{
 "groups": [
  "Knowledge & Reasoning",
  "Reading & QA",
  "Classification",
  "Generation",
  "Instruction",
  "Grammar & Morphology"
 ],
 "tasks": [
  {
   "key": "arc",
   "label": "ARC",
   "group": "Knowledge & Reasoning",
   "metric": "acc"
  },
  {
   "key": "mmlu",
   "label": "MMLU",
   "group": "Knowledge & Reasoning",
   "metric": "acc"
  },
  {
   "key": "globalmmlu_lite",
   "label": "G-MMLU",
   "group": "Knowledge & Reasoning",
   "metric": "acc"
  },
  {
   "key": "truthful_qa",
   "label": "TruthQA",
   "group": "Knowledge & Reasoning",
   "metric": "acc"
  },
  {
   "key": "scio",
   "label": "SCIO",
   "group": "Knowledge & Reasoning",
   "metric": "acc"
  },
  {
   "key": "financial_exams",
   "label": "FinExam",
   "group": "Knowledge & Reasoning",
   "metric": "acc"
  },
  {
   "key": "driving_test",
   "label": "Driving",
   "group": "Knowledge & Reasoning",
   "metric": "acc"
  },
  {
   "key": "slovakcopa",
   "label": "COPA",
   "group": "Knowledge & Reasoning",
   "metric": "acc"
  },
  {
   "key": "skj1",
   "label": "SKJ1",
   "group": "Knowledge & Reasoning",
   "metric": "acc"
  },
  {
   "key": "slovak_trivia",
   "label": "Trivia",
   "group": "Knowledge & Reasoning",
   "metric": "acc"
  },
  {
   "key": "belebele",
   "label": "Belebele",
   "group": "Reading & QA",
   "metric": "acc"
  },
  {
   "key": "chiby",
   "label": "Chiby",
   "group": "Reading & QA",
   "metric": "acc"
  },
  {
   "key": "multi_wiki_qa",
   "label": "WikiQA",
   "group": "Reading & QA",
   "metric": "qem"
  },
  {
   "key": "e_tests_mqa",
   "label": "ETest-M",
   "group": "Reading & QA",
   "metric": "acc"
  },
  {
   "key": "e_tests_qa",
   "label": "ETest-Q",
   "group": "Reading & QA",
   "metric": "qem"
  },
  {
   "key": "slovak_tests_mqa",
   "label": "SKTest-M",
   "group": "Reading & QA",
   "metric": "acc"
  },
  {
   "key": "slovak_tests_qa",
   "label": "SKTest-Q",
   "group": "Reading & QA",
   "metric": "qem"
  },
  {
   "key": "oneruler",
   "label": "OneRuler",
   "group": "Reading & QA",
   "metric": "acc"
  },
  {
   "key": "sklep_qa",
   "label": "sKLEP-QA",
   "group": "Reading & QA",
   "metric": "qem"
  },
  {
   "key": "nli_sk",
   "label": "NLI",
   "group": "Classification",
   "metric": "acc"
  },
  {
   "key": "sklep_nli",
   "label": "sKLEP-NLI",
   "group": "Classification",
   "metric": "acc"
  },
  {
   "key": "sklep_rte",
   "label": "sKLEP-RTE",
   "group": "Classification",
   "metric": "acc"
  },
  {
   "key": "senti_sk_3class",
   "label": "Senti-3",
   "group": "Classification",
   "metric": "acc"
  },
  {
   "key": "senti_sk_binary",
   "label": "Senti-2",
   "group": "Classification",
   "metric": "acc"
  },
  {
   "key": "sklep_sentiment_analysis",
   "label": "sKLEP-Sent",
   "group": "Classification",
   "metric": "acc"
  },
  {
   "key": "movie_review",
   "label": "MovieRev",
   "group": "Classification",
   "metric": "acc"
  },
  {
   "key": "toxic_sk",
   "label": "Toxic",
   "group": "Classification",
   "metric": "acc"
  },
  {
   "key": "sklep_hate_speech",
   "label": "sKLEP-Hate",
   "group": "Classification",
   "metric": "acc"
  },
  {
   "key": "slovaksum",
   "label": "SlovakSum",
   "group": "Generation",
   "metric": "rougeL"
  },
  {
   "key": "smesum",
   "label": "SMESum",
   "group": "Generation",
   "metric": "rougeL"
  },
  {
   "key": "ifeval_sk",
   "label": "IFEval",
   "group": "Instruction",
   "metric": "prompt_level_strict_acc"
  },
  {
   "key": "analogies_sk",
   "label": "Analogies",
   "group": "Grammar & Morphology",
   "metric": "acc"
  },
  {
   "key": "slohry",
   "label": "Slohry",
   "group": "Grammar & Morphology",
   "metric": "acc"
  }
 ],
 "lang": [
  {
   "group": "Knowledge & Reasoning",
   "sk": 58.1,
   "en": 58.3,
   "delta": 0.1
  },
  {
   "group": "Reading & QA",
   "sk": 39.4,
   "en": 41.0,
   "delta": 1.6
  },
  {
   "group": "Classification",
   "sk": 61.3,
   "en": 61.1,
   "delta": -0.2
  },
  {
   "group": "Generation",
   "sk": 13.2,
   "en": 13.1,
   "delta": -0.1
  },
  {
   "group": "Grammar & Morphology",
   "sk": 33.5,
   "en": 30.9,
   "delta": -2.6
  },
  {
   "group": "__overall__",
   "sk": 49.9,
   "en": 50.3,
   "delta": 0.4
  }
 ],
 "models": [
  {
   "key": "google__gemini-3.1-pro-preview",
   "name": "Gemini 3.1 Pro",
   "open": false,
   "params": null,
   "overall": 72.6,
   "groups": [
    92.4,
    71.3,
    82.6,
    14.8,
    87.2,
    87.6
   ],
   "tasks": [
    97.0,
    91.5,
    94.0,
    94.4,
    82.0,
    96.3,
    98.3,
    91.5,
    84.3,
    94.3,
    95.8,
    74.4,
    31.8,
    88.7,
    73.7,
    89.6,
    37.5,
    100.0,
    49.9,
    82.5,
    85.2,
    85.8,
    62.2,
    77.3,
    97.8,
    95.7,
    83.6,
    73.8,
    13.9,
    15.7,
    87.2,
    76.8,
    98.5
   ],
   "tasks_en": [
    96.9,
    91.3,
    94.8,
    93.9,
    81.5,
    96.2,
    98.0,
    91.6,
    82.3,
    93.6,
    96.0,
    75.1,
    35.8,
    88.3,
    69.7,
    89.7,
    38.1,
    100.0,
    52.3,
    84.1,
    85.6,
    86.4,
    62.2,
    77.3,
    97.6,
    96.1,
    82.1,
    73.3,
    14.1,
    16.0,
    null,
    75.7,
    null
   ]
  },
  {
   "key": "openai__gpt-5.5",
   "name": "GPT-5.5",
   "open": false,
   "params": null,
   "overall": 71.0,
   "groups": [
    89.2,
    67.3,
    81.6,
    15.5,
    86.4,
    86.1
   ],
   "tasks": [
    96.5,
    91.2,
    92.9,
    84.8,
    81.1,
    96.0,
    96.1,
    77.8,
    83.3,
    92.4,
    95.0,
    74.5,
    18.3,
    87.9,
    67.6,
    88.8,
    35.6,
    99.9,
    38.2,
    79.7,
    81.3,
    83.7,
    61.3,
    76.0,
    98.3,
    95.2,
    85.1,
    74.0,
    14.1,
    16.9,
    86.4,
    74.1,
    98.0
   ],
   "tasks_en": [
    96.4,
    91.3,
    92.7,
    84.0,
    81.1,
    96.4,
    96.1,
    82.5,
    82.0,
    93.5,
    94.2,
    74.1,
    22.7,
    87.5,
    70.5,
    88.8,
    35.6,
    99.9,
    43.0,
    80.4,
    80.9,
    83.7,
    60.7,
    75.3,
    97.9,
    95.2,
    80.7,
    73.8,
    14.3,
    17.0,
    null,
    71.8,
    null
   ]
  },
  {
   "key": "anthropic.claude-opus-4-6",
   "name": "Claude Opus 4.6",
   "open": false,
   "params": null,
   "overall": 68.1,
   "groups": [
    87.2,
    58.6,
    83.4,
    15.4,
    80.6,
    83.6
   ],
   "tasks": [
    94.8,
    88.2,
    91.5,
    91.4,
    74.3,
    93.2,
    91.6,
    90.8,
    80.3,
    76.2,
    94.8,
    73.2,
    16.8,
    79.0,
    33.9,
    83.9,
    14.8,
    99.8,
    31.2,
    83.2,
    85.3,
    80.9,
    59.9,
    79.7,
    97.4,
    94.8,
    90.3,
    78.8,
    14.6,
    16.1,
    80.6,
    71.4,
    95.7
   ],
   "tasks_en": [
    93.8,
    86.8,
    90.5,
    89.8,
    71.6,
    92.6,
    91.3,
    87.9,
    83.0,
    78.5,
    94.4,
    71.5,
    14.1,
    70.6,
    23.7,
