Submitting LFM2.5 models results.

models.json

@@ -61,6 +61,1066 @@
   ],
   "models": [
     {
+  "id": "liquidai-lfm2.5-1.2b-base",
+  "name": "LiquidAI/LFM2.5-1.2B-Base",
+  "org": "LiquidAI",
+  "params_b": null,
+  "license": null,
+  "architecture": null,
+  "url": "https://huggingface.co/LiquidAI/LFM2.5-1.2B-Base",
+  "model_revision": "f6a5d174bc3e52bd0df245d69133f9930b4828d8",
+  "script_sha256": "0c557dde5397ded8568280d621300759b4387a9f12227817c619a9325be8806a",
+  "runs": {
+    "bench-effortless-6-2026": {
+      "score": 0.0,
+      "n": 240,
+      "notes": "Exact-match, normalized.",
+      "categories": {
+        "Commonsense-reasoning": {
+          "n": 37,
+          "exact_match": 0.0
+        },
+        "Knowledge-basic": {
+          "n": 42,
+          "exact_match": 0.0
+        },
+        "Language-comprehension": {
+          "n": 42,
+          "exact_match": 0.0
+        },
+        "Logic-deduction": {
+          "n": 42,
+          "exact_match": 0.0
+        },
+        "Math-arithmetic": {
+          "n": 40,
+          "exact_match": 0.0
+        },
+        "Pattern-recognition": {
+          "n": 37,
+          "exact_match": 0.0
+        }
+      }
+    },
+    "bench-easy-6-2026": {
+      "score": 0.3087,
+      "n": 238,
+      "notes": "Hybrid category-aware scoring (strict / flexible / semantic).",
+      "categories": {
+        "Commonsense-causality": {
+          "n": 10,
+          "hybrid_score": 0.7338
+        },
+        "Commonsense-reasoning": {
+          "n": 10,
+          "hybrid_score": 0.7347
+        },
+        "Commonsense-simulation": {
+          "n": 10,
+          "hybrid_score": 0.742
+        },
+        "Knowledge-basic": {
+          "n": 33,
+          "hybrid_score": 0.0303
+        },
+        "Knowledge-definitions": {
+          "n": 38,
+          "hybrid_score": 0.8057
+        },
+        "Language-comprehension": {
+          "n": 10,
+          "hybrid_score": 0.7448
+        },
+        "Language-structure": {
+          "n": 10,
+          "hybrid_score": 0.2311
+        },
+        "Language-transformation": {
+          "n": 10,
+          "hybrid_score": 0.7685
+        },
+        "Logic-consistency": {
+          "n": 10,
+          "hybrid_score": 0.0
+        },
+        "Logic-deduction": {
+          "n": 15,
+          "hybrid_score": 0.0667
+        },
+        "Logic-pattern": {
+          "n": 10,
+          "hybrid_score": 0.0
+        },
+        "Math-arithmetic": {
+          "n": 33,
+          "hybrid_score": 0.0
+        },
+        "Math-pattern": {
+          "n": 14,
+          "hybrid_score": 0.0
+        },
+        "Math-reasoning": {
+          "n": 15,
+          "hybrid_score": 0.0868
+        },
+        "Pattern-matching": {
+          "n": 10,
+          "hybrid_score": 0.0
+        }
+      }
+    },
+    "bench-mid-6-2026": {
+      "score": 0.621,
+      "n": 143,
+      "acc": 0.5385,
+      "acc_norm": 0.6154,
+      "soft_score": 0.5455,
+      "soft_score_norm": 0.621,
+      "stderr": 0.0404,
+      "categories": {
+        "Commonsense-causality": {
+          "n": 5,
+          "acc": 0.6,
+          "acc_norm": 0.6
+        },
+        "Commonsense-reasoning": {
+          "n": 10,
+          "acc": 0.6,
+          "acc_norm": 0.5
+        },
+        "Commonsense-simulation": {
+          "n": 10,
+          "acc": 0.4,
+          "acc_norm": 0.7
