Spaces:

---

AxiomicLabs

/

Open_SLM_Leaderboard

Like 153

Running

{
  "model": {
    "repo": "specklabs/Speck1-140M-Instruct",
    "revision": "686350e82db5996f9ab65bdadca70c6d41d49227",
    "parameters": 140654208
  },
  "leaderboard": {
    "repo": "AxiomicLabs/Open_SLM_Leaderboard",
    "revision": "2eafcfc647b667e67f3b0288e9b67da497a78052"
  },
  "scores_percent": {
    "hellaswag": 35.22,
    "arc_easy": 45.66,
    "arc_challenge": 25.85,
    "piqa": 63.6,
    "arithmark_2": 33.64,
    "arithmark_3": 36.1,
    "combined_arc": 35.75,
    "average": 42.67,
    "intelligence_index": 17.75
  },
  "samples": {
    "hellaswag": 10042,
    "arc_easy": 2376,
    "arc_challenge": 1172,
    "piqa": 1838,
    "arithmark_2": 2500,
    "arithmark_3": 1000
  },
  "metrics": {
    "hellaswag": "acc_norm",
    "arc_easy": "acc_norm",
    "arc_challenge": "acc_norm",
    "piqa": "acc_norm",
    "arithmark_2": "acc",
    "arithmark_3": "acc_norm"
  },
  "evaluation": {
    "zero_shot": true,
    "lm_eval_revision": "64f3d0924fc695efd6d776a5ac91f97138085516",
    "lm_eval_version": "0.4.13.dev0",
    "transformers_version": "5.1.0",
    "dataset_revisions": {
      "Rowan/hellaswag": "218ec52e09a7e7462a5400043bb9a69a41d06b76",
      "allenai/ai2_arc": "210d026faf9955653af8916fad021475a3f00453",
      "baber/piqa": "142f6d7367fd9877f0fb3b5734ea6a545f54cdd1"
    },
    "arithmark_2_revision": "5bd986c7305dcccec88432d630aae1ac9280a71f",
    "arithmark_3_revision": "6f6e59dd9b7e2c63455f7af7f838f9ecc3d0a746"
  },
  "artifacts": {
    "lm_eval_sha256": "a5f0e6b8cb31d5474aa55b1310a2c268d5916275b6bad574335bfafb71e083cd",
    "arithmark_2_sha256": "2afffe80da4f9fba0e6ca4e164ebeb4603ceb6e176b55624775de04b20df9531",
    "arithmark_3_sha256": "fc155b40e4186180d62921d547a2b3fbece8f701e33f932e1f329ce0d070446c"
  }
}