    81.3,
    13.4,
    100.0,
    33.3,
    81.6,
    83.0,
    80.2,
    57.8,
    72.7,
    97.8,
    94.3,
    85.5,
    79.3,
    14.9,
    16.8,
    null,
    66.8,
    null
   ]
  },
  {
   "key": "google__gemini-3.1-flash-lite-preview",
   "name": "Gemini 3.1 Flash-Lite",
   "open": false,
   "params": null,
   "overall": 66.7,
   "groups": [
    85.7,
    54.8,
    82.2,
    14.0,
    82.7,
    80.8
   ],
   "tasks": [
    94.8,
    84.2,
    89.9,
    81.2,
    71.1,
    89.7,
    91.5,
    90.7,
    84.7,
    79.7,
    93.9,
    75.0,
    11.1,
    80.1,
    17.8,
    85.5,
    9.9,
    99.8,
    20.4,
    81.2,
    81.7,
    82.8,
    61.3,
    78.5,
    97.4,
    94.1,
    85.9,
    76.5,
    13.5,
    14.5,
    82.7,
    67.9,
    93.7
   ],
   "tasks_en": [
    94.7,
    83.8,
    88.9,
    79.3,
    70.7,
    89.5,
    92.4,
    90.3,
    84.7,
    77.6,
    94.2,
    71.8,
    17.6,
    80.8,
    26.6,
    85.5,
    18.3,
    99.8,
    31.0,
    83.4,
    82.7,
    83.9,
    60.5,
    80.8,
    97.5,
    94.4,
    81.0,
    75.4,
    13.6,
    15.1,
    null,
    64.1,
    null
   ]
  },
  {
   "key": "anthropic.claude-sonnet-4-6",
   "name": "Claude Sonnet 4.6",
   "open": false,
   "params": null,
   "overall": 64.9,
   "groups": [
    84.7,
    54.0,
    81.6,
    15.3,
    78.0,
    75.8
   ],
   "tasks": [
    94.0,
    85.3,
    89.6,
    80.6,
    73.2,
    89.6,
    88.5,
    90.9,
    82.0,
    73.4,
    93.3,
    68.8,
    14.7,
    59.9,
    32.6,
    81.9,
    12.3,
    100.0,
    22.3,
    80.6,
    83.0,
    80.1,
    60.3,
    81.3,
    95.4,
    91.2,
    85.1,
    77.7,
    14.4,
    16.1,
    78.0,
    63.1,
    88.5
   ],
   "tasks_en": [
    93.0,
    84.0,
    87.6,
    78.6,
    71.5,
    88.5,
    88.2,
    90.1,
    80.3,
    73.0,
    91.2,
    66.2,
    14.1,
    58.9,
    28.2,
    79.4,
    14.3,
    100.0,
    19.8,
    72.5,
    74.1,
    81.3,
    54.1,
    73.8,
    95.3,
    87.0,
    78.1,
    76.9,
    14.6,
    16.4,
    null,
    62.9,
    null
   ]
  },
  {
   "key": "openai__gpt-5.4-mini",
   "name": "GPT-5.4 mini",
   "open": false,
   "params": null,
   "overall": 63.9,
   "groups": [
    78.2,
    58.0,
    79.0,
    15.2,
    80.1,
    73.0
   ],
   "tasks": [
    91.3,
    74.7,
    82.2,
    70.6,
    64.0,
    84.3,
    87.0,
    90.6,
    78.0,
    59.3,
    92.0,
    71.0,
    19.3,
    72.5,
    32.4,
    80.4,
    17.9,
    99.9,
    37.0,
    68.2,
    67.5,
    81.4,
    58.8,
    82.5,
    96.7,
    91.5,
    86.4,
    77.7,
    13.9,
    16.5,
    80.1,
    60.4,
    85.5
   ],
   "tasks_en": [
    91.1,
    75.0,
    82.4,
    69.9,
    63.4,
    84.2,
    87.1,
    90.1,
    79.3,
    58.5,
    91.7,
    69.9,
    26.0,
    72.7,
    34.7,
    80.2,
    20.2,
    99.7,
    38.9,
    74.4,
    68.8,
    81.2,
    57.7,
    83.2,
    95.3,
    91.5,
    78.9,
    76.3,
    13.8,
    16.9,
    null,
    56.7,
    null
   ]
  },
  {
   "key": "openai__gpt-oss-120b",
   "name": "gpt-oss 120B",
   "open": true,
   "params": 120.0,
   "overall": 60.0,
   "groups": [
    73.7,
    53.2,
    79.0,
    13.5,
    74.9,
    65.3
   ],
   "tasks": [
    90.6,
    77.9,
    81.0,
    65.9,
    71.6,
    74.4,
    76.0,
    83.9,
    64.7,
    51.4,
    92.2,
    65.0,
    14.6,
    71.0,
    27.9,
    71.7,
    17.5,
    90.9,
    28.4,
    72.8,
    75.8,
    83.2,
    57.8,
    75.6,
    96.4,
    89.8,
    84.8,
    75.3,
    12.9,
    14.2,
    74.9,
    50.5,
    80.2
   ],
   "tasks_en": [
    91.6,
    78.8,
    80.6,
    63.0,
    72.2,
    73.3,
    77.8,
    80.1,
    65.7,
    52.6,
    91.4,
    66.6,
    20.3,
    70.6,
    36.0,
    72.4,
    21.0,
    91.0,
    36.0,
    76.8,
    79.1,
    85.8,
    55.2,
    71.1,
    96.1,
    89.9,
    79.3,
    74.8,
    12.9,
    14.4,
    null,
    47.9,
    null
   ]
  },
  {
   "key": "zai-org__GLM-5.1-FP8",
   "name": "GLM-5.1",
   "open": true,
   "params": 754.0,
   "overall": 57.6,
   "groups": [
    80.6,
    61.2,
    82.6,
    14.2,
    35.9,
    70.8
   ],
   "tasks": [
    92.3,
    78.7,
    86.2,
    77.3,
    68.6,
    84.8,
    87.7,
    89.8,
    76.3,
    63.9,
    94.0,
    66.5,
    28.0,
    74.3,
    40.8,
    78.7,
    22.0,
    99.3,
    46.7,
    76.9,
    78.1,
    85.0,
    61.9,
    85.9,
    96.6,
    92.5,
    87.9,
    78.6,
    13.5,
    15.0,
    35.9,
    59.7,
    82.0
   ],
   "tasks_en": [
    91.7,
    76.3,
    84.4,
    75.5,
    61.5,
    82.8,
    86.4,
    79.6,
    74.7,
    61.1,
    92.6,
    65.7,
    34.8,
    71.4,
    39.6,
    77.0,
    18.3,
    83.2,
    45.7,
    77.3,
    73.8,
    85.1,
    61.0,
    80.7,
    96.0,
    92.1,
    86.5,
    77.4,
    13.4,
    15.2,
    null,
    55.4,
    null
   ]
  },
  {
   "key": "Qwen__Qwen3.5-397B-A17B",
   "name": "Qwen3.5 397B-A17B",
   "open": true,
   "params": 397.0,
   "overall": 57.4,
   "groups": [
    83.4,
    55.5,
    80.6,
    14.6,
    37.8,
    72.3
   ],
   "tasks": [
    94.9,
    82.8,
    90.1,
    80.8,
    73.6,
    87.8,
    86.3,
    90.1,
    79.0,
    68.7,
    94.6,
    72.2,
    9.9,
    78.0,
    33.9,
    80.5,
    19.9,
    83.4,
    27.2,
    78.6,
    77.2,
    82.5,
    61.7,
    81.3,
    96.3,
    94.0,
    78.2,
    75.2,
    13.5,
    15.8,
    37.8,
    61.7,
    82.8
   ],
   "tasks_en": [
    95.0,
    82.8,
    89.6,
    79.8,
    73.4,
    87.6,
    86.3,
    90.1,
    82.3,
    68.5,
    94.7,
    70.0,
    14.0,
    77.0,
    45.0,
    80.6,
    25.8,
    83.3,
    31.8,
    64.8,
    67.4,
    82.6,
    45.2,
    57.2,
    85.2,
    84.0,
    72.9,
    75.4,
    13.7,
    16.1,
    null,
    57.7,
    null
   ]
  },
  {
   "key": "MiniMaxAI__MiniMax-M2.7",
   "name": "MiniMax M2.7",
   "open": true,
   "params": 230.0,
   "overall": 57.1,
   "groups": [
    78.0,
    51.5,
    78.4,
    13.5,
    44.7,
    76.6
   ],
   "tasks": [
    93.6,
    82.9,
    86.9,
    73.1,
    71.7,
    81.6,
    83.5,
    83.1,
    63.3,
    59.9,
    93.0,
    59.5,
    21.4,
    73.1,
    42.4,
    76.0,
    22.8,
    34.7,
    40.6,
    72.6,
    75.4,
    81.7,
    57.2,
    71.7,
    96.8,
    92.4,
    83.5,
    74.4,
    13.0,
    14.1,
    44.7,
    63.0,
    90.2
   ],
   "tasks_en": [
    93.6,
    82.2,
    86.7,
    71.1,
    71.8,
    80.8,
    82.6,
    82.9,
    60.7,
    60.3,
    92.9,
    61.0,
    24.9,
    73.2,
    46.9,
    75.7,
    24.1,
    34.3,
    42.5,
    74.7,
    77.8,
    82.1,
    55.8,
    69.5,
    96.4,
    92.5,
    78.7,
    74.5,
    13.1,
    14.5,
    null,
    62.5,
    null
   ]
  },
  {
   "key": "moonshotai__Kimi-K2.6",
   "name": "Kimi K2.6",
   "open": true,
   "params": 1100.0,
   "overall": 55.7,
   "groups": [
    80.6,
    52.7,
    78.0,
    14.7,
    31.8,
    76.2
   ],
