{
  "model": "Glint-Router-1M",
  "author": "Glint-Research",
  "parameters": 985826,
  "baseline": "SupraLabs/Supra-Router-51M (51,786,240 params)",
  "training": {
    "params": 985826,
    "train_rows": 87604,
    "val_rows": 7617,
    "steps": 14479,
    "minutes": 15.0,
    "domain": 0.9464356045687279,
    "route": 0.939608769856899,
    "complexity": 0.7923066824209006,
    "code": 0.991466456610214,
    "math": 0.978075357752396,
    "reasoning": 0.8949717736641722,
    "long_output": 0.9516870158855192,
    "ece_raw": 0.05564934242829622,
    "ece_calibrated": 0.02029288645098859,
    "hardware": "RTX 3060 Ti",
    "rounds": 1,
    "wall_clock_minutes": 15.0,
    "corpus_rows": 95221
  },
  "neutral_holdout": {
    "val_rows": 3418,
    "slice_rows": {
      "aqua_rat": 254,
      "dolly": 2500,
      "humaneval": 164,
      "mbpp": 500
    },
    "glint": {
      "route_accuracy": 0.9441193680514921,
      "code_accuracy": 0.9751316559391457,
      "math_accuracy": 0.9526038619075483,
      "complexity_exact": 0.46284376828554713,
      "complexity_within_1": 0.9590403744880047,
      "ms_per_prompt": 0.05992146021082586,
      "parse_failures": 0
    },
    "glint_aqua_rat": {
      "route_accuracy": 0.9094488188976378,
      "code_accuracy": 0.9960629921259843,
      "math_accuracy": 0.889763779527559,
      "complexity_exact": 0.1141732283464567,
      "complexity_within_1": 0.8070866141732284,
      "ms_per_prompt": 0.05992146021082586,
      "parse_failures": 0
    },
    "glint_dolly": {
      "route_accuracy": 0.9424,
      "code_accuracy": 0.9956,
      "math_accuracy": 0.9612,
      "complexity_exact": 0.5688,
      "complexity_within_1": 0.9944,
      "ms_per_prompt": 0.05992146021082586,
      "parse_failures": 0
    },
    "glint_humaneval": {
      "route_accuracy": 0.8719512195121951,
      "code_accuracy": 0.5670731707317073,
      "math_accuracy": 0.9024390243902439,
      "complexity_exact": 0.4451219512195122,
      "complexity_within_1": 0.9817073170731707,
      "ms_per_prompt": 0.05992146021082586,
      "parse_failures": 0
    },
    "glint_mbpp": {
      "route_accuracy": 0.994,
      "code_accuracy": 0.996,
      "math_accuracy": 0.958,
      "complexity_exact": 0.116,
      "complexity_within_1": 0.852,
      "ms_per_prompt": 0.05992146021082586,
      "parse_failures": 0
    },
    "supra": {
      "route_accuracy": 0.903744880046811,
      "code_accuracy": 0.9643066120538326,
      "math_accuracy": 0.9207138677589234,
      "complexity_exact": 0.3905792861322411,
      "complexity_within_1": 0.9163253364540667,
      "ms_per_prompt": 14.334112498536923,
      "parse_failures": 4
    },
    "supra_aqua_rat": {
      "route_accuracy": 0.9133858267716536,
      "code_accuracy": 1.0,
      "math_accuracy": 0.9094488188976378,
      "complexity_exact": 0.0,
      "complexity_within_1": 0.09448818897637795,
      "ms_per_prompt": 14.334112498536923,
      "parse_failures": 4
    },
    "supra_dolly": {
      "route_accuracy": 0.8896,
      "code_accuracy": 0.996,
      "math_accuracy": 0.9428,
      "complexity_exact": 0.482,
      "complexity_within_1": 0.9776,
      "ms_per_prompt": 14.334112498536923,
      "parse_failures": 4
    },
    "supra_humaneval": {
      "route_accuracy": 0.8292682926829268,
      "code_accuracy": 0.676829268292683,
      "math_accuracy": 0.8414634146341463,
      "complexity_exact": 0.16463414634146342,
      "complexity_within_1": 1.0,
      "ms_per_prompt": 14.334112498536923,
      "parse_failures": 4
    },
    "supra_mbpp": {
      "route_accuracy": 0.994,
      "code_accuracy": 0.882,
      "math_accuracy": 0.842,
      "complexity_exact": 0.206,
      "complexity_within_1": 1.0,
      "ms_per_prompt": 14.334112498536923,
      "parse_failures": 4
    }
  },
  "in_corpus_val": {
    "val_rows": 7617,
    "glint": {
      "route_accuracy": 0.939608769856899,
      "code_accuracy": 0.991466456610214,
      "math_accuracy": 0.978075357752396,
      "complexity_exact": 0.7923066824209006,
      "complexity_within_1": 0.9883156098201391,
      "ms_per_prompt": 0.0748591950898926,
      "parse_failures": 0
    },
    "glint_trap": {
      "route_accuracy": 1.0,
      "code_accuracy": 1.0,
      "math_accuracy": 1.0,
      "complexity_exact": 1.0,
      "complexity_within_1": 1.0,
      "parse_failures": 0
    },
    "supra": {
      "route_accuracy": 0.8575554680320336,
      "code_accuracy": 0.9761060785085992,
      "math_accuracy": 0.9400026257056584,
      "complexity_exact": 0.4629119075751608,
      "complexity_within_1": 0.923723250623605,
      "ms_per_prompt": 14.768008985689887,
      "parse_failures": 1
    },
    "supra_trap": {
      "route_accuracy": 0.908695652173913,
      "code_accuracy": 0.9869565217391304,
      "math_accuracy": 1.0,
      "complexity_exact": 0.33043478260869563,
      "complexity_within_1": 0.8391304347826087,
      "parse_failures": 1
    },
    "note": "labels from the glint pipeline. glint is in-distribution here, supra is not. read the holdout numbers for the fair comparison."
  },
  "supra_own_rows": {
    "val_rows": 91,
    "glint": {
      "route_accuracy": 0.8901098901098901,
      "code_accuracy": 0.9010989010989011,
      "math_accuracy": 0.8131868131868132,
      "complexity_exact": 0.5054945054945055
    },
    "supra": {
      "route_accuracy": 0.967032967032967,
      "code_accuracy": 1.0,
      "math_accuracy": 0.978021978021978,
      "complexity_exact": 0.8571428571428571
    },
    "note": "supra's own 992-row dataset, held out of glint training. these rows are supra's TRAINING data, so supra is scoring a memorised set. published because leaving it out would be dishonest."
  }
}