+        },
+        "Knowledge-basic": {
+          "n": 7,
+          "acc": 0.5714,
+          "acc_norm": 0.5714
+        },
+        "Knowledge-definitions": {
+          "n": 10,
+          "acc": 0.3,
+          "acc_norm": 0.9
+        },
+        "Language-comprehension": {
+          "n": 10,
+          "acc": 0.6,
+          "acc_norm": 0.7
+        },
+        "Language-structure": {
+          "n": 10,
+          "acc": 0.5,
+          "acc_norm": 0.4
+        },
+        "Language-transformation": {
+          "n": 10,
+          "acc": 0.5,
+          "acc_norm": 0.7
+        },
+        "Logic-consistency": {
+          "n": 5,
+          "acc": 0.0,
+          "acc_norm": 0.0
+        },
+        "Logic-deduction": {
+          "n": 10,
+          "acc": 0.3,
+          "acc_norm": 0.3
+        },
+        "Logic-pattern": {
+          "n": 10,
+          "acc": 0.5,
+          "acc_norm": 0.6
+        },
+        "Math-arithmetic": {
+          "n": 8,
+          "acc": 0.875,
+          "acc_norm": 0.875
+        },
+        "Math-pattern": {
+          "n": 7,
+          "acc": 0.8571,
+          "acc_norm": 0.8571
+        },
+        "Math-reasoning": {
+          "n": 10,
+          "acc": 0.4,
+          "acc_norm": 0.3
+        },
+        "Pattern-generation": {
+          "n": 4,
+          "acc": 1.0,
+          "acc_norm": 1.0
+        },
+        "Pattern-matching": {
+          "n": 8,
+          "acc": 1.0,
+          "acc_norm": 0.875
+        },
+        "Pattern-recognition": {
+          "n": 9,
+          "acc": 0.4444,
+          "acc_norm": 0.6667
+        }
+      }
+    },
+    "bench-AGI": {
+      "score": null,
+      "n": null,
+      "notes": "Not yet evaluated on this tier."
+    }
+  }
+},
+    {
+  "id": "liquidai-lfm2.5-1.2b-instruct",
+  "name": "LiquidAI/LFM2.5-1.2B-Instruct",
+  "org": "LiquidAI",
+  "params_b": null,
+  "license": null,
+  "architecture": null,
+  "url": "https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct",
+  "model_revision": "868df74dd56ff8a0c2ac5dbf281690c2dbebe4c9",
+  "script_sha256": "0c557dde5397ded8568280d621300759b4387a9f12227817c619a9325be8806a",
+  "runs": {
+    "bench-effortless-6-2026": {
+      "score": 0.1208,
+      "n": 240,
+      "notes": "Exact-match, normalized.",
+      "categories": {
+        "Commonsense-reasoning": {
+          "n": 37,
+          "exact_match": 0.0
+        },
+        "Knowledge-basic": {
+          "n": 42,
+          "exact_match": 0.119
+        },
+        "Language-comprehension": {
+          "n": 42,
+          "exact_match": 0.0
+        },
+        "Logic-deduction": {
+          "n": 42,
+          "exact_match": 0.0952
+        },
+        "Math-arithmetic": {
+          "n": 40,
+          "exact_match": 0.475
+        },
+        "Pattern-recognition": {
+          "n": 37,
+          "exact_match": 0.027
+        }
+      }
+    },
+    "bench-easy-6-2026": {
+      "score": 0.441,
+      "n": 238,
+      "notes": "Hybrid category-aware scoring (strict / flexible / semantic).",
+      "categories": {
+        "Commonsense-causality": {
+          "n": 10,
+          "hybrid_score": 0.7508
+        },
+        "Commonsense-reasoning": {
+          "n": 10,
+          "hybrid_score": 0.7711
+        },
+        "Commonsense-simulation": {
+          "n": 10,
+          "hybrid_score": 0.7765
+        },
+        "Knowledge-basic": {
+          "n": 33,
