{
 "criteria": {
  "probes": "every |platform endpoint - official reference| <= 1e-06",
  "reproduced": "all 75 cells within 0.005",
  "within_one_step": "all within 0.02",
  "not_reproduced": "any cell beyond 0.02"
 },
 "probes": {
  "n": 26,
  "max_abs_diff": 0.0,
  "equal": 26,
  "pass": true,
  "scores": [
   2.9140625,
   2.1796875,
   1.0302734375,
   1.10546875,
   2.03125,
   3.03125,
   1.671875,
   1.486328125,
   3.78125,
   2.25,
   1.1630859375,
   1.1513671875,
   2.6328125,
   1.6875,
   1.2333984375,
   1.53125,
   3.796875,
   2.71875,
   3.234375,
   1.84375,
   4.890625,
   4.546875,
   1.41015625,
   2.4375,
   1.53515625,
   1.53515625
  ]
 },
 "anchor": {
  "rows": {
   "ChatGLM3-6B": {
    "scores": 8032,
    "cells": {
     "ka": {
      "platform": 2.7847522958739552,
      "paper": 2.792,
      "diff": -0.007247704126044585
     },
     "cs": {
      "platform": 2.9276329269201296,
      "paper": 2.932,
      "diff": -0.004367073079870387
     },
     "coh": {
      "platform": 3.6480705993997176,
      "paper": 3.647,
      "diff": 0.0010705993997177643
     },
     "ed": {
      "platform": 1.9732628127451344,
      "paper": 1.969,
      "diff": 0.004262812745134292
     },
     "flu": {
      "platform": 3.2809646408279223,
      "paper": 3.269,
      "diff": 0.011964640827922146
     },
     "ke": {
      "platform": 2.020533158331692,
      "paper": 2.016,
      "diff": 0.0045331583316921
     },
     "pu": {
      "platform": 2.8126760240417816,
      "paper": 2.812,
      "diff": 0.0006760240417817975
     },
     "cons": {
      "platform": 3.278281386582168,
      "paper": 3.283,
      "diff": -0.004718613417832085
     },
     "pb": {
      "platform": 2.4615908490286933,
      "paper": 2.455,
      "diff": 0.006590849028693224
     },
     "kh": {
      "platform": 2.7126133294753085,
      "paper": 2.704,
      "diff": 0.008613329475308351
     },
     "emp": {
      "platform": 2.986574890793011,
      "paper": 2.993,
      "diff": -0.00642510920698891
     },
     "hl": {
      "platform": 3.0706574666565953,
      "paper": 3.064,
      "diff": 0.006657466656595279
     },
     "ca_avg": {
      "platform": 3.4024388756032686,
      "paper": 3.399,
      "diff": 0.0034388756032686096
     },
     "cc_avg": {
      "platform": 2.558433131350286,
      "paper": 2.556,
      "diff": 0.0024331313502861107
     },
     "ra_avg": {
      "platform": 2.7395320242787173,
      "paper": 2.739,
      "diff": 0.0005320242787174578
     }
    }
   },
   "Baichuan2-7B": {
    "scores": 8032,
    "cells": {
     "ka": {
      "platform": 2.840292587917827,
      "paper": 2.849,
      "diff": -0.008707412082173072
     },
     "cs": {
      "platform": 2.728624723262943,
      "paper": 2.728,
      "diff": 0.0006247232629426058
     },
     "coh": {
      "platform": 3.892417433571681,
      "paper": 3.894,
      "diff": -0.001582566428319332
     },
     "ed": {
      "platform": 2.114333847646312,
      "paper": 2.115,
      "diff": -0.0006661523536881653
     },
     "flu": {
      "platform": 3.5453721083603895,
      "paper": 3.551,
      "diff": -0.005627891639610638
     },
     "ke": {
      "platform": 1.816818652032804,
      "paper": 1.813,
      "diff": 0.0038186520328040707
     },
     "pu": {
      "platform": 3.078828927561723,
      "paper": 3.081,
      "diff": -0.0021710724382768554
     },
     "cons": {
      "platform": 3.827838988404174,