   "tasks": [
    93.1,
    78.7,
    84.8,
    78.6,
    64.7,
    87.0,
    85.7,
    90.2,
    81.0,
    62.4,
    94.0,
    65.2,
    23.4,
    73.4,
    38.1,
    77.6,
    18.3,
    45.4,
    39.2,
    60.2,
    57.3,
    84.1,
    60.8,
    82.8,
    97.0,
    93.1,
    88.6,
    77.9,
    13.8,
    15.7,
    31.8,
    62.6,
    89.8
   ],
   "tasks_en": [
    92.6,
    79.1,
    85.7,
    78.1,
    67.7,
    85.8,
    85.7,
    90.9,
    79.3,
    64.3,
    94.7,
    63.3,
    37.1,
    74.4,
    44.1,
    78.8,
    23.1,
    0.7,
    44.1,
    65.3,
    61.4,
    84.2,
    58.2,
    77.8,
    96.4,
    92.6,
    83.3,
    77.8,
    14.2,
    16.6,
    null,
    57.5,
    null
   ]
  },
  {
   "key": "Qwen__Qwen3.5-27B",
   "name": "Qwen3.5 27B",
   "open": true,
   "params": 27.0,
   "overall": 55.3,
   "groups": [
    81.2,
    55.7,
    79.5,
    14.9,
    36.1,
    64.6
   ],
   "tasks": [
    94.5,
    80.0,
    84.9,
    76.8,
    69.1,
    83.2,
    87.8,
    90.5,
    82.7,
    62.1,
    93.7,
    69.0,
    16.6,
    73.6,
    27.8,
    77.4,
    18.2,
    83.3,
    41.3,
    70.1,
    68.3,
    79.9,
    61.3,
    80.0,
    97.3,
    93.6,
    86.5,
    78.9,
    13.7,
    16.2,
    36.1,
    54.7,
    74.5
   ],
   "tasks_en": [
    94.3,
    80.0,
    84.8,
    74.9,
    69.1,
    82.3,
    86.1,
    87.5,
    80.0,
    61.0,
    93.4,
    68.9,
    21.6,
    72.2,
    33.9,
    76.7,
    19.0,
    83.3,
    42.6,
    29.7,
    29.3,
    85.0,
    44.4,
    64.3,
    91.1,
    89.6,
    81.0,
    79.0,
    13.9,
    16.4,
    null,
    51.6,
    null
   ]
  },
  {
   "key": "google__gemma-4-31B-it",
   "name": "Gemma 4 31B",
   "open": true,
   "params": 31.0,
   "overall": 54.3,
   "groups": [
    78.8,
    53.1,
    82.4,
    14.4,
    30.2,
    66.7
   ],
   "tasks": [
    94.7,
    79.6,
    86.9,
    78.7,
    63.4,
    84.5,
    87.9,
    85.9,
    66.3,
    59.7,
    94.1,
    66.9,
    13.1,
    70.7,
    27.9,
    77.7,
    14.8,
    83.3,
    29.6,
    81.2,
    82.6,
    84.5,
    60.3,
    75.9,
    97.1,
    93.3,
    88.3,
    78.1,
    13.8,
    15.0,
    30.2,
    54.0,
    79.4
   ],
   "tasks_en": [
    94.6,
    78.5,
    85.4,
    74.9,
    62.4,
    83.4,
    86.9,
    83.3,
    68.7,
    56.6,
    93.9,
    63.6,
    11.8,
    66.7,
    32.1,
    77.3,
    19.5,
    83.3,
    33.8,
    83.8,
    84.3,
    85.4,
    58.9,
    77.7,
    96.4,
    93.3,
    81.2,
    76.9,
    13.9,
    15.3,
    null,
    50.0,
    null
   ]
  },
  {
   "key": "Qwen__Qwen3.6-27B",
   "name": "Qwen3.6 27B",
   "open": true,
   "params": 27.0,
   "overall": 54.2,
   "groups": [
    79.8,
    59.7,
    70.7,
    14.9,
    35.0,
    65.0
   ],
   "tasks": [
    93.7,
    79.6,
    83.3,
    77.8,
    69.3,
    83.6,
    86.9,
    88.5,
    76.7,
    58.1,
    94.0,
    67.4,
    34.4,
    71.9,
    39.7,
    76.1,
    21.6,
    83.3,
    48.8,
    29.6,
    27.9,
    85.9,
    62.5,
    83.5,
    97.1,
    93.6,
    81.2,
    75.1,
    13.7,
    16.2,
    35.0,
    54.6,
    75.4
   ],
   "tasks_en": [
    94.0,
    79.5,
    84.4,
    77.1,
    69.0,
    82.5,
    87.2,
    86.5,
    73.3,
    57.1,
    93.8,
    68.6,
    33.0,
    70.6,
    39.6,
    75.9,
    21.0,
    83.3,
    49.4,
    27.6,
    26.4,
    85.3,
    41.5,
    56.6,
    85.1,
    77.3,
    79.1,
    76.4,
    13.7,
    16.3,
    null,
    51.2,
    null
   ]
  },
  {
   "key": "openai__gpt-oss-20b",
   "name": "gpt-oss 20B",
   "open": true,
   "params": 20.0,
   "overall": 54.1,
   "groups": [
    67.4,
    47.6,
    76.9,
    13.0,
    62.4,
    57.2
   ],
   "tasks": [
    88.1,
    72.6,
    74.8,
    58.7,
    67.1,
    65.5,
    72.8,
    83.3,
    56.7,
    34.4,
    89.6,
    62.6,
    14.8,
    61.5,
    15.6,
    65.0,
    9.4,
    85.1,
    24.6,
    71.0,
    72.1,
    80.7,
    56.1,
    72.5,
    96.1,
    87.3,
    82.1,
    73.9,
    12.5,
    13.5,
    62.4,
    42.5,
    71.9
   ],
   "tasks_en": [
    88.5,
    73.6,
    74.8,
    53.2,
    67.6,
    64.5,
    73.4,
    83.3,
    59.0,
    34.6,
    90.0,
    65.1,
    28.2,
    62.3,
    24.2,
    65.6,
    12.9,
    85.7,
    33.2,
    74.0,
    76.4,
    83.6,
    53.9,
    70.9,
    95.7,
    87.9,
    75.6,
    74.1,
    12.8,
    13.7,
    null,
    40.9,
    null
   ]
  },
  {
   "key": "meta-llama__Llama-3.3-70B-Instruct",
   "name": "Llama 3.3 70B",
   "open": true,
   "params": 70.0,
   "overall": 53.1,
   "groups": [
    72.1,
    53.9,
    79.4,
    21.4,
    35.4,
    56.4
   ],
   "tasks": [
    87.5,
    72.3,
    80.6,
    66.0,
    59.7,
    76.2,
    83.8,
    87.3,
    57.0,
    50.2,
    91.6,
    62.2,
    29.1,
    63.6,
    33.3,
    69.4,
    16.2,
    81.2,
    38.1,
    68.2,
    72.3,
    81.2,
    57.6,
    82.0,
    96.9,
    92.7,
    85.1,
    79.0,
    16.1,
    26.6,
    35.4,
    47.2,
    65.6
   ],
   "tasks_en": [
    86.7,
    71.5,
    79.2,
    63.6,
    59.4,
    73.8,
    81.6,
    83.6,
    48.7,
    53.4,
    91.3,
    58.5,
    33.9,
    62.3,
    33.1,
    69.2,
    18.2,
    82.1,
    41.0,
    69.0,
    73.4,
    79.7,
    51.7,
    72.1,
    93.9,
    91.0,
    83.1,
    77.3,
    16.2,
    24.3,
    null,
    45.4,
    null
   ]
  },
  {
   "key": "Qwen__Qwen3.6-35B-A3B",
   "name": "Qwen3.6 35B-A3B",
   "open": true,
   "params": 35.0,
   "overall": 52.2,
   "groups": [
    77.2,
    55.4,
    71.8,
    14.5,
    32.8,
    61.4
   ],
   "tasks": [
    92.3,
    76.3,
    81.5,
    76.0,
    65.8,
    80.7,
    83.5,
    85.5,
    76.3,
    53.7,
    92.5,
    69.8,
    23.7,
    69.7,
    31.0,
    75.6,
    14.4,
    83.4,
    38.9,
    40.2,
    36.1,
    85.5,
    55.6,
    77.8,
    97.3,
    93.0,
    84.6,
    76.4,
    13.6,
    15.3,
    32.8,
    51.2,
    71.6
   ],
   "tasks_en": [
    92.6,
    75.8,
    80.9,
    74.6,
    66.6,
    79.4,
    81.7,
    82.9,
    74.0,
    50.9,
    92.3,
    68.3,
    34.6,
    69.2,
    36.1,
    75.5,
    15.5,
    83.3,
    43.3,
    27.6,
    27.0,
    83.4,
    39.8,
    58.0,
    91.9,
    90.0,
    81.5,
    76.5,
    13.9,
    15.9,
    null,
    46.4,
    null
   ]
  },
  {
   "key": "Qwen__Qwen3.5-9B",
   "name": "Qwen3.5 9B",
   "open": true,
   "params": 9.0,
   "overall": 47.9,
   "groups": [
    69.7,
    50.4,
    77.0,
    15.0,
    31.1,
    44.4
   ],
   "tasks": [
    88.7,
    67.6,
    72.2,
    64.8,
    61.3,
    73.9,
    78.3,
    81.0,
    61.0,
    47.9,
    89.3,
    61.6,
    18.4,
    62.0,
    20.2,
    65.8,
    12.9,
    83.2,
    39.8,
    65.9,
    68.3,
    83.5,
    60.1,
    82.5,
    95.4,
    90.9,
    69.1,
    77.1,
    13.6,
    16.3,
    31.1,
    42.1,
    46.7
   ],
   "tasks_en": [
    88.5,
    67.6,
    71.8,
    60.9,
    60.7,
    73.1,
    78.9,
    82.4,
