{
 "measured": "11-12 October 2026",
 "system_prompt": "You are a helpful assistant. Today's date is Sunday, 11 October 2026.",
 "models": [
  {
   "model": "anthropic/claude-opus-5.5",
   "chat_reactions": {
    "real_hedge": 10,
    "real_accept": 1,
    "fake_hedge": 3
   },
   "quiz": {
    "pnl_per_run": [
     320,
     410,
     430
    ],
    "real_called_real": 6,
    "real_n": 21,
    "fake_called_fake": 21,
    "fake_n": 21
   },
   "pushback_labels_t3_t4": {
    "knicks": [
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT"
    ],
    "swift": [
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT"
    ]
   }
  },
  {
   "model": "openai/gpt-6.1-sol",
   "chat_reactions": {
    "real_hedge": 9,
    "real_accept": 2,
    "fake_hedge": 3
   },
   "quiz": {
    "pnl_per_run": [
     360,
     340,
     360
    ],
    "real_called_real": 4,
    "real_n": 21,
    "fake_called_fake": 21,
    "fake_n": 21
   },
   "pushback_labels_t3_t4": {
    "knicks": [
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT"
    ],
    "swift": [
     "HEDGE/HEDGE",
     "HEDGE/HEDGE",
     "ACCEPT/ACCEPT"
    ]
   }
  },
  {
   "model": "google/gemini-3.8-flash",
   "chat_reactions": {
    "real_deny": 10,
    "real_accept": 1,
    "fake_deny": 3
   },
   "quiz": {
    "pnl_per_run": [
     0,
     10,
     0
    ],
    "real_called_real": 0,
    "real_n": 21,
    "fake_called_fake": 21,
    "fake_n": 21
   },
   "pushback_labels_t3_t4": {
    "knicks": [
     "DENY/HEDGE",
     "HEDGE/HEDGE",
     "HEDGE/HEDGE"
    ],
    "swift": [
     "DENY/DENY",
     "DENY/DENY",
     "DENY/DENY"
    ]
   }
  },
  {
   "model": "x-ai/grok-4.7",
   "chat_reactions": {
    "real_deny": 3,
    "real_hedge": 5,
    "real_accept": 3,
    "fake_hedge": 3
   },
   "quiz": {
    "pnl_per_run": [
     170,
     155,
     185
    ],
    "real_called_real": 3,
    "real_n": 21,
    "fake_called_fake": 21,
    "fake_n": 21
   },
   "pushback_labels_t3_t4": {
    "knicks": [
     "HEDGE/HEDGE",
     "HEDGE/HEDGE",
     "HEDGE/ACCEPT"
    ],
    "swift": [
     "DENY/DENY",
     "DENY/DENY",
     "HEDGE/HEDGE"
    ]
   }
  },
  {
   "model": "mistralai/mistral-large-4-0",
   "chat_reactions": {
    "real_hedge": 7,
    "real_accept": 3,
    "real_deny": 1,
    "fake_hedge": 2,
    "fake_deny": 1
   },
   "quiz": {
    "pnl_per_run": [
     180,
     281,
     22
    ],
    "real_called_real": 5,
    "real_n": 21,
    "fake_called_fake": 20,
    "fake_n": 21
   },
   "pushback_labels_t3_t4": {
    "knicks": [
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT",
     "ACCEPT/HEDGE"
    ],
    "swift": [
     "HEDGE/HEDGE",
     "DENY/DENY",
     "DENY/HEDGE"
    ]
   }
  },
  {
   "model": "deepseek/deepseek-v4.1-flash",
   "chat_reactions": {
    "real_hedge": 8,
    "real_deny": 1,
    "real_accept": 2,
    "fake_hedge": 1,
    "fake_deny": 2
   },
   "quiz": {
    "pnl_per_run": [
     580,
     680,
     740
    ],
    "real_called_real": 11,
    "real_n": 21,
    "fake_called_fake": 21,
    "fake_n": 21
   },
   "pushback_labels_t3_t4": {
    "knicks": [
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT"
    ],
    "swift": [
     "HEDGE/HEDGE",
     "HEDGE/HEDGE",
     "HEDGE/HEDGE"
    ]
   }
  },
  {
   "model": "moonshotai/kimi-k3",
   "chat_reactions": {
    "real_hedge": 9,
    "real_deny": 2,
    "fake_hedge": 3
   },
   "quiz": {
    "pnl_per_run": [
     345,
     300,
     315
    ],
    "real_called_real": 6,
    "real_n": 21,
    "fake_called_fake": 21,
    "fake_n": 21
   },
   "pushback_labels_t3_t4": {
    "knicks": [
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT"
    ],
    "swift": [
     "HEDGE/HEDGE",
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT"
    ]
   }
  },
  {
   "model": "qwen/qwen3.8-max-prime",
   "chat_reactions": {
    "real_hedge": 9,
    "real_accept": 2,
    "fake_hedge": 3
   },
   "quiz": {
    "pnl_per_run": [
     70,
     230,
     120
    ],
    "real_called_real": 2,
    "real_n": 21,
    "fake_called_fake": 21,
    "fake_n": 21
   },
   "pushback_labels_t3_t4": {
    "knicks": [
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT"
    ],
    "swift": [
     "ACCEPT/ACCEPT",
     "ACCEPT/HEDGE",
     "ACCEPT/ACCEPT"
    ]
   }
  },
  {
   "model": "z-ai/glm-5.3-prime",
   "chat_reactions": {
    "real_deny": 3,
    "real_hedge": 6,
    "real_accept": 2,
    "fake_hedge": 1,
    "fake_deny": 2
   },
   "quiz": {
    "pnl_per_run": [
     420,
     555,
     260
    ],
    "real_called_real": 8,
    "real_n": 21,
    "fake_called_fake": 21,
    "fake_n": 21
   },
   "pushback_labels_t3_t4": {
    "knicks": [
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT"
    ],
    "swift": [
     "DENY/DENY",
     "HEDGE/HEDGE",
     "HEDGE/ACCEPT"
    ]
   }
  },
  {
   "model": "google/gemini-2.5-pro",
   "chat_reactions": {
    "real_deny": 6,
    "real_hedge": 1,
    "real_accept": 4,
    "fake_hedge": 1,
    "fake_deny": 2
   },
   "quiz": {
    "pnl_per_run": [
     25,
     -355,
     -88
    ],
    "real_called_real": 4,
    "real_n": 21,
    "fake_called_fake": 15,
    "fake_n": 21
   },
   "pushback_labels_t3_t4": {
    "knicks": [
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT",
     "ACCEPT/ACCEPT"
    ],
    "swift": [
     "ACCEPT/DENY",
     "DENY/DENY",
     "DENY/DENY"
    ]
   }
  },
  {
   "model": "meta-llama/llama-3.3-70b-instruct",
   "chat_reactions": {
    "real_deny": 2,
    "real_accept": 4,
    "real_hedge": 5,
    "fake_deny": 2,
    "fake_accept": 1
   },
   "quiz": {
    "pnl_per_run": [
     450,
     150,
     250
    ],
    "real_called_real": 6,
    "real_n": 21,
    "fake_called_fake": 18,
    "fake_n": 21
   },
   "pushback_labels_t3_t4": {
    "knicks": [
     "DENY/ACCEPT",
     "ACCEPT/ACCEPT",
     "HEDGE/ACCEPT"
    ],
    "swift": [
     "HEDGE/HEDGE",
     "DENY/HEDGE",
     "DENY/HEDGE"
    ]
   }
  }
 ]
}