": "100",
"trace_chars": 60
},
{
"id": "e19",
"correct": true,
"predicted": "90",
"trace_chars": 75
},
{
"id": "e20",
"correct": true,
"predicted": "125",
"trace_chars": 74
},
{
"id": "m01",
"correct": true,
"predicted": "1081",
"trace_chars": 91
},
{
"id": "m02",
"correct": true,
"predicted": "32768",
"trace_chars": 224
},
{
"id": "m03",
"correct": true,
"predicted": "5050",
"trace_chars": 171
},
{
"id": "m04",
"correct": true,
"predicted": "5",
"trace_chars": 490
},
{
"id": "m05",
"correct": true,
"predicted": "36",
"trace_chars": 74
},
{
"id": "m06",
"correct": true,
"predicted": "12",
"trace_chars": 236
},
{
"id": "m07",
"correct": true,
"predicted": "300",
"trace_chars": 268
},
{
"id": "m08",
"correct": true,
"predicted": "204",
"trace_chars": 130
},
{
"id": "m09",
"correct": true,
"predicted": "72",
"trace_chars": 223
},
{
"id": "m10",
"correct": true,
"predicted": "1210",
"trace_chars": 197
},
{
"id": "m11",
"correct": true,
"predicted": "8",
"trace_chars": 85
},
{
"id": "m12",
"correct": true,
"predicted": "28",
"trace_chars": 101
},
{
"id": "m13",
"correct": true,
"predicted": "154",
"trace_chars": 108
},
{
"id": "m14",
"correct": true,
"predicted": "13",
"trace_chars": 164
},
{
"id": "m15",
"correct": true,
"predicted": "75",
"trace_chars": 90
},
{
"id": "m16",
"correct": true,
"predicted": "6",
"trace_chars": 134
},
{
"id": "m17",
"correct": true,
"predicted": "48",
"trace_chars": 148
},
{
"id": "m18",
"correct": true,
"predicted": "18",
"trace_chars": 140
},
{
"id": "m19",
"correct": true,
"predicted": "0.5",
"trace_chars": 209
},
{
"id": "m20",
"correct": true,
"predicted": "216",
"trace_chars": 69
},
{
"id": "h01",
"correct": true,
"predicted": "42",
"trace_chars": 251
},
{
"id": "h02",
"correct": true,
"predicted": "1048576",
"trace_chars": 299
},
{
"id": "h03",
"correct": true,
"predicted": "10",
"trace_chars": 103
},
{
"id": "h04",
"correct": true,
"predicted": "8",
"trace_chars": 136
},
{
"id": "h05",
"correct": true,
"predicted": "100",
"trace_chars": 259
},
{
"id": "h06",
"correct": true,
"predicted": "56",
"trace_chars": 201
},
{
"id": "h07",
"correct": true,
"predicted": "20",
"trace_chars": 180
},
{
"id": "h08",
"correct": true,
"predicted": "10",
"trace_chars": 166
},
{
"id": "h09",
"correct": true,
"predicted": "12",
"trace_chars": 202
},
{
"id": "h10",
"correct": true,
"predicted": "13",
"trace_chars": 119
},
{
"id": "h11",
"correct": true,
"predicted": "17",
"trace_chars": 129
},
{
"id": "h12",
"correct": true,
"predicted": "25",
"trace_chars": 152
},
{
"id": "h13",
"correct": true,
"predicted": "30",
"trace_chars": 246
},
{
"id": "h14",
"correct": true,
"predicted": "132",
"trace_chars": 163
},
{
"id": "h15",
"correct": true,
"predicted": "12",
"trace_chars": 389
},
{
"id": "h16",
"correct": true,
"predicted": "720",
"trace_chars": 130
},
{
"id": "h17",
"correct": true,
"predicted": "1",
"trace_chars": 336
},
{
"id": "h18",
"correct": true,
"predicted": "60",
"trace_chars": 373
},
{
"id": "h19",
"correct": true,
"predicted": "0.375",
"trace_chars": 204
},
{
"id": "h20",
"correct": true,
"predicted": "55",
"trace_chars": 196
},
{
"id": "i01",
"correct": false,
"predicted": "A",
"trace_chars": 1677
},
{
"id": "i02",
"correct": false,
"predicted": "A",
"trace_chars": 793
},
{
"id": "i03",
"correct": false,
"predicted": "B",
"trace_chars": 824
},
{
"id": "i04",
"correct": false,
"predicted": "A",
"trace_chars": 860
},
{
"id": "i05",
"correct": false,
"predicted": "A",
"trace_chars": 1345
},
{
"id": "i06",
"correct": false,
"predicted": "B",
"trace_chars": 1138
},
{
"id": "i07",
"correct": false,
"predicted": "A",
"trace_chars": 1155
},
{
"id": "i08",
"correct": true,
"predicted": "B",
"trace_chars": 793
}
]
},
"low": {
"n": 68,
"accuracy": 0.9265,
"median_thinking_tokens": 40.5,
"empty_trace_rate": 0.0,
"responses": [
{
"id": "e01",
"correct": true,
"predicted": "43",
"trace_chars": 51
},
{
"id": "e02",
"correct": true,
"predicted": "62",
"trace_chars": 159
},
{
"id": "e03",
"correct": true,
"predicted": "12",
"trace_chars": 57
},
{
"id": "e04",
"correct": true,
"predicted": "12",
"trace_chars": 61
},
{
"id": "e05",
"correct": true,
"predicted": "150",
"trace_chars": 110
},
{
"id": "e06",
"correct": true,
"predicted": "5.75",
"trace_chars": 61
},
{
"id": "e07",
"correct": true,
"predicted": "33",
"trace_chars": 58
},
{
"id": "e08",
"correct": true,
"predicted": "1024",
"trace_chars": 122
},