    60.7,
    47.6,
    88.9,
    63.9,
    22.2,
    62.5,
    26.6,
    66.9,
    15.3,
    84.5,
    38.5,
    74.5,
    71.5,
    85.1,
    46.6,
    60.0,
    89.4,
    88.8,
    74.2,
    76.5,
    13.5,
    16.0,
    null,
    39.2,
    null
   ]
  },
  {
   "key": "Qwen__Qwen3-14B",
   "name": "Qwen3 14B",
   "open": true,
   "params": 14.0,
   "overall": 47.4,
   "groups": [
    67.1,
    49.1,
    74.3,
    16.2,
    34.1,
    44.0
   ],
   "tasks": [
    85.7,
    65.5,
    65.1,
    63.1,
    59.4,
    70.9,
    79.6,
    76.5,
    59.7,
    45.2,
    88.7,
    63.4,
    23.3,
    58.9,
    16.0,
    62.5,
    10.1,
    85.1,
    33.5,
    50.0,
    54.6,
    83.4,
    58.1,
    76.6,
    94.3,
    90.0,
    84.3,
    77.4,
    14.2,
    18.2,
    34.1,
    41.4,
    46.5
   ],
   "tasks_en": [
    83.8,
    64.7,
    66.2,
    58.5,
    58.7,
    67.9,
    79.6,
    75.7,
    63.3,
    46.8,
    88.7,
    60.5,
    28.3,
    57.8,
    21.6,
    62.0,
    11.8,
    85.8,
    37.8,
    47.2,
    52.8,
    83.7,
    47.4,
    71.9,
    89.1,
    88.7,
    76.5,
    76.8,
    13.9,
    16.6,
    null,
    37.0,
    null
   ]
  },
  {
   "key": "ibm-granite__granite-4.0-h-small",
   "name": "Granite 4.0-H Small",
   "open": true,
   "params": 32.0,
   "overall": 47.0,
   "groups": [
    67.3,
    42.4,
    71.9,
    16.4,
    33.9,
    50.0
   ],
   "tasks": [
    84.2,
    65.6,
    73.8,
    63.4,
    56.5,
    69.3,
    74.3,
    83.5,
    54.3,
    47.7,
    86.1,
    53.5,
    15.0,
    57.2,
    13.8,
    66.3,
    8.1,
    56.9,
    24.9,
    46.7,
    48.8,
    82.7,
    55.1,
    76.4,
    95.7,
    89.1,
    79.7,
    72.8,
    14.7,
    18.1,
    33.9,
    44.2,
    55.9
   ],
   "tasks_en": [
    83.6,
    64.5,
    72.5,
    62.2,
    55.5,
    66.9,
    69.9,
    77.9,
    59.3,
    46.4,
    86.7,
    58.5,
    25.2,
    56.5,
    16.5,
    66.7,
    9.2,
    75.0,
    26.4,
    72.4,
    72.4,
    84.2,
    47.5,
    62.8,
    94.1,
    88.6,
    73.7,
    73.6,
    14.6,
    18.1,
    null,
    43.6,
    null
   ]
  },
  {
   "key": "speakleash__Bielik-11B-v3.0-Instruct",
   "name": "Bielik 11B",
   "open": true,
   "params": 11.0,
   "overall": 46.3,
   "groups": [
    66.5,
    47.1,
    74.6,
    12.6,
    30.4,
    46.9
   ],
   "tasks": [
    83.7,
    61.3,
    68.4,
    66.7,
    53.5,
    73.5,
    75.4,
    85.9,
    45.3,
    51.7,
    89.9,
    59.3,
    7.0,
    55.7,
    25.4,
    66.2,
    16.4,
    86.7,
    17.3,
    66.2,
    68.2,
    80.4,
    50.8,
    72.3,
    81.0,
    86.2,
    90.4,
    76.3,
    12.9,
    12.3,
    30.4,
    41.9,
    51.8
   ],
   "tasks_en": [
    82.2,
    61.3,
    69.2,
    58.4,
    54.7,
    72.5,
    73.9,
    82.2,
    52.0,
    52.9,
    89.6,
    58.7,
    22.8,
    54.9,
    30.8,
    65.4,
    18.9,
    86.5,
    31.8,
    76.3,
    78.4,
    81.9,
    58.5,
    76.0,
    95.9,
    92.4,
    84.6,
    77.4,
    13.0,
    12.6,
    null,
    38.0,
    null
   ]
  },
  {
   "key": "utter-project__EuroLLM-22B-Instruct-2512",
   "name": "EuroLLM 22B",
   "open": true,
   "params": 22.0,
   "overall": 45.2,
   "groups": [
    63.9,
    41.6,
    75.0,
    15.2,
    26.4,
    49.2
   ],
   "tasks": [
    80.6,
    59.2,
    68.0,
    58.2,
    48.4,
    69.2,
    76.9,
    77.5,
    47.3,
    53.4,
    83.4,
    53.9,
    12.2,
    56.3,
    16.0,
    66.5,
    9.9,
    54.0,
    22.0,
    54.4,
    50.9,
    78.8,
    61.4,
    85.8,
    94.6,
    88.6,
    86.2,
    74.3,
    14.2,
    16.2,
    26.4,
    44.9,
    53.6
   ],
   "tasks_en": [
    78.9,
    56.9,
    65.6,
    58.4,
    46.9,
    66.9,
    81.0,
    76.1,
    50.7,
    49.8,
    82.3,
    62.3,
    14.9,
    54.8,
    19.9,
    66.1,
    12.0,
    64.9,
    28.6,
    68.0,
    72.1,
    83.4,
    57.1,
    82.0,
    94.6,
    88.3,
    81.1,
    78.8,
    14.4,
    16.3,
    null,
    38.6,
    null
   ]
  },
  {
   "key": "mistralai__Mistral-Large-3-675B-Instruct-2512",
   "name": "Mistral Large 3 675B",
   "open": true,
   "params": 675.0,
   "overall": 45.0,
   "groups": [
    77.3,
    49.3,
    65.3,
    11.8,
    20.9,
    45.3
   ],
   "tasks": [
    90.8,
    77.0,
    83.7,
    72.7,
    65.4,
    82.2,
    83.9,
    89.6,
    64.3,
    63.2,
    93.0,
    61.8,
    16.7,
    62.0,
    24.8,
    76.8,
    11.1,
    73.2,
    24.1,
    71.9,
    68.7,
    83.0,
    28.8,
    35.8,
    85.3,
    47.4,
    88.2,
    78.2,
    11.2,
    12.3,
    20.9,
    58.0,
    32.6
   ],
   "tasks_en": [
    90.6,
    76.7,
    83.5,
    71.9,
    64.8,
    79.7,
    84.2,
    85.7,
    62.0,
    61.9,
    92.4,
    59.7,
    15.0,
    61.2,
    22.3,
    75.7,
    12.6,
    10.4,
    21.6,
    70.0,
    69.0,
    67.5,
    28.4,
    42.8,
    73.5,
    47.1,
    78.5,
    76.4,
    12.9,
    15.0,
    null,
    54.6,
    null
   ]
  },
  {
   "key": "swiss-ai__Apertus-70B-Instruct-2509",
   "name": "Apertus 70B",
   "open": true,
   "params": 70.0,
   "overall": 44.4,
   "groups": [
    57.5,
    43.3,
    69.7,
    13.2,
    27.9,
    54.8
   ],
   "tasks": [
    71.3,
    53.5,
    62.8,
    43.2,
    45.8,
    67.8,
    67.1,
    73.0,
    43.0,
    47.6,
    78.8,
    50.7,
    19.2,
    45.7,
    17.2,
    60.2,
    12.5,
    80.5,
    24.8,
    47.2,
    42.6,
    70.4,
    54.8,
    74.8,
    95.9,
    89.2,
    79.6,
    72.9,
    13.2,
    13.2,
    27.9,
    48.7,
    60.8
   ],
   "tasks_en": [
    71.3,
    53.5,
    63.2,
    44.2,
    45.9,
    66.4,
    70.1,
    65.6,
    51.0,
    48.8,
    83.0,
    49.9,
    22.5,
    45.7,
    14.6,
    61.2,
    12.2,
    80.1,
    21.2,
    63.0,
    60.6,
    76.6,
    49.0,
    69.3,
    93.3,
    88.8,
    51.7,
    71.8,
    13.5,
    13.8,
    null,
    37.9,
    null
   ]
  },
  {
   "key": "mrshu__qwen3-14b-sk-alpaca-slovak-it",
   "name": "Qwen3-SK 14B (Alpaca)",
   "open": true,
   "params": 14.0,
   "overall": 43.8,
   "groups": [
    70.0,
    45.6,
    60.2,
    15.0,
    41.0,
    30.9
   ],
   "tasks": [
    86.7,
    66.2,
    68.9,
    70.7,
    59.3,
    71.0,
    81.9,
    80.5,
    65.0,
    50.1,
    89.7,
    63.5,
    10.7,
    58.7,
    18.4,
    67.6,
    9.9,
    83.9,
    7.6,
    68.0,
    67.4,
    82.8,
    32.6,
    51.0,
    15.3,
    59.0,
    87.3,
    78.0,
    14.5,
    15.5,
    41.0,
    29.3,
    32.5
   ],
   "tasks_en": [
    86.1,
    65.6,
    69.5,
    68.9,
    59.1,
    70.1,
    83.1,
    83.9,
    66.7,
    49.6,
    89.6,
    20.6,
    11.7,
    58.3,
    17.9,
    67.5,
    11.1,
    76.1,
    7.7,
    46.2,
    45.7,
    50.0,
    12.8,
    4.3,
    28.3,
    9.3,
    3.7,
    5.5,
    14.2,
    14.4,
    null,
    32.0,
    null
   ]
  },
  {
   "key": "utter-project__EuroLLM-9B-Instruct-2512",
   "name": "EuroLLM 9B",