+          "hybrid_score": 0.303
+        },
+        "Knowledge-definitions": {
+          "n": 38,
+          "hybrid_score": 0.8172
+        },
+        "Language-comprehension": {
+          "n": 10,
+          "hybrid_score": 0.7459
+        },
+        "Language-structure": {
+          "n": 10,
+          "hybrid_score": 0.4632
+        },
+        "Language-transformation": {
+          "n": 10,
+          "hybrid_score": 0.7849
+        },
+        "Logic-consistency": {
+          "n": 10,
+          "hybrid_score": 0.0
+        },
+        "Logic-deduction": {
+          "n": 15,
+          "hybrid_score": 0.0667
+        },
+        "Logic-pattern": {
+          "n": 10,
+          "hybrid_score": 0.2
+        },
+        "Math-arithmetic": {
+          "n": 33,
+          "hybrid_score": 0.2727
+        },
+        "Math-pattern": {
+          "n": 14,
+          "hybrid_score": 0.0
+        },
+        "Math-reasoning": {
+          "n": 15,
+          "hybrid_score": 0.4654
+        },
+        "Pattern-matching": {
+          "n": 10,
+          "hybrid_score": 0.2
+        }
+      }
+    },
+    "bench-mid-6-2026": {
+      "score": 0.607,
+      "n": 143,
+      "acc": 0.5175,
+      "acc_norm": 0.6014,
+      "soft_score": 0.5231,
+      "soft_score_norm": 0.607,
+      "stderr": 0.0406,
+      "categories": {
+        "Commonsense-causality": {
+          "n": 5,
+          "acc": 0.8,
+          "acc_norm": 0.8
+        },
+        "Commonsense-reasoning": {
+          "n": 10,
+          "acc": 0.6,
+          "acc_norm": 0.5
+        },
+        "Commonsense-simulation": {
+          "n": 10,
+          "acc": 0.3,
+          "acc_norm": 0.6
+        },
+        "Knowledge-basic": {
+          "n": 7,
+          "acc": 1.0,
+          "acc_norm": 1.0
+        },
+        "Knowledge-definitions": {
+          "n": 10,
+          "acc": 0.4,
+          "acc_norm": 0.9
+        },
+        "Language-comprehension": {
+          "n": 10,
+          "acc": 0.6,
+          "acc_norm": 0.6
+        },
+        "Language-structure": {
+          "n": 10,
+          "acc": 0.2,
+          "acc_norm": 0.3
+        },
+        "Language-transformation": {
+          "n": 10,
+          "acc": 0.6,
+          "acc_norm": 0.6
+        },
+        "Logic-consistency": {
+          "n": 5,
+          "acc": 0.0,
+          "acc_norm": 0.2
+        },
+        "Logic-deduction": {
+          "n": 10,
+          "acc": 0.0,
+          "acc_norm": 0.3
+        },
+        "Logic-pattern": {
+          "n": 10,
+          "acc": 0.4,
+          "acc_norm": 0.3
+        },
+        "Math-arithmetic": {
+          "n": 8,
+          "acc": 1.0,
+          "acc_norm": 1.0
+        },
+        "Math-pattern": {
+          "n": 7,
+          "acc": 1.0,
+          "acc_norm": 1.0
+        },
+        "Math-reasoning": {
+          "n": 10,
+          "acc": 0.3,
+          "acc_norm": 0.3
+        },
+        "Pattern-generation": {
+          "n": 4,
+          "acc": 0.75,
+          "acc_norm": 0.75
+        },
+        "Pattern-matching": {
+          "n": 8,
+          "acc": 0.75,
+          "acc_norm": 0.75
+        },
+        "Pattern-recognition": {
+          "n": 9,
+          "acc": 0.5556,
+          "acc_norm": 0.6667
+        }
+      }
+    },
+    "bench-AGI": {
+      "score": null,
+      "n": null,
+      "notes": "Not yet evaluated on this tier."