      "paper": 3.827,
      "diff": 0.000838988404173957
     },
     "pb": {
      "platform": 2.8200992266337077,
      "paper": 2.83,
      "diff": -0.00990077336629236
     },
     "kh": {
      "platform": 2.9297015657150207,
      "paper": 2.929,
      "diff": 0.0007015657150208909
     },
     "emp": {
      "platform": 2.9840146136540238,
      "paper": 2.984,
      "diff": 1.4613654023776235e-05
     },
     "hl": {
      "platform": 3.6668498845390194,
      "paper": 3.67,
      "diff": -0.0031501154609805404
     },
     "ca_avg": {
      "platform": 3.7552095101120813,
      "paper": 3.757,
      "diff": -0.0017904898879188558
     },
     "cc_avg": {
      "platform": 2.6971481919722167,
      "paper": 2.7,
      "diff": -0.002851808027783509
     },
     "ra_avg": {
      "platform": 2.8734557672755745,
      "paper": 2.874,
      "diff": -0.0005442327244256084
     }
    }
   },
   "XVERSE-7B": {
    "scores": 8032,
    "cells": {
     "ka": {
      "platform": 2.780303360027855,
      "paper": 2.774,
      "diff": 0.006303360027855032
     },
     "cs": {
      "platform": 2.7400111892242847,
      "paper": 2.743,
      "diff": -0.0029888107757152227
     },
     "coh": {
      "platform": 3.7498206876765536,
      "paper": 3.752,
      "diff": -0.0021793123234461476
     },
     "ed": {
      "platform": 2.011195851795709,
      "paper": 2.013,
      "diff": -0.0018041482042909784
     },
     "flu": {
      "platform": 3.4031510786576704,
      "paper": 3.393,
      "diff": 0.01015107865767062
     },
     "ke": {
      "platform": 1.8297562372116816,
      "paper": 1.834,
      "diff": -0.004243762788318506
     },
     "pu": {
      "platform": 2.8870640538674035,
      "paper": 2.887,
      "diff": 6.405386740349073e-05
     },
     "cons": {
      "platform": 3.518080405922203,
      "paper": 3.518,
      "diff": 8.040592220304177e-05
     },
     "pb": {
      "platform": 2.569406615363227,
      "paper": 2.564,
      "diff": 0.005406615363226841
     },
     "kh": {
      "platform": 2.7591869212962963,
      "paper": 2.763,
      "diff": -0.0038130787037036207
     },
     "emp": {
      "platform": 2.9364945606518815,
      "paper": 2.936,
      "diff": 0.0004945606518815815
     },
     "hl": {
      "platform": 3.390934559521754,
      "paper": 3.395,
      "diff": -0.004065440478246085
     },
     "ca_avg": {
      "platform": 3.5570173907521423,
      "paper": 3.554,
      "diff": 0.003017390752142468
     },
     "cc_avg": {
      "platform": 2.5651434375532927,
      "paper": 2.564,
      "diff": 0.0011434375532926033
     },
     "ra_avg": {
      "platform": 2.769659040298407,
      "paper": 2.772,
      "diff": -0.0023409597015926487
     }
    }
   },
   "InternLM-7B": {
    "scores": 8032,
    "cells": {
     "ka": {
      "platform": 2.801572836873259,
      "paper": 2.8,
      "diff": 0.0015728368732590425
     },
     "cs": {
      "platform": 2.6247079625766347,
      "paper": 2.622,
      "diff": 0.002707962576634859
     },
     "coh": {
      "platform": 3.8254215218926553,
      "paper": 3.823,
      "diff": 0.0024215218926553206
     },
     "ed": {
      "platform": 2.0698165013638086,
      "paper": 2.07,
      "diff": -0.0001834986361912705
     },
     "flu": {
      "platform": 3.5311548802759742,
      "paper": 3.527,
      "diff": 0.004154880275974104
     },
     "ke": {
      "platform": 1.7814863188927914,