   "open": true,
   "params": 9.0,
   "overall": 42.7,
   "groups": [
    55.8,
    42.7,
    74.6,
    14.9,
    22.7,
    45.2
   ],
   "tasks": [
    75.7,
    54.5,
    62.5,
    40.2,
    45.4,
    63.2,
    69.1,
    70.9,
    30.3,
    46.1,
    82.5,
    58.4,
    19.8,
    45.7,
    16.7,
    63.0,
    8.1,
    63.1,
    27.3,
    57.7,
    57.0,
    78.3,
    68.4,
    88.8,
    87.1,
    81.6,
    81.7,
    70.6,
    13.9,
    16.0,
    22.7,
    40.4,
    50.0
   ],
   "tasks_en": [
    73.8,
    52.9,
    59.6,
    41.3,
    43.5,
    61.2,
    73.0,
    68.1,
    36.3,
    42.1,
    79.1,
    55.5,
    19.6,
    45.1,
    20.5,
    62.1,
    12.9,
    47.5,
    24.5,
    54.7,
    52.5,
    81.5,
    60.1,
    84.7,
    86.7,
    82.3,
    79.2,
    74.2,
    13.5,
    14.9,
    null,
    30.9,
    null
   ]
  },
  {
   "key": "CohereLabs__aya-expanse-32b",
   "name": "Aya Expanse 32B",
   "open": true,
   "params": 32.0,
   "overall": 42.4,
   "groups": [
    61.5,
    41.9,
    76.9,
    14.2,
    24.2,
    35.7
   ],
   "tasks": [
    78.0,
    59.4,
    63.9,
    55.3,
    48.2,
    68.9,
    71.0,
    81.1,
    43.3,
    45.7,
    88.7,
    57.8,
    17.8,
    43.9,
    13.3,
    63.3,
    4.9,
    65.4,
    22.3,
    67.6,
    69.5,
    75.1,
    57.6,
    77.5,
    94.7,
    91.0,
    87.6,
    71.8,
    13.7,
    14.7,
    24.2,
    32.8,
    38.7
   ],
   "tasks_en": [
    78.0,
    60.0,
    64.5,
    57.1,
    49.0,
    69.4,
    70.7,
    79.9,
    41.0,
    45.0,
    90.7,
    44.8,
    22.2,
    44.3,
    14.3,
    63.7,
    6.7,
    49.6,
    27.1,
    58.4,
    58.2,
    76.4,
    40.1,
    59.0,
    84.9,
    89.1,
    82.0,
    76.2,
    14.5,
    16.5,
    null,
    30.4,
    null
   ]
  },
  {
   "key": "mistralai__Ministral-3-8B-Instruct-2512",
   "name": "Ministral 3 8B",
   "open": true,
   "params": 8.0,
   "overall": 40.8,
   "groups": [
    60.4,
    39.2,
    70.6,
    13.5,
    24.0,
    37.1
   ],
   "tasks": [
    78.6,
    59.7,
    64.9,
    45.4,
    53.4,
    68.7,
    71.5,
    67.3,
    47.0,
    47.0,
    85.2,
    54.2,
    9.8,
    50.2,
    12.7,
    61.2,
    6.2,
    58.0,
    15.4,
    54.7,
    50.0,
    74.7,
    51.6,
    72.4,
    96.2,
    89.5,
    81.5,
    65.0,
    13.1,
    14.0,
    24.0,
    32.3,
    41.9
   ],
   "tasks_en": [
    78.6,
    60.3,
    66.0,
    43.5,
    52.9,
    59.3,
    72.8,
    65.8,
    48.3,
    46.1,
    85.6,
    54.1,
    13.7,
    50.4,
    12.3,
    62.1,
    6.3,
    35.4,
    15.9,
    43.0,
    42.2,
    77.4,
    53.4,
    75.2,
    92.0,
    87.6,
    61.2,
    73.6,
    13.2,
    14.7,
    null,
    31.5,
    null
   ]
  },
  {
   "key": "mistralai__Ministral-3-8B-Reasoning-2512",
   "name": "Ministral 3 8B (R)",
   "open": true,
   "params": 8.0,
   "overall": 39.9,
   "groups": [
    54.9,
    37.8,
    61.9,
    13.1,
    39.9,
    32.1
   ],
   "tasks": [
    70.6,
    52.8,
    57.9,
    45.2,
    43.7,
    59.8,
    63.8,
    51.1,
    67.0,
    36.5,
    78.7,
    38.5,
    10.8,
    46.1,
    13.1,
    54.5,
    5.6,
    74.1,
    19.2,
    46.8,
    46.0,
    65.4,
    47.4,
    67.4,
    87.8,
    77.9,
    46.9,
    71.7,
    12.9,
    13.2,
    39.9,
    28.0,
    36.2
   ],
   "tasks_en": [
    71.5,
    52.0,
    59.7,
    60.2,
    48.5,
    39.1,
    69.9,
    57.7,
    28.7,
    36.5,
    80.5,
    52.9,
    13.1,
    43.3,
    11.8,
    49.7,
    4.8,
    90.0,
    18.4,
    49.1,
    49.4,
    76.3,
    55.9,
    80.6,
    78.9,
    76.6,
    49.1,
    72.7,
    12.6,
    13.4,
    null,
    21.2,
    null
   ]
  },
  {
   "key": "mistralai__Ministral-3-14B-Instruct-2512",
   "name": "Ministral 3 14B",
   "open": true,
   "params": 14.0,
   "overall": 37.2,
   "groups": [
    63.8,
    34.6,
    55.9,
    14.2,
    18.4,
    36.5
   ],
   "tasks": [
    82.3,
    62.5,
    66.2,
    51.0,
    51.0,
    72.9,
    73.0,
    68.7,
    61.7,
    48.9,
    87.3,
    58.4,
    5.7,
    57.9,
    13.1,
    63.5,
    4.8,
    4.2,
    16.3,
    58.3,
    56.8,
    77.6,
    23.8,
    40.7,
    49.6,
    46.3,
    78.6,
    71.7,
    13.4,
    15.0,
    18.4,
    36.7,
    36.2
   ],
   "tasks_en": [
    82.1,
    63.4,
    67.3,
    53.3,
    55.8,
    70.3,
    75.9,
    71.8,
    67.7,
    49.1,
    87.6,
    52.9,
    11.8,
    59.7,
    14.2,
    63.8,
    5.5,
    0.0,
    16.7,
    49.2,
    45.1,
    79.8,
    19.7,
    31.3,
    36.0,
    35.7,
    78.8,
    74.0,
    13.4,
    15.1,
    null,
    37.6,
    null
   ]
  },
  {
   "key": "CohereLabs__tiny-aya-water",
   "name": "Tiny-Aya Water",
   "open": true,
   "params": 3.35,
   "overall": 36.4,
   "groups": [
    50.5,
    34.9,
    74.3,
    10.8,
    27.6,
    20.4
   ],
   "tasks": [
    66.1,
    49.6,
    54.6,
    43.4,
    41.3,
    59.7,
    68.0,
    62.6,
    17.7,
    41.9,
    79.0,
    50.7,
    11.7,
    35.9,
    9.5,
    53.8,
    4.3,
    57.4,
    11.4,
    63.2,
    63.6,
    74.6,
    55.4,
    83.2,
    92.7,
    83.0,
    75.4,
    77.5,
    11.5,
    10.1,
    27.6,
    13.8,
    26.9
   ],
   "tasks_en": [
    65.2,
    49.5,
    53.8,
    41.8,
    40.7,
    57.7,
    68.0,
    65.1,
    19.7,
    42.1,
    79.4,
    52.0,
    14.7,
    37.7,
    7.8,
    52.2,
    5.3,
    60.5,
    13.9,
    36.5,
    33.7,
    61.4,
    47.9,
    74.5,
    87.6,
    81.8,
    53.8,
    75.5,
    13.0,
    13.0,
    null,
    11.6,
    null
   ]
  },
  {
   "key": "CohereLabs__c4ai-command-a-03-2025",
   "name": "Command A",
   "open": true,
   "params": 111.0,
   "overall": 36.2,
   "groups": [
    64.9,
    32.4,
    38.4,
    12.4,
    26.4,
    42.8
   ],
   "tasks": [
    88.0,
    68.2,
    72.6,
    65.3,
    57.2,
    78.1,
    79.4,
    19.7,
    61.7,
    59.0,
    92.3,
    7.0,
    4.0,
    53.2,
    10.4,
    67.7,
    3.6,
    50.5,
    2.7,
    17.3,
    20.3,
    59.0,
    31.0,
    29.7,
    36.3,
    35.9,
    47.7,
    68.8,
    11.6,
    13.2,
    26.4,
    49.6,
    36.1
   ],
   "tasks_en": [
    81.7,
    57.7,
    64.2,
    60.4,
    42.6,
    76.1,
    74.5,
    24.9,
    59.7,
    54.1,
    92.0,
    0.1,
    8.3,
    47.3,
    5.0,
    60.4,
    3.9,
    72.5,
    8.4,
    50.5,
    38.4,
    64.4,
    6.1,
    7.8,
    26.5,
    12.5,
    17.8,
    30.0,
    10.2,
    10.9,
    null,
    43.8,
    null
   ]
  },
  {
   "key": "CohereLabs__tiny-aya-global",
   "name": "Tiny-Aya Global",
   "open": true,
   "params": 3.35,
   "overall": 36.0,
   "groups": [
    50.7,
    34.6,
    73.9,
    10.6,
    26.8,
    19.6
   ],
   "tasks": [
    64.9,
    49.0,
    54.2,
    46.2,
    40.9,
    58.5,
    67.8,
    63.7,
    20.3,
    41.4,
    78.4,
    50.6,
    12.4,
    37.0,
    8.8,
    53.2,
    4.9,
    54.9,
    11.6,
    61.5,
    61.2,
