data/developers/alephalpha.json

{
  "developer": "AlephAlpha",
  "models": [
    {
      "id": "AlephAlpha/luminous-base",
      "name": "Luminous Base 13B",
      "developer": "AlephAlpha",
      "evaluator_relationship": null,
      "benchmark_scores": {
        "helm_lite/Mean win rate": 0.041,
        "helm_lite/NarrativeQA": 0.633,
        "helm_lite/NaturalQuestions (closed-book)": 0.197,
        "helm_lite/OpenbookQA": 0.286,
        "helm_lite/MMLU": 0.243,
        "helm_lite/MATH": 0.026,
        "helm_lite/GSM8K": 0.028,
        "helm_lite/LegalBench": 0.332,
        "helm_lite/MedQA": 0.26,
        "helm_lite/WMT 2014": 0.066
      }
    },
    {
      "id": "AlephAlpha/luminous-extended",
      "name": "Luminous Extended 30B",
      "developer": "AlephAlpha",
      "evaluator_relationship": null,
      "benchmark_scores": {
        "helm_lite/Mean win rate": 0.078,
        "helm_lite/NarrativeQA": 0.684,
        "helm_lite/NaturalQuestions (closed-book)": 0.253,
        "helm_lite/OpenbookQA": 0.272,
        "helm_lite/MMLU": 0.248,
        "helm_lite/MATH": 0.04,
        "helm_lite/GSM8K": 0.075,
        "helm_lite/LegalBench": 0.421,
        "helm_lite/MedQA": 0.276,
        "helm_lite/WMT 2014": 0.083
      }
    },
    {
      "id": "AlephAlpha/luminous-supreme",
      "name": "Luminous Supreme 70B",
      "developer": "AlephAlpha",
      "evaluator_relationship": null,
      "benchmark_scores": {
        "helm_lite/Mean win rate": 0.145,
        "helm_lite/NarrativeQA": 0.743,
        "helm_lite/NaturalQuestions (closed-book)": 0.299,
        "helm_lite/OpenbookQA": 0.284,
        "helm_lite/MMLU": 0.316,
        "helm_lite/MATH": 0.078,
        "helm_lite/GSM8K": 0.137,
        "helm_lite/LegalBench": 0.452,
        "helm_lite/MedQA": 0.276,
        "helm_lite/WMT 2014": 0.102
      }
    }
  ]
}