benchmark-open.json

{
  "model": "Reframr-RFM-v2-Base/model.safetensors",
  "created_at": "2026-05-08T19:30:00+01:00",
  "gate": "local_v2_blind_gate",
  "temperatures": {
    "0.35": {
      "semantic_pass": 8,
      "strict_pass": 8,
      "total": 8
    },
    "0.58": {
      "semantic_pass": 8,
      "strict_pass": 8,
      "total": 8
    },
    "0.72": {
      "semantic_pass": 8,
      "strict_pass": 8,
      "total": 8
    }
  },
  "cases": [
    "identity_chat",
    "instruction_persona",
    "blind_story",
    "compound_task",
    "no_tool_current",
    "emoji_unseen",
    "blind_reasoning",
    "tool_result_current"
  ],
  "note": "This is a local release gate for packaging confidence, not an external benchmark or GPT-5 parity claim."
}