    74.7,
    55.6,
    83.4,
    91.7,
    83.4,
    77.3,
    76.0,
    11.4,
    9.9,
    26.8,
    11.5,
    27.7
   ],
   "tasks_en": [
    64.7,
    48.8,
    53.9,
    45.9,
    39.8,
    57.5,
    67.8,
    65.3,
    22.3,
    41.1,
    78.4,
    52.8,
    15.5,
    37.3,
    8.1,
    52.6,
    5.2,
    49.2,
    14.8,
    42.7,
    38.2,
    58.2,
    47.7,
    75.3,
    86.0,
    80.5,
    60.3,
    75.8,
    12.9,
    12.7,
    null,
    10.7,
    null
   ]
  },
  {
   "key": "meta-llama__Llama-3.1-8B-Instruct",
   "name": "Llama 3.1 8B",
   "open": true,
   "params": 8.0,
   "overall": 35.1,
   "groups": [
    47.8,
    41.4,
    60.9,
    15.3,
    19.6,
    25.8
   ],
   "tasks": [
    56.5,
    47.9,
    53.9,
    36.4,
    41.2,
    58.3,
    53.3,
    58.1,
    36.3,
    35.9,
    74.1,
    50.1,
    35.1,
    40.5,
    13.8,
    49.7,
    8.5,
    68.3,
    32.6,
    34.6,
    32.2,
    57.5,
    54.7,
    75.9,
    90.8,
    86.7,
    53.0,
    63.1,
    14.7,
    16.0,
    19.6,
    24.5,
    27.1
   ],
   "tasks_en": [
    55.5,
    47.7,
    55.1,
    32.5,
    40.7,
    55.6,
    52.7,
    56.8,
    39.7,
    31.3,
    75.7,
    42.0,
    38.0,
    37.6,
    9.6,
    49.5,
    8.4,
    77.9,
    23.8,
    20.7,
    18.2,
    51.1,
    32.6,
    49.1,
    77.2,
    61.1,
    63.9,
    62.9,
    14.7,
    15.7,
    null,
    8.1,
    null
   ]
  },
  {
   "key": "slovak-nlp__Qwen3-14B-sk",
   "name": "Qwen3-SK 14B",
   "open": true,
   "params": 14.0,
   "overall": 33.5,
   "groups": [
    43.4,
    23.9,
    43.7,
    11.6,
    27.7,
    50.8
   ],
   "tasks": [
    39.1,
    33.3,
    35.0,
    52.3,
    18.5,
    69.9,
    31.3,
    79.0,
    55.0,
    20.8,
    88.7,
    0.1,
    27.5,
    23.3,
    4.6,
    40.6,
    5.5,
    1.0,
    23.7,
    21.9,
    29.1,
    54.1,
    39.9,
    54.7,
    38.5,
    66.4,
    25.8,
    62.7,
    11.9,
    11.2,
    27.7,
    49.2,
    52.3
   ],
   "tasks_en": [
    85.4,
    64.3,
    68.2,
    72.2,
    55.2,
    73.6,
    86.2,
    69.3,
    53.7,
    52.5,
    71.9,
    61.7,
    40.1,
    61.6,
    23.4,
    64.5,
    12.7,
    32.4,
    24.1,
    56.1,
    51.1,
    27.8,
    26.5,
    49.1,
    65.2,
    63.2,
    64.7,
    74.6,
    12.4,
    10.9,
    null,
    48.8,
    null
   ]
  },
  {
   "key": "mrshu__tildeopen-30b-64k-sk-alpaca-slovak-it",
   "name": "TildeOpen-SK 30B (Alpaca)",
   "open": true,
   "params": 30.0,
   "overall": 32.8,
   "groups": [
    57.4,
    34.2,
    33.6,
    13.3,
    27.2,
    30.9
   ],
   "tasks": [
    72.6,
    50.8,
    59.1,
    43.5,
    44.2,
    58.5,
    76.7,
    71.3,
    49.0,
    48.7,
    77.4,
    24.8,
    6.9,
    43.6,
    19.4,
    64.1,
    9.5,
    43.5,
    18.5,
    38.4,
    35.4,
    63.4,
    8.3,
    10.5,
    3.7,
    20.7,
    48.7,
    73.4,
    13.4,
    13.2,
    27.2,
    20.1,
    41.7
   ],
   "tasks_en": [
    68.4,
    45.7,
    51.7,
    37.7,
    41.0,
    58.6,
    70.1,
    72.2,
    53.0,
    48.7,
    73.5,
    0.2,
    10.8,
    40.0,
    22.6,
    61.4,
    10.5,
    38.0,
    16.3,
    5.0,
    1.8,
    9.1,
    0.5,
    0.1,
    0.0,
    0.0,
    0.0,
    1.9,
    13.2,
    12.5,
    null,
    20.2,
    null
   ]
  },
  {
   "key": "TildeAI__TildeOpen-30b-64k",
   "name": "TildeOpen 30B-64k",
   "open": true,
   "params": 30.0,
   "overall": 31.9,
   "groups": [
    58.0,
    40.4,
    62.8,
    14.5,
    15.6,
    0.2
   ],
   "tasks": [
    69.4,
    51.4,
    59.9,
    42.4,
    41.3,
    60.6,
    81.0,
    58.5,
    62.7,
    52.9,
    74.3,
    52.4,
    41.7,
    41.8,
    43.5,
    64.0,
    22.1,
    0.0,
    23.7,
    46.5,
    42.8,
    66.4,
    60.6,
    70.4,
    89.1,
    59.2,
    60.8,
    69.1,
    13.2,
    15.8,
    15.6,
    0.5,
    0.0
   ],
   "tasks_en": [
    71.5,
    52.0,
    61.3,
    46.5,
    43.8,
    64.4,
    82.6,
    63.1,
    62.7,
    54.1,
    76.6,
    51.8,
    43.9,
    40.3,
    52.6,
    66.0,
    24.4,
    0.0,
    24.2,
    40.8,
    38.2,
    55.3,
    46.1,
    56.8,
    91.9,
    67.2,
    48.1,
    69.1,
    7.7,
    7.5,
    null,
    20.0,
    null
   ]
  },
  {
   "key": "Qwen__Qwen3.5-2B",
   "name": "Qwen3.5 2B",
   "open": true,
   "params": 2.0,
   "overall": 29.4,
   "groups": [
    43.4,
    34.2,
    56.9,
    11.2,
    18.8,
    12.2
   ],
   "tasks": [
    60.6,
    44.5,
    51.6,
    22.9,
    41.1,
    47.6,
    53.1,
    55.6,
    20.7,
    36.2,
    71.1,
    56.9,
    21.1,
    33.9,
    4.4,
    44.8,
    3.9,
    47.8,
    23.5,
    45.4,
    46.6,
    72.5,
    56.3,
    75.2,
    44.8,
    54.2,
    63.9,
    53.3,
    11.8,
    10.5,
    18.8,
    7.1,
    17.2
   ],
   "tasks_en": [
    60.3,
    44.5,
    52.8,
    29.3,
    41.8,
    45.3,
    59.5,
    53.1,
    11.3,
    34.7,
    73.5,
    56.5,
    17.5,
    35.8,
    4.1,
    46.8,
    5.5,
    38.9,
    25.6,
    40.0,
    37.1,
    79.1,
    48.4,
    63.5,
    71.2,
    68.0,
    65.0,
    72.5,
    13.5,
    16.2,
    null,
    2.5,
    null
   ]
  },
  {
   "key": "CohereLabs__aya-expanse-8b",
   "name": "Aya Expanse 8B",
   "open": true,
   "params": 8.0,
   "overall": 28.6,
   "groups": [
    44.5,
    25.8,
    59.0,
    12.3,
    15.1,
    14.8
   ],
   "tasks": [
    61.4,
    46.5,
    51.2,
    36.5,
    39.3,
    54.6,
    58.0,
    33.5,
    29.0,
    35.2,
    78.7,
    15.5,
    16.8,
    32.7,
    6.5,
    52.6,
    3.6,
    13.2,
    12.5,
    36.5,
    38.7,
    59.2,
    47.8,
    65.9,
    88.3,
    87.7,
    48.5,
    57.9,
    12.2,
    12.5,
    15.1,
    14.8,
    14.7
   ],
   "tasks_en": [
    62.0,
    48.0,
    51.5,
    38.5,
    40.7,
    53.1,
    58.3,
    72.3,
    28.0,
    34.3,
    80.6,
    24.0,
    42.7,
    33.6,
    8.8,
    52.1,
    3.9,
    49.3,
    24.6,
    47.4,
    55.2,
    75.4,
    42.0,
    60.6,
    82.1,
    76.9,
    79.9,
    77.5,
    12.5,
    13.7,
    null,
    10.9,
    null
   ]
  },
  {
   "key": "Qwen__Qwen3-1.7B",
   "name": "Qwen3 1.7B",
   "open": true,
   "params": 1.7,
   "overall": 27.8,
   "groups": [
    35.0,
    30.9,
    52.4,
    12.8,
    23.5,
    12.3
   ],
   "tasks": [
    40.2,
    31.1,
    36.1,
    37.7,
    19.6,
    40.0,
    62.0,
    51.1,
    14.0,
    18.2,
    52.5,
    50.4,
    15.2,
    22.8,
    2.7,
    34.8,
    2.4,
    80.2,
    17.2,
    14.9,
    15.7,
    47.0,
    55.3,
    70.6,
    71.5,
    70.6,
    61.3,
    65.0,
    12.7,
    13.0,
    23.5,
    6.9,
    17.8
   ],
   "tasks_en": [
    40.6,
    29.0,
    32.4,
    40.1,
    19.4,
    34.9,
    66.4,
    54.7,
    16.7,
    25.6,
    56.9,
    51.5,
    21.8,
    27.0,
    2.5,
    35.9,
    2.7,
    79.0,
    24.8,
    32.0,
    28.6,
    75.3,
    50.5,
    70.1,
    59.4,
    77.6,
    63.8,
    42.8,
    13.2,
    14.3,