      "paper": 1.782,
      "diff": -0.0005136811072086189
     },
     "pu": {
      "platform": 3.0131080585290055,
      "paper": 3.016,
      "diff": -0.0028919414709944746
     },
     "cons": {
      "platform": 3.748101507867133,
      "paper": 3.744,
      "diff": 0.004101507867132703
     },
     "pb": {
      "platform": 2.7165239810943604,
      "paper": 2.719,
      "diff": -0.002476018905639421
     },
     "kh": {
      "platform": 2.78734648276749,
      "paper": 2.781,
      "diff": 0.006346482767489725
     },
     "emp": {
      "platform": 2.8990911668346775,
      "paper": 2.897,
      "diff": 0.0020911668346776935
     },
     "hl": {
      "platform": 3.544124708649862,
      "paper": 3.546,
      "diff": -0.0018752913501378643
     },
     "ca_avg": {
      "platform": 3.7015593033452543,
      "paper": 3.698,
      "diff": 0.0035593033452543388
     },
     "cc_avg": {
      "platform": 2.6200075356313812,
      "paper": 2.62,
      "diff": 7.535631381117014e-06
     },
     "ra_avg": {
      "platform": 2.784435084856246,
      "paper": 2.784,
      "diff": 0.000435084856245993
     }
    }
   },
   "Qwen-7B": {
    "scores": 8032,
    "cells": {
     "ka": {
      "platform": 2.7284258574164344,
      "paper": 2.728,
      "diff": 0.0004258574164341944
     },
     "cs": {
      "platform": 2.7856481900332084,
      "paper": 2.791,
      "diff": -0.005351809966791521
     },
     "coh": {
      "platform": 3.563231042549435,
      "paper": 3.564,
      "diff": -0.0007689574505649333
     },
     "ed": {
      "platform": 2.05657965195551,
      "paper": 2.052,
      "diff": 0.004579651955510133
     },
     "flu": {
      "platform": 3.188857041396104,
      "paper": 3.187,
      "diff": 0.0018570413961040977
     },
     "ke": {
      "platform": 1.9597707155371915,
      "paper": 1.956,
      "diff": 0.003770715537191549
     },
     "pu": {
      "platform": 2.7741348519509668,
      "paper": 2.78,
      "diff": -0.005865148049033042
     },
     "cons": {
      "platform": 3.2408899694055946,
      "paper": 3.229,
      "diff": 0.011889969405594503
     },
     "pb": {
      "platform": 2.6088686015870834,
      "paper": 2.605,
      "diff": 0.0038686015870834645
     },
     "kh": {
      "platform": 2.622134612911523,
      "paper": 2.633,
      "diff": -0.010865387088477174
     },
     "emp": {
      "platform": 2.8371463898689515,
      "paper": 2.838,
      "diff": -0.0008536101310485655
     },
     "hl": {
      "platform": 3.0311812089951657,
      "paper": 3.036,
      "diff": -0.004818791004834289
     },
     "ca_avg": {
      "platform": 3.330992684450378,
      "paper": 3.327,
      "diff": 0.003992684450377926
     },
     "cc_avg": {
      "platform": 2.53866692788064,
      "paper": 2.54,
      "diff": -0.001333072119360068
     },
     "ra_avg": {
      "platform": 2.677638860213209,
      "paper": 2.679,
      "diff": -0.0013611397867907549
     }
    }
   }
  },
  "cells": 75,
  "verdict": "within one step",
  "max_abs_diff": 0.011964640827922146,
  "mean_signed_diff": 0.00027827050653558356,
  "within_0.0005": 8,
  "within_0.001": 18,
  "within_0.005": 58,
  "within_0.02": 75,
  "character_consistency_order": {
   "platform": [
    "Baichuan2-7B",
    "InternLM-7B",
    "XVERSE-7B",
    "ChatGLM3-6B",
    "Qwen-7B"
   ],
   "paper": [
    "Baichuan2-7B",
    "InternLM-7B",
    "XVERSE-7B",
    "ChatGLM3-6B",
    "Qwen-7B"
   ]
  }
 }
}