{
  "created_at": "2026-09-13T00:16:25.063883+00:00",
  "benchmark": "BananaMind Base Bench 1.1",
  "benchmark_version": "1.1",
  "dataset_id": "BananaMind/BananaMind-Base-Bench-1.1",
  "dataset_revision": "d4aade51312889e8580963e1ce960c6eaef1a450",
  "dataset_sha256": "2f563bb46df778ca494fa20f994a8d3045d4c51fbbffeee433764e2813abea21",
  "model": "SlayerLab/fabryka-english-base-250m-e01",
  "model_revision": "1e9760c8a1cc0a41f2461d49b5f12d7e4148a2d5",
  "tokenizer": "SlayerLab/fabryka-english-base-250m-e01",
  "device": "cpu",
  "dtype": "float32",
  "model_context_length": 2048,
  "scoring": {
    "task": "four-choice base-text continuation",
    "choice_score": "mean conditional token log-probability",
    "chat_template": false,
    "generation": false,
    "add_special_tokens": false,
    "add_bos": false
  },
  "elo": {
    "scale": 400.0,
    "prior_rating": 1000.0,
    "prior_weight": 4.0,
    "method": "weighted fixed-item logistic maximum-likelihood rating"
  },
  "summary": {
    "official_complete_run": true,
    "cases": 350,
    "passed": 106,
    "accuracy": 0.3028571428571429,
    "weighted_points": 192.5625,
    "possible_weighted_points": 668.1875,
    "weighted_accuracy": 0.28818632494621643,
    "overall_elo": 842,
    "overall_elo_unrounded": 841.5314663792717,
    "categories": {
      "language_completion": {
        "cases": 50,
        "passed": 30,
        "accuracy": 0.6,
        "weighted_points": 49.0,
        "possible_weighted_points": 78.5,
        "weighted_accuracy": 0.6242038216560509,
        "elo": 993,
        "elo_unrounded": 993.4680335899088
      },
      "commonsense": {
        "cases": 50,
        "passed": 15,
        "accuracy": 0.3,
        "weighted_points": 23.1,
        "possible_weighted_points": 87.17500000000001,
        "weighted_accuracy": 0.2649842271293375,
        "elo": 772,
        "elo_unrounded": 772.4284853146141
      },
      "world_knowledge": {
        "cases": 50,
        "passed": 15,
        "accuracy": 0.3,
        "weighted_points": 25.025000000000002,
        "possible_weighted_points": 87.72500000000001,
        "weighted_accuracy": 0.2852664576802508,
        "elo": 791,
        "elo_unrounded": 791.3189921625742
      },
      "context_tracking": {
        "cases": 50,
        "passed": 11,
        "accuracy": 0.22,
        "weighted_points": 17.7,
        "possible_weighted_points": 94.19999999999999,
        "weighted_accuracy": 0.18789808917197454,
        "elo": 740,
        "elo_unrounded": 740.3310741220985
      },
      "quantitative": {
        "cases": 50,
        "passed": 16,
        "accuracy": 0.32,
        "weighted_points": 34.45,
        "possible_weighted_points": 103.025,
        "weighted_accuracy": 0.33438485804416407,
        "elo": 925,
        "elo_unrounded": 925.4521956942147
      },
      "logical_reasoning": {
        "cases": 50,
        "passed": 14,
        "accuracy": 0.28,
        "weighted_points": 31.387500000000003,
        "possible_weighted_points": 107.66250000000001,
        "weighted_accuracy": 0.29153605015673983,
        "elo": 939,
        "elo_unrounded": 938.8608126904453
      },
      "code_completion": {
        "cases": 50,
        "passed": 5,
        "accuracy": 0.1,
        "weighted_points": 11.899999999999999,
        "possible_weighted_points": 109.89999999999999,
        "weighted_accuracy": 0.10828025477707005,
        "elo": 729,
        "elo_unrounded": 728.9371753478358
      }
    },
    "difficulties": {
      "easy": {
        "cases": 117,
        "passed": 39,
        "accuracy": 0.3333333333333333,
        "weighted_points": 44.25,
        "possible_weighted_points": 141.2,
        "weighted_accuracy": 0.3133852691218131,
        "elo": 731,
        "elo_unrounded": 730.9701408690678
      },
      "medium": {
        "cases": 117,
        "passed": 32,
        "accuracy": 0.27350427350427353,
        "weighted_points": 57.300000000000004,
        "possible_weighted_points": 211.875,
        "weighted_accuracy": 0.2704424778761062,
        "elo": 791,
        "elo_unrounded": 790.8983609544082
      },
      "hard": {
        "cases": 116,
        "passed": 35,
        "accuracy": 0.3017241379310345,
        "weighted_points": 91.0125,
        "possible_weighted_points": 315.1125,
        "weighted_accuracy": 0.2888254194930382,
        "elo": 953,
        "elo_unrounded": 953.4654883221033
      }
    },
    "context_truncations": 0
  },
  "verification": {
    "complete": true,
    "report_sha256": "befd8ed7c3b5d2862a12eca06bcb443a49d415f3386e70cb7f1480283f0b9f2f",
    "runner_sha256": "973a81d09d1c4075d031e1369b4278c52a7813d1ab3b11b33eef665d3247bf2c",
    "verifier_sha256": "a0d441f3e633abd1b282d8728f435c777bbc9317a3410865a1d9d31598802d40",
    "runtime": {
      "torch": "2.14.0+cpu",
      "transformers": "5.3.0",
      "tokenizers": "0.22.2"
    },
    "checks": [
      "350 unique original records and all choices",
      "mean-logprob predictions and item weights",
      "overall/category/difficulty accuracy and weighted accuracy",
      "fixed-item Elo likelihood equation with official prior",
      "reported context truncations"
    ],
    "scope": "Result integrity and official-runner aggregation; not an independent model rerun or contamination guarantee."
  }
}