data/benchmarks.json

[
  {
    "benchmark": "ace",
    "model_count": 12
  },
  {
    "benchmark": "apex-agents",
    "model_count": 20
  },
  {
    "benchmark": "apex-v1",
    "model_count": 10
  },
  {
    "benchmark": "appworld_test_normal",
    "model_count": 3
  },
  {
    "benchmark": "bfcl",
    "model_count": 109
  },
  {
    "benchmark": "browsecompplus",
    "model_count": 3
  },
  {
    "benchmark": "global-mmlu-lite",
    "model_count": 27
  },
  {
    "benchmark": "helm_capabilities",
    "model_count": 61
  },
  {
    "benchmark": "helm_classic",
    "model_count": 67
  },
  {
    "benchmark": "helm_instruct",
    "model_count": 4
  },
  {
    "benchmark": "helm_lite",
    "model_count": 91
  },
  {
    "benchmark": "helm_mmlu",
    "model_count": 79
  },
  {
    "benchmark": "hfopenllm_v2",
    "model_count": 4493
  },
  {
    "benchmark": "la_leaderboard",
    "model_count": 5
  },
  {
    "benchmark": "livecodebenchpro",
    "model_count": 27
  },
  {
    "benchmark": "reward-bench",
    "model_count": 328
  },
  {
    "benchmark": "swe-bench",
    "model_count": 3
  },
  {
    "benchmark": "tau-bench-2_airline",
    "model_count": 3
  },
  {
    "benchmark": "tau-bench-2_retail",
    "model_count": 3
  },
  {
    "benchmark": "tau-bench-2_telecom",
    "model_count": 3
  },
  {
    "benchmark": "terminal-bench-2.0",
    "model_count": 37
  },
  {
    "benchmark": "theory_of_mind",
    "model_count": 1
  }
]