+    }
+  }
+},
+    {
+  "id": "liquidai-lfm2.5-230m-base",
+  "name": "LiquidAI/LFM2.5-230M-Base",
+  "org": "LiquidAI",
+  "params_b": null,
+  "license": null,
+  "architecture": null,
+  "url": "https://huggingface.co/LiquidAI/LFM2.5-230M-Base",
+  "model_revision": "9d2be5519834990d30996f878b6771cccbd24f2c",
+  "script_sha256": "0c557dde5397ded8568280d621300759b4387a9f12227817c619a9325be8806a",
+  "runs": {
+    "bench-effortless-6-2026": {
+      "score": 0.0042,
+      "n": 240,
+      "notes": "Exact-match, normalized.",
+      "categories": {
+        "Commonsense-reasoning": {
+          "n": 37,
+          "exact_match": 0.0
+        },
+        "Knowledge-basic": {
+          "n": 42,
+          "exact_match": 0.0
+        },
+        "Language-comprehension": {
+          "n": 42,
+          "exact_match": 0.0
+        },
+        "Logic-deduction": {
+          "n": 42,
+          "exact_match": 0.0
+        },
+        "Math-arithmetic": {
+          "n": 40,
+          "exact_match": 0.0
+        },
+        "Pattern-recognition": {
+          "n": 37,
+          "exact_match": 0.027
+        }
+      }
+    },
+    "bench-easy-6-2026": {
+      "score": 0.2876,
+      "n": 238,
+      "notes": "Hybrid category-aware scoring (strict / flexible / semantic).",
+      "categories": {
+        "Commonsense-causality": {
+          "n": 10,
+          "hybrid_score": 0.7301
+        },
+        "Commonsense-reasoning": {
+          "n": 10,
+          "hybrid_score": 0.7137
+        },
+        "Commonsense-simulation": {
+          "n": 10,
+          "hybrid_score": 0.7434
+        },
+        "Knowledge-basic": {
+          "n": 33,
+          "hybrid_score": 0.0
+        },
+        "Knowledge-definitions": {
+          "n": 38,
+          "hybrid_score": 0.7888
+        },
+        "Language-comprehension": {
+          "n": 10,
+          "hybrid_score": 0.7182
+        },
+        "Language-structure": {
+          "n": 10,
+          "hybrid_score": 0.2974
+        },
+        "Language-transformation": {
+          "n": 10,
+          "hybrid_score": 0.6079
+        },
+        "Logic-consistency": {
+          "n": 10,
+          "hybrid_score": 0.0
+        },
+        "Logic-deduction": {
+          "n": 15,
+          "hybrid_score": 0.0
+        },
+        "Logic-pattern": {
+          "n": 10,
+          "hybrid_score": 0.0
+        },
+        "Math-arithmetic": {
+          "n": 33,
+          "hybrid_score": 0.0
+        },
+        "Math-pattern": {
+          "n": 14,
+          "hybrid_score": 0.0
+        },
+        "Math-reasoning": {
+          "n": 15,
+          "hybrid_score": 0.0247
+        },
+        "Pattern-matching": {
+          "n": 10,
+          "hybrid_score": 0.0
+        }
+      }
+    },
+    "bench-mid-6-2026": {
+      "score": 0.5301,
+      "n": 143,
+      "acc": 0.4266,
+      "acc_norm": 0.5245,
+      "soft_score": 0.4357,
+      "soft_score_norm": 0.5301,
+      "stderr": 0.0415,
+      "categories": {
+        "Commonsense-causality": {
+          "n": 5,
+          "acc": 0.8,
+          "acc_norm": 0.6
+        },
+        "Commonsense-reasoning": {
+          "n": 10,
+          "acc": 0.5,
+          "acc_norm": 0.4
+        },
+        "Commonsense-simulation": {
+          "n": 10,
+          "acc": 0.3,
+          "acc_norm": 0.4
+        },
+        "Knowledge-basic": {
+          "n": 7,
+          "acc": 0.5714,
+          "acc_norm": 0.8571
+        },
+        "Knowledge-definitions": {
+          "n": 10,
+          "acc": 0.1,
+          "acc_norm": 0.7
+        },
+        "Language-comprehension": {
+          "n": 10,
+          "acc": 0.5,
+          "acc_norm": 0.8
+        },
+        "Language-structure": {
+          "n": 10,
+          "acc": 0.1,
+          "acc_norm": 0.3
+        },
+        "Language-transformation": {
+          "n": 10,
+          "acc": 0.2,
+          "acc_norm": 0.4
+        },
+        "Logic-consistency": {
+          "n": 5,
+          "acc": 0.0,
+          "acc_norm": 0.0
+        },
+        "Logic-deduction": {
+          "n": 10,
+          "acc": 0.6,
+          "acc_norm": 0.7
+        },
+        "Logic-pattern": {
+          "n": 10,
+          "acc": 0.3,
+          "acc_norm": 0.4
+        },
+        "Math-arithmetic": {
+          "n": 8,
+          "acc": 0.875,
+          "acc_norm": 0.875
+        },
+        "Math-pattern": {
+          "n": 7,
+          "acc": 0.8571,
+          "acc_norm": 0.8571
+        },
+        "Math-reasoning": {
+          "n": 10,
+          "acc": 0.4,
+          "acc_norm": 0.3
+        },
+        "Pattern-generation": {
+          "n": 4,
+          "acc": 0.75,
+          "acc_norm": 0.5
+        },
+        "Pattern-matching": {
+          "n": 8,
+          "acc": 0.5,
+          "acc_norm": 0.5
+        },
+        "Pattern-recognition": {
+          "n": 9,
+          "acc": 0.3333,
+          "acc_norm": 0.3333
+        }
+      }
+    },
+    "bench-AGI": {
+      "score": null,
+      "n": null,
+      "notes": "Not yet evaluated on this tier."