{
"id": "e09",
"correct": true,
"predicted": "210",
"trace_chars": 162
},
{
"id": "e10",
"correct": true,
"predicted": "495",
"trace_chars": 88
},
{
"id": "e11",
"correct": true,
"predicted": "28",
"trace_chars": 171
},
{
"id": "e12",
"correct": true,
"predicted": "63",
"trace_chars": 73
},
{
"id": "e13",
"correct": true,
"predicted": "64",
"trace_chars": 80
},
{
"id": "e14",
"correct": true,
"predicted": "144",
"trace_chars": 58
},
{
"id": "e15",
"correct": true,
"predicted": "7",
"trace_chars": 67
},
{
"id": "e16",
"correct": true,
"predicted": "8",
"trace_chars": 84
},
{
"id": "e17",
"correct": true,
"predicted": "12",
"trace_chars": 140
},
{
"id": "e18",
"correct": true,
"predicted": "100",
"trace_chars": 65
},
{
"id": "e19",
"correct": true,
"predicted": "90",
"trace_chars": 71
},
{
"id": "e20",
"correct": true,
"predicted": "125",
"trace_chars": 74
},
{
"id": "m01",
"correct": true,
"predicted": "1081",
"trace_chars": 91
},
{
"id": "m02",
"correct": true,
"predicted": "32768",
"trace_chars": 225
},
{
"id": "m03",
"correct": true,
"predicted": "5050",
"trace_chars": 208
},
{
"id": "m04",
"correct": true,
"predicted": "5",
"trace_chars": 411
},
{
"id": "m05",
"correct": true,
"predicted": "36",
"trace_chars": 145
},
{
"id": "m06",
"correct": true,
"predicted": "12",
"trace_chars": 221
},
{
"id": "m07",
"correct": true,
"predicted": "300",
"trace_chars": 212
},
{
"id": "m08",
"correct": true,
"predicted": "204",
"trace_chars": 140
},
{
"id": "m09",
"correct": true,
"predicted": "72",
"trace_chars": 198
},
{
"id": "m10",
"correct": true,
"predicted": "1210",
"trace_chars": 195
},
{
"id": "m11",
"correct": true,
"predicted": "8",
"trace_chars": 116
},
{
"id": "m12",
"correct": true,
"predicted": "28",
"trace_chars": 129
},
{
"id": "m13",
"correct": true,
"predicted": "154",
"trace_chars": 144
},
{
"id": "m14",
"correct": true,
"predicted": "13",
"trace_chars": 158
},
{
"id": "m15",
"correct": true,
"predicted": "75",
"trace_chars": 90
},
{
"id": "m16",
"correct": true,
"predicted": "6",
"trace_chars": 210
},
{
"id": "m17",
"correct": true,
"predicted": "48",
"trace_chars": 158
},
{
"id": "m18",
"correct": true,
"predicted": "18",
"trace_chars": 156
},
{
"id": "m19",
"correct": true,
"predicted": "0.5",
"trace_chars": 111
},
{
"id": "m20",
"correct": true,
"predicted": "216",
"trace_chars": 135
},
{
"id": "h01",
"correct": true,
"predicted": "42",
"trace_chars": 207
},
{
"id": "h02",
"correct": true,
"predicted": "1048576",
"trace_chars": 299
},
{
"id": "h03",
"correct": true,
"predicted": "10",
"trace_chars": 62
},
{
"id": "h04",
"correct": true,
"predicted": "8",
"trace_chars": 207
},
{
"id": "h05",
"correct": true,
"predicted": "100",
"trace_chars": 275
},
{
"id": "h06",
"correct": true,
"predicted": "56",
"trace_chars": 200
},
{
"id": "h07",
"correct": true,
"predicted": "20",
"trace_chars": 179
},
{
"id": "h08",
"correct": true,
"predicted": "10",
"trace_chars": 176
},
{
"id": "h09",
"correct": true,
"predicted": "12",
"trace_chars": 206
},
{
"id": "h10",
"correct": true,
"predicted": "13",
"trace_chars": 70
},
{
"id": "h11",
"correct": true,
"predicted": "17",
"trace_chars": 156
},
{
"id": "h12",
"correct": true,
"predicted": "25",
"trace_chars": 152
},
{
"id": "h13",
"correct": true,
"predicted": "30",
"trace_chars": 188
},
{
"id": "h14",
"correct": true,
"predicted": "132",
"trace_chars": 161
},
{
"id": "h15",
"correct": true,
"predicted": "12",
"trace_chars": 389
},
{
"id": "h16",
"correct": true,
"predicted": "720",
"trace_chars": 216
},
{
"id": "h17",
"correct": true,
"predicted": "1",
"trace_chars": 433
},
{
"id": "h18",
"correct": true,
"predicted": "60",
"trace_chars": 335
},
{
"id": "h19",
"correct": true,
"predicted": "0.375",
"trace_chars": 235
},
{
"id": "h20",
"correct": true,
"predicted": "55",
"trace_chars": 196
},
{
"id": "i01",
"correct": false,
"predicted": "A",
"trace_chars": 1140
},
{
"id": "i02",
"correct": true,
"predicted": "C",
"trace_chars": 820
},
{
"id": "i03",
"correct": true,
"predicted": "A",
"trace_chars": 907
},
{
"id": "i04",
"correct": false,
"predicted": "A",
"trace_chars": 700
},
{
"id": "i05",
"correct": false,
"predicted": "A",
"trace_chars": 1353
},
{
"id": "i06",
"correct": true,
"predicted": "A",
"trace_chars": 748
},
{
"id": "i07",
"correct": false,
"predicted": "A",
"trace_chars": 977
},
{
"id": "i08",
"correct": false,
"predicted": "A",
"trace_chars": 984
}
]
}
}
}