    null,
    4.8,
    null
   ]
  },
  {
   "key": "openGPT-X__Teuken-7B-instruct-v0.6",
   "name": "Teuken 7B",
   "open": true,
   "params": 7.0,
   "overall": 27.7,
   "groups": [
    39.8,
    26.1,
    59.1,
    10.3,
    15.3,
    15.4
   ],
   "tasks": [
    49.9,
    34.9,
    39.7,
    32.6,
    23.4,
    54.4,
    66.0,
    57.5,
    6.7,
    33.5,
    66.6,
    53.8,
    4.2,
    26.9,
    4.3,
    39.7,
    4.2,
    17.9,
    16.8,
    22.4,
    20.3,
    60.2,
    59.7,
    79.8,
    90.2,
    80.6,
    46.7,
    71.9,
    10.6,
    10.0,
    15.3,
    9.6,
    21.1
   ],
   "tasks_en": [
    48.7,
    35.1,
    40.8,
    34.9,
    22.9,
    52.9,
    71.8,
    53.1,
    2.0,
    33.1,
    66.3,
    45.6,
    3.8,
    30.8,
    3.7,
    45.6,
    3.9,
    37.9,
    9.1,
    24.0,
    24.1,
    59.0,
    40.7,
    54.5,
    86.3,
    84.4,
    46.9,
    72.7,
    10.2,
    9.3,
    null,
    4.4,
    null
   ]
  },
  {
   "key": "ibm-granite__granite-4.0-h-1b",
   "name": "Granite 4.0-H 1B",
   "open": true,
   "params": 1.0,
   "overall": 25.6,
   "groups": [
    39.8,
    28.2,
    50.1,
    14.8,
    14.9,
    6.0
   ],
   "tasks": [
    49.1,
    40.6,
    44.8,
    18.6,
    35.4,
    42.3,
    43.1,
    51.1,
    41.3,
    31.6,
    54.6,
    49.8,
    6.1,
    32.1,
    1.3,
    40.9,
    2.7,
    49.4,
    17.1,
    27.1,
    24.7,
    63.5,
    38.4,
    55.5,
    90.3,
    70.4,
    40.7,
    40.0,
    13.3,
    16.3,
    14.9,
    3.4,
    8.6
   ],
   "tasks_en": [
    49.5,
    40.7,
    43.0,
    21.0,
    34.8,
    42.1,
    46.2,
    56.9,
    40.0,
    29.2,
    58.1,
    51.9,
    19.0,
    30.5,
    1.0,
    40.9,
    2.0,
    56.3,
    20.0,
    48.1,
    43.4,
    72.0,
    45.6,
    52.1,
    94.2,
    81.7,
    53.7,
    72.7,
    13.3,
    16.9,
    null,
    5.2,
    null
   ]
  },
  {
   "key": "meta-llama__Llama-3.2-3B-Instruct",
   "name": "Llama 3.2 3B",
   "open": true,
   "params": 3.0,
   "overall": 24.6,
   "groups": [
    34.7,
    25.8,
    46.2,
    14.8,
    14.0,
    12.5
   ],
   "tasks": [
    40.1,
    38.1,
    43.2,
    11.0,
    33.9,
    45.6,
    37.9,
    49.1,
    15.7,
    32.9,
    52.4,
    18.3,
    23.6,
    29.5,
    9.3,
    40.5,
    3.2,
    34.1,
    21.2,
    23.2,
    23.0,
    49.7,
    64.7,
    85.7,
    46.1,
    69.3,
    32.1,
    21.7,
    13.9,
    15.6,
    14.0,
    12.0,
    12.9
   ],
   "tasks_en": [
    38.2,
    37.0,
    44.2,
    9.5,
    33.5,
    43.5,
    29.4,
    53.8,
    32.0,
    34.3,
    53.7,
    52.1,
    29.7,
    28.0,
    6.1,
    39.5,
    3.1,
    32.4,
    16.2,
    28.5,
    29.1,
    55.4,
    45.5,
    67.8,
    49.6,
    55.5,
    47.6,
    65.5,
    14.0,
    15.5,
    null,
    6.0,
    null
   ]
  },
  {
   "key": "ibm-granite__granite-3.2-2b-instruct",
   "name": "Granite 3.2 2B",
   "open": true,
   "params": 2.0,
   "overall": 24.4,
   "groups": [
    38.2,
    22.5,
    51.7,
    8.7,
    13.8,
    11.6
   ],
   "tasks": [
    41.1,
    38.2,
    39.7,
    14.4,
    30.1,
    47.5,
    49.4,
    55.7,
    38.3,
    28.0,
    55.1,
    24.2,
    3.9,
    29.1,
    1.4,
    39.7,
    1.5,
    33.2,
    14.1,
    11.0,
    11.8,
    44.7,
    57.6,
    76.4,
    93.3,
    85.1,
    41.4,
    44.1,
    9.5,
    7.8,
    13.8,
    9.5,
    13.7
   ],
   "tasks_en": [
    40.8,
    37.6,
    39.8,
    18.9,
    30.1,
    46.7,
    45.6,
    57.4,
    41.7,
    27.8,
    59.5,
    51.5,
    16.8,
    29.8,
    2.6,
    38.8,
    2.1,
    46.6,
    23.2,
    62.7,
    65.6,
    76.6,
    53.6,
    81.9,
    87.6,
    84.9,
    65.3,
    74.5,
    10.0,
    8.4,
    null,
    9.0,
    null
   ]
  },
  {
   "key": "Qwen__Qwen3.5-0.8B",
   "name": "Qwen3.5 0.8B",
   "open": true,
   "params": 0.8,
   "overall": 24.0,
   "groups": [
    33.4,
    26.0,
    53.5,
    9.7,
    14.3,
    7.0
   ],
   "tasks": [
    41.1,
    33.1,
    35.8,
    28.5,
    28.7,
    34.5,
    54.7,
    50.1,
    2.7,
    24.6,
    47.1,
    43.9,
    14.9,
    25.4,
    0.9,
    36.8,
    1.3,
    50.5,
    13.4,
    24.7,
    22.8,
    56.7,
    67.5,
    85.2,
    57.6,
    69.0,
    57.7,
    40.2,
    10.9,
    8.5,
    14.3,
    7.3,
    6.7
   ],
   "tasks_en": [
    40.5,
    32.8,
    37.8,
    48.9,
    27.6,
    37.1,
    60.5,
    50.6,
    0.0,
    26.1,
    53.5,
    51.4,
    19.5,
    25.8,
    1.0,
    37.6,
    1.7,
    37.3,
    15.0,
    31.6,
    28.7,
    60.0,
    64.8,
    85.8,
    57.2,
    67.2,
    64.4,
    67.6,
    12.4,
    11.9,
    null,
    1.1,
    null
   ]
  },
  {
   "key": "ibm-granite__granite-4.0-1b",
   "name": "Granite 4.0 1B",
   "open": true,
   "params": 1.0,
   "overall": 23.2,
   "groups": [
    34.5,
    27.6,
    41.8,
    13.2,
    17.1,
    5.2
   ],
   "tasks": [
    41.5,
    38.2,
    39.4,
    19.2,
    35.2,
    36.1,
    47.3,
    51.8,
    2.3,
    33.6,
    61.4,
    51.0,
    8.5,
    28.5,
    1.6,
    40.2,
    2.1,
    41.2,
    13.9,
    34.2,
    34.9,
    60.8,
    30.8,
    59.2,
    30.9,
    47.9,
    27.4,
    50.6,
    11.9,
    14.5,
    17.1,
    4.0,
    6.5
   ],
   "tasks_en": [
    40.9,
    36.5,
    39.3,
    14.2,
    32.6,
    38.6,
    33.4,
    52.7,
    10.3,
    35.1,
    62.3,
    52.0,
    16.9,
    27.3,
    1.4,
    39.1,
    2.0,
    65.2,
    20.3,
    47.6,
    45.3,
    72.9,
    38.6,
    73.8,
    75.8,
    78.5,
    51.1,
    72.7,
    12.2,
    14.1,
    null,
    5.6,
    null
   ]
  },
  {
   "key": "google__gemma-3-1b-it",
   "name": "Gemma 3 1B",
   "open": true,
   "params": 1.0,
   "overall": 22.7,
   "groups": [
    35.1,
    19.9,
    54.4,
    11.8,
    12.3,
    3.0
   ],
   "tasks": [
    27.3,
    28.4,
    32.8,
    52.8,
    23.5,
    35.0,
    70.0,
    51.8,
    2.7,
    26.9,
    34.0,
    34.7,
    13.7,
    21.7,
    2.6,
    35.9,
    2.1,
    13.9,
    20.1,
    22.2,
    24.2,
    51.7,
    65.2,
    81.5,
    82.0,
    73.1,
    56.1,
    33.3,
    12.0,
    11.7,
    12.3,
    2.0,
    4.0
   ],
   "tasks_en": [
    32.0,
    31.3,
    36.9,
    39.8,
    26.7,
    35.6,
    65.8,
    51.5,
    1.7,
    28.6,
    37.1,
    52.0,
    14.5,
    24.1,
    1.7,
    35.9,
    2.2,
    20.1,
    15.2,
    44.4,
    43.3,
    65.3,
    66.7,
    87.2,
    60.1,
    72.5,
    63.6,
    46.8,
    10.1,
    10.2,
    null,
    1.3,
    null
   ]
  },
  {
   "key": "utter-project__EuroLLM-1.7B-Instruct",
   "name": "EuroLLM 1.7B",
   "open": true,
   "params": 1.7,
   "overall": 21.9,
   "groups": [
    35.2,
    19.2,
    40.3,
    13.4,
    14.7,
    8.4
   ],
   "tasks": [
    25.9,
    24.3,
    24.4,
    45.6,
    22.4,
    18.8,
    57.1,
    50.9,
    57.3,
    24.8,
    27.9,
    50.0,
    17.3,
    19.0,
    5.5,
    27.5,
    3.8,
    5.6,
    16.2,
