leaderboard/template_jsons/mt_bench.json

{
  "score_w_mean": null,
  "score_mean": null,
  "writing_score_w_mean": null,
  "writing_score_mean": null,
  "roleplay_score_w_mean": null,
  "roleplay_score_mean": null,
  "reasoning_score_w_mean": null,
  "reasoning_score_mean": null,
  "math_score_w_mean": null,
  "math_score_mean": null,
  "coding_score_w_mean": null,
  "coding_score_mean": null,
  "extraction_score_w_mean": null,
  "extraction_score_mean": null,
  "stem_score_w_mean": null,
  "stem_score_mean": null,
  "humanities_score_w_mean": null,
  "humanities_score_mean": null,
  "persian_general_knowledge_score_w_mean": null,
  "persian_general_knowledge_score_mean": null,
  "chatbot_rag_score_w_mean": null,
  "chatbot_rag_score_mean": null
}