+    }
+  }
+},
+    {
+  "id": "liquidai-lfm2.5-350m",
+  "name": "LiquidAI/LFM2.5-350M",
+  "org": "LiquidAI",
+  "params_b": null,
+  "license": null,
+  "architecture": null,
+  "url": "https://huggingface.co/LiquidAI/LFM2.5-350M",
+  "model_revision": "b9d6e4e2d75f440b12a2b4d731c808004ecbbd89",
+  "script_sha256": "0c557dde5397ded8568280d621300759b4387a9f12227817c619a9325be8806a",
+  "runs": {
+    "bench-effortless-6-2026": {
+      "score": 0.1375,
+      "n": 240,
+      "notes": "Exact-match, normalized.",
+      "categories": {
+        "Commonsense-reasoning": {
+          "n": 37,
+          "exact_match": 0.027
+        },
+        "Knowledge-basic": {
+          "n": 42,
+          "exact_match": 0.0952
+        },
+        "Language-comprehension": {
+          "n": 42,
+          "exact_match": 0.2143
+        },
+        "Logic-deduction": {
+          "n": 42,
+          "exact_match": 0.4286
+        },
+        "Math-arithmetic": {
+          "n": 40,
+          "exact_match": 0.0
+        },
+        "Pattern-recognition": {
+          "n": 37,
+          "exact_match": 0.027
+        }
+      }
+    },
+    "bench-easy-6-2026": {
+      "score": 0.358,
+      "n": 238,
+      "notes": "Hybrid category-aware scoring (strict / flexible / semantic).",
+      "categories": {
+        "Commonsense-causality": {
+          "n": 10,
+          "hybrid_score": 0.721
+        },
+        "Commonsense-reasoning": {
+          "n": 10,
+          "hybrid_score": 0.7313
+        },
+        "Commonsense-simulation": {
+          "n": 10,
+          "hybrid_score": 0.75
+        },
+        "Knowledge-basic": {
+          "n": 33,
+          "hybrid_score": 0.2424
+        },
+        "Knowledge-definitions": {
+          "n": 38,
+          "hybrid_score": 0.7996
+        },
+        "Language-comprehension": {
+          "n": 10,
+          "hybrid_score": 0.741
+        },
+        "Language-structure": {
+          "n": 10,
+          "hybrid_score": 0.3121
+        },
+        "Language-transformation": {
+          "n": 10,
+          "hybrid_score": 0.7689
+        },
+        "Logic-consistency": {
+          "n": 10,
+          "hybrid_score": 0.1
+        },
+        "Logic-deduction": {
+          "n": 15,
+          "hybrid_score": 0.2
+        },
+        "Logic-pattern": {
+          "n": 10,
+          "hybrid_score": 0.0
+        },
+        "Math-arithmetic": {
+          "n": 33,
+          "hybrid_score": 0.0
+        },
+        "Math-pattern": {
+          "n": 14,
+          "hybrid_score": 0.0
+        },
+        "Math-reasoning": {
+          "n": 15,
+          "hybrid_score": 0.1049
+        },
+        "Pattern-matching": {
+          "n": 10,
+          "hybrid_score": 0.1
+        }
+      }
+    },
+    "bench-mid-6-2026": {
+      "score": 0.5105,
+      "n": 143,
+      "acc": 0.4755,
+      "acc_norm": 0.5035,
+      "soft_score": 0.4825,
+      "soft_score_norm": 0.5105,
+      "stderr": 0.0417,
+      "categories": {
+        "Commonsense-causality": {
+          "n": 5,
+          "acc": 0.8,
+          "acc_norm": 0.8
+        },
+        "Commonsense-reasoning": {
+          "n": 10,
+          "acc": 0.5,
+          "acc_norm": 0.6
+        },
+        "Commonsense-simulation": {
+          "n": 10,
+          "acc": 0.4,
+          "acc_norm": 0.5
+        },
+        "Knowledge-basic": {
+          "n": 7,
+          "acc": 0.8571,