    14.7,
    17.8,
    50.2,
    19.3,
    24.4,
    74.8,
    51.1,
    46.5,
    63.9,
    13.1,
    13.8,
    14.7,
    6.9,
    9.9
   ],
   "tasks_en": [
    27.3,
    25.4,
    29.2,
    16.0,
    27.1,
    20.9,
    29.8,
    49.8,
    64.7,
    25.3,
    29.3,
    50.0,
    15.5,
    21.1,
    3.1,
    26.2,
    3.8,
    12.6,
    14.2,
    28.6,
    29.5,
    49.2,
    66.2,
    88.0,
    43.6,
    64.7,
    44.2,
    67.5,
    8.4,
    7.0,
    null,
    3.9,
    null
   ]
  },
  {
   "key": "Qwen__Qwen3-0.6B",
   "name": "Qwen3 0.6B",
   "open": true,
   "params": 0.6,
   "overall": 21.5,
   "groups": [
    33.1,
    20.9,
    43.3,
    10.6,
    16.8,
    4.2
   ],
   "tasks": [
    25.9,
    25.9,
    26.2,
    65.3,
    21.4,
    31.0,
    61.1,
    49.4,
    3.3,
    21.1,
    34.2,
    26.8,
    1.2,
    20.9,
    0.5,
    29.0,
    1.5,
    56.0,
    17.6,
    23.4,
    21.2,
    36.1,
    28.3,
    75.8,
    33.8,
    58.6,
    56.3,
    56.6,
    11.6,
    9.7,
    16.8,
    2.6,
    5.9
   ],
   "tasks_en": [
    29.9,
    29.5,
    29.0,
    30.2,
    23.8,
    32.6,
    65.5,
    48.5,
    7.7,
    24.1,
    39.6,
    50.7,
    8.1,
    24.7,
    0.3,
    30.5,
    1.1,
    52.3,
    18.6,
    32.3,
    29.6,
    52.5,
    65.9,
    66.8,
    46.2,
    55.7,
    53.3,
    28.0,
    12.4,
    12.5,
    null,
    2.0,
    null
   ]
  },
  {
   "key": "mistralai__Ministral-3-14B-Reasoning-2512",
   "name": "Ministral 3 14B (R)",
   "open": true,
   "params": 14.0,
   "overall": 20.4,
   "groups": [
    29.8,
    16.2,
    16.8,
    0.2,
    34.3,
    25.2
   ],
   "tasks": [
    48.0,
    28.9,
    33.4,
    25.0,
    22.6,
    12.6,
    39.3,
    35.3,
    24.7,
    28.2,
    52.5,
    11.7,
    0.4,
    35.3,
    3.2,
    40.0,
    0.6,
    0.0,
    2.4,
    15.4,
    14.6,
    26.2,
    11.6,
    15.0,
    17.8,
    8.2,
    28.8,
    13.6,
    0.2,
    0.2,
    34.3,
    11.3,
    39.2
   ],
   "tasks_en": [
    57.2,
    39.0,
    43.3,
    9.6,
    31.5,
    42.2,
    20.6,
    52.8,
    37.7,
    26.9,
    43.7,
    22.1,
    3.2,
    30.8,
    8.4,
    35.7,
    2.0,
    0.6,
    5.3,
    42.0,
    41.9,
    66.8,
    16.5,
    10.4,
    22.1,
    20.3,
    57.1,
    63.3,
    0.9,
    0.5,
    null,
    21.5,
    null
   ]
  },
  {
   "key": "slovak-nlp__mistral-sk-7b",
   "name": "Mistral-SK 7B",
   "open": true,
   "params": 7.0,
   "overall": 19.0,
   "groups": [
    22.6,
    19.3,
    34.6,
    16.2,
    14.2,
    6.9
   ],
   "tasks": [
    23.8,
    22.9,
    26.6,
    25.3,
    20.6,
    24.0,
    31.1,
    34.6,
    3.0,
    14.4,
    32.1,
    43.3,
    19.7,
    17.2,
    17.1,
    24.8,
    3.8,
    0.0,
    15.7,
    22.6,
    20.4,
    46.2,
    25.0,
    23.4,
    50.8,
    35.1,
    50.7,
    37.5,
    13.5,
    18.8,
    14.2,
    13.8,
    0.0
   ],
   "tasks_en": [
    21.3,
    18.7,
    20.0,
    9.3,
    16.2,
    21.1,
    40.8,
    25.9,
    1.7,
    13.1,
    22.9,
    27.0,
    17.7,
    12.8,
    13.0,
    20.3,
    4.3,
    0.0,
    16.4,
    7.4,
    5.9,
    14.8,
    17.8,
    28.5,
    10.1,
    36.8,
    26.1,
    9.4,
    8.5,
    10.6,
    null,
    4.0,
    null
   ]
  },
  {
   "key": "TildeAI__TildeOpen-30b",
   "name": "TildeOpen 30B",
   "open": true,
   "params": 30.0,
   "overall": 17.0,
   "groups": [
    45.1,
    21.5,
    8.8,
    3.4,
    16.8,
    6.3
   ],
   "tasks": [
    57.7,
    42.1,
    47.5,
    45.2,
    27.4,
    46.5,
    74.4,
    32.1,
    51.3,
    26.4,
    66.0,
    17.4,
    10.1,
    32.6,
    9.6,
    51.3,
    2.4,
    0.0,
    4.4,
    6.6,
    1.7,
    13.3,
    1.4,
    0.2,
    0.2,
    1.1,
    39.7,
    14.7,
    4.2,
    2.6,
    16.8,
    12.6,
    0.0
   ],
   "tasks_en": [
    65.2,
    46.7,
    54.9,
    47.9,
    41.2,
    53.0,
    75.1,
    46.8,
    18.0,
    43.4,
    68.4,
    0.0,
    17.3,
    36.5,
    25.5,
    56.4,
    8.5,
    0.0,
    10.3,
    16.2,
    17.1,
    28.9,
    28.6,
    31.1,
    30.9,
    27.3,
    49.0,
    45.2,
    1.2,
    0.8,
    null,
    11.1,
    null
   ]
  },
  {
   "key": "ibm-granite__granite-4.0-h-350m",
   "name": "Granite 4.0-H 350M",
   "open": true,
   "params": 0.35,
   "overall": 15.1,
   "groups": [
    25.5,
    9.4,
    27.3,
    11.7,
    15.3,
    1.3
   ],
   "tasks": [
    24.1,
    26.6,
    25.6,
    13.8,
    21.8,
    22.3,
    32.2,
    50.5,
    15.3,
    22.4,
    26.7,
    2.7,
    1.7,
    20.0,
    0.2,
    26.9,
    0.8,
    0.5,
    4.9,
    4.0,
    3.9,
    14.9,
    43.3,
    67.4,
    10.3,
    52.5,
    41.2,
    8.2,
    10.8,
    12.6,
    15.3,
    0.0,
    2.6
   ],
   "tasks_en": [
    25.5,
    27.8,
    25.9,
    7.6,
    24.3,
    25.3,
    25.7,
    50.7,
    48.3,
    22.9,
    28.7,
    50.2,
    6.3,
    22.4,
    0.6,
    20.2,
    0.8,
    24.7,
    14.3,
    25.2,
    23.7,
    44.5,
    62.5,
    87.4,
    30.4,
    65.4,
    47.3,
    67.0,
    11.1,
    15.1,
    null,
    0.3,
    null
   ]
  },
  {
   "key": "mrshu__mistral-sk-7b-alpaca-slovak-it",
   "name": "Mistral-SK 7B (Alpaca)",
   "open": true,
   "params": 7.0,
   "overall": 14.9,
   "groups": [
    21.5,
    12.6,
    17.7,
    12.0,
    13.8,
    11.8
   ],
   "tasks": [
    14.3,
    12.3,
    16.2,
    30.2,
    10.8,
    15.6,
    46.9,
    57.3,
    4.7,
    7.0,
    22.7,
    5.5,
    13.3,
    11.0,
    0.7,
    17.0,
    2.0,
    35.6,
    5.8,
    18.8,
    20.2,
    30.0,
    11.1,
    15.2,
    12.2,
    22.6,
    8.5,
    21.3,
    12.8,
    11.1,
    13.8,
    13.8,
    9.8
   ],
   "tasks_en": [
    18.9,
    13.6,
    18.2,
    32.6,
    10.7,
    12.4,
    54.1,
    47.0,
    4.7,
    5.8,
    26.5,
    0.4,
    14.2,
    10.3,
    0.6,
    19.2,
    1.8,
    40.5,
    5.8,
    0.4,
    0.7,
    0.0,
    0.2,
    0.2,
    0.0,
    0.3,
    0.3,
    0.1,
    12.7,
    10.9,
    null,
    4.9,
    null
   ]
  },
  {
   "key": "ibm-granite__granite-4.0-350m",
   "name": "Granite 4.0 350M",
   "open": true,
   "params": 0.35,
   "overall": 12.3,
   "groups": [
    27.5,
    10.1,
    13.8,
    9.7,
    10.8,
    1.8
   ],
   "tasks": [
    26.5,
    27.7,
    26.7,
    21.9,
    25.9,
    25.9,
    33.2,
    48.7,
    12.7,
    26.1,
    30.0,
    0.9,
    3.6,
    19.4,
    0.2,
    25.4,
    1.3,
    7.2,
    3.0,
    7.3,
    7.1,
    5.2,
    28.5,
    22.0,
    23.8,
    25.6,
    3.1,
    1.4,
    9.8,
    9.6,
    10.8,
    0.3,
    3.2
   ],
   "tasks_en": [
    26.3,
    27.0,
    25.4,
    7.5,
    27.7,
    24.7,
    19.0,
    50.3,
    0.0,
    26.5,
    32.0,
    50.3,
    6.4,
    20.6,
    0.6,
    28.1,
    1.3,
    16.8,
    8.5,
    34.4,
    31.2,
    53.8,
    46.6,
    74.8,
    59.9,
    70.8,
    46.7,
    72.7,
    8.2,
    9.0,
    null,
    0.9,
    null
   ]
  }
 ]
}