+          "acc_norm": 0.8571
+        },
+        "Knowledge-definitions": {
+          "n": 10,
+          "acc": 0.6,
+          "acc_norm": 0.8
+        },
+        "Language-comprehension": {
+          "n": 10,
+          "acc": 0.4,
+          "acc_norm": 0.8
+        },
+        "Language-structure": {
+          "n": 10,
+          "acc": 0.2,
+          "acc_norm": 0.1
+        },
+        "Language-transformation": {
+          "n": 10,
+          "acc": 0.2,
+          "acc_norm": 0.4
+        },
+        "Logic-consistency": {
+          "n": 5,
+          "acc": 0.0,
+          "acc_norm": 0.0
+        },
+        "Logic-deduction": {
+          "n": 10,
+          "acc": 0.3,
+          "acc_norm": 0.4
+        },
+        "Logic-pattern": {
+          "n": 10,
+          "acc": 0.4,
+          "acc_norm": 0.3
+        },
+        "Math-arithmetic": {
+          "n": 8,
+          "acc": 0.875,
+          "acc_norm": 0.875
+        },
+        "Math-pattern": {
+          "n": 7,
+          "acc": 0.7143,
+          "acc_norm": 0.7143
+        },
+        "Math-reasoning": {
+          "n": 10,
+          "acc": 0.2,
+          "acc_norm": 0.1
+        },
+        "Pattern-generation": {
+          "n": 4,
+          "acc": 0.75,
+          "acc_norm": 0.5
+        },
+        "Pattern-matching": {
+          "n": 8,
+          "acc": 0.75,
+          "acc_norm": 0.375
+        },
+        "Pattern-recognition": {
+          "n": 9,
+          "acc": 0.5556,
+          "acc_norm": 0.5556
+        }
+      }
+    },
+    "bench-AGI": {
+      "score": null,
+      "n": null,
+      "notes": "Not yet evaluated on this tier."
+    }
+  }
+},
+    {
+  "id": "liquidai-lfm2.5-350m-base",
+  "name": "LiquidAI/LFM2.5-350M-Base",
+  "org": "LiquidAI",
+  "params_b": null,
+  "license": null,
+  "architecture": null,
+  "url": "https://huggingface.co/LiquidAI/LFM2.5-350M-Base",
+  "model_revision": "9960764e30892e01f29a6dc23df2533fcd8bd5ae",
+  "script_sha256": "0c557dde5397ded8568280d621300759b4387a9f12227817c619a9325be8806a",
+  "runs": {
+    "bench-effortless-6-2026": {
+      "score": 0.0,
+      "n": 240,
+      "notes": "Exact-match, normalized.",
+      "categories": {
+        "Commonsense-reasoning": {
+          "n": 37,
+          "exact_match": 0.0
+        },
+        "Knowledge-basic": {
+          "n": 42,
+          "exact_match": 0.0
+        },
+        "Language-comprehension": {
+          "n": 42,
+          "exact_match": 0.0
+        },
+        "Logic-deduction": {
+          "n": 42,
+          "exact_match": 0.0
+        },
+        "Math-arithmetic": {
+          "n": 40,
+          "exact_match": 0.0
+        },
+        "Pattern-recognition": {
+          "n": 37,
+          "exact_match": 0.0
+        }
+      }
+    },
+    "bench-easy-6-2026": {
+      "score": 0.2788,
+      "n": 238,
+      "notes": "Hybrid category-aware scoring (strict / flexible / semantic).",
+      "categories": {
+        "Commonsense-causality": {
+          "n": 10,
+          "hybrid_score": 0.7048
+        },
+        "Commonsense-reasoning": {
+          "n": 10,
+          "hybrid_score": 0.6998
+        },
+        "Commonsense-simulation": {
+          "n": 10,
+          "hybrid_score": 0.744
+        },
+        "Knowledge-basic": {
+          "n": 33,
+          "hybrid_score": 0.0
+        },
+        "Knowledge-definitions": {
+          "n": 38,
+          "hybrid_score": 0.7958
+        },
+        "Language-comprehension": {
+          "n": 10,
+          "hybrid_score": 0.7201
+        },
+        "Language-structure": {
+          "n": 10,
+          "hybrid_score": 0.146
+        },
+        "Language-transformation": {
+          "n": 10,
+          "hybrid_score": 0.5558
+        },
+        "Logic-consistency": {
+          "n": 10,
+          "hybrid_score": 0.0
+        },
+        "Logic-deduction": {
+          "n": 15,
+          "hybrid_score": 0.0
+        },
+        "Logic-pattern": {
+          "n": 10,
+          "hybrid_score": 0.0
+        },
+        "Math-arithmetic": {
+          "n": 33,
+          "hybrid_score": 0.0
+        },
+        "Math-pattern": {
+          "n": 14,
+          "hybrid_score": 0.0
+        },
+        "Math-reasoning": {
+          "n": 15,
+          "hybrid_score": 0.0271
+        },
+        "Pattern-matching": {
+          "n": 10,
+          "hybrid_score": 0.0
+        }
+      }
+    },
+    "bench-mid-6-2026": {
+      "score": 0.5105,
+      "n": 143,
+      "acc": 0.3986,
+      "acc_norm": 0.5035,
+      "soft_score": 0.4091,
+      "soft_score_norm": 0.5105,
+      "stderr": 0.0417,
+      "categories": {
+        "Commonsense-causality": {
+          "n": 5,
+          "acc": 0.8,
+          "acc_norm": 0.6
+        },
+        "Commonsense-reasoning": {
+          "n": 10,
+          "acc": 0.4,
+          "acc_norm": 0.5
+        },
+        "Commonsense-simulation": {
+          "n": 10,
+          "acc": 0.3,
+          "acc_norm": 0.3
+        },
+        "Knowledge-basic": {
+          "n": 7,
+          "acc": 0.4286,
+          "acc_norm": 0.5714
+        },
+        "Knowledge-definitions": {
+          "n": 10,
+          "acc": 0.1,
+          "acc_norm": 0.7
+        },
+        "Language-comprehension": {
+          "n": 10,
+          "acc": 0.3,
+          "acc_norm": 0.8
+        },
+        "Language-structure": {
+          "n": 10,
+          "acc": 0.0,
+          "acc_norm": 0.2
+        },
+        "Language-transformation": {
+          "n": 10,
+          "acc": 0.5,
+          "acc_norm": 0.7
+        },
+        "Logic-consistency": {
+          "n": 5,
+          "acc": 0.0,
+          "acc_norm": 0.0
+        },
+        "Logic-deduction": {
+          "n": 10,
+          "acc": 0.4,
+          "acc_norm": 0.6
+        },
+        "Logic-pattern": {
+          "n": 10,
+          "acc": 0.4,
+          "acc_norm": 0.5
+        },
+        "Math-arithmetic": {
+          "n": 8,
+          "acc": 0.875,
+          "acc_norm": 0.875
+        },
+        "Math-pattern": {
+          "n": 7,
+          "acc": 0.7143,
+          "acc_norm": 0.7143
+        },
+        "Math-reasoning": {
+          "n": 10,
+          "acc": 0.4,
+          "acc_norm": 0.3
+        },
+        "Pattern-generation": {
+          "n": 4,
+          "acc": 0.75,
+          "acc_norm": 0.5
+        },
+        "Pattern-matching": {
+          "n": 8,
+          "acc": 0.625,
+          "acc_norm": 0.375
+        },
+        "Pattern-recognition": {
+          "n": 9,
+          "acc": 0.2222,
+          "acc_norm": 0.2222
+        }
+      }
+    },
+    "bench-AGI": {
+      "score": null,
+      "n": null,
+      "notes": "Not yet evaluated on this tier."
+    }
+  }
+},
+    {
   "id": "liquidai-lfm2.5-230m",
   "name": "LiquidAI/LFM2.5-230M",
   "org": "LiquidAI",