{
  "schema_version": 1,
  "generated_at": "2026-05-17T11:26:14Z",
  "count": 9,
  "models": [
    {
      "slug": "qwen3.5-35b-a3b",
      "model_id": "qwen3.5-35b-a3b",
      "model_name": "qwen3.5-35b-a3b",
      "vendor": "Alibaba",
      "evaluation_date": "2026-04-10",
      "generated_at": "2026-04-10T16:26:44.591594",
      "total_valid_responses": 42512,
      "validity_rate": {
        "L4": 100.0,
        "L3": 100.0,
        "L2": 100.0
      },
      "files": {
        "report": "/data/aio-benchmark/qwen3.5-35b-a3b/report.json",
        "pcs_trr": {
          "L2": "/data/aio-benchmark/qwen3.5-35b-a3b/pcs-trr-L2.json",
          "L3": "/data/aio-benchmark/qwen3.5-35b-a3b/pcs-trr-L3.json",
          "L4": "/data/aio-benchmark/qwen3.5-35b-a3b/pcs-trr-L4.json"
        },
        "rankings": {
          "L2": "/data/aio-benchmark/qwen3.5-35b-a3b/rankings/L2.json",
          "L3": "/data/aio-benchmark/qwen3.5-35b-a3b/rankings/L3.json",
          "L4": "/data/aio-benchmark/qwen3.5-35b-a3b/rankings/L4.json"
        }
      }
    },
    {
      "slug": "gemma-4-31b-it",
      "model_id": "gemma-4-31b-it",
      "model_name": "gemma-4-31b-it",
      "vendor": "Google",
      "evaluation_date": "2026-04-09",
      "generated_at": "2026-04-10T16:26:44.490760",
      "total_valid_responses": 42524,
      "validity_rate": {
        "L4": 100.0,
        "L3": 100.0,
        "L2": 100.0
      },
      "files": {
        "report": "/data/aio-benchmark/gemma-4-31b-it/report.json",
        "pcs_trr": {
          "L2": "/data/aio-benchmark/gemma-4-31b-it/pcs-trr-L2.json",
          "L3": "/data/aio-benchmark/gemma-4-31b-it/pcs-trr-L3.json",
          "L4": "/data/aio-benchmark/gemma-4-31b-it/pcs-trr-L4.json"
        },
        "rankings": {
          "L2": "/data/aio-benchmark/gemma-4-31b-it/rankings/L2.json",
          "L3": "/data/aio-benchmark/gemma-4-31b-it/rankings/L3.json",
          "L4": "/data/aio-benchmark/gemma-4-31b-it/rankings/L4.json"
        }
      }
    },
    {
      "slug": "trinity-large",
      "model_id": "trinity-large",
      "model_name": "trinity-large",
      "vendor": "Arcee",
      "evaluation_date": "2026-03-19",
      "generated_at": "2026-04-10T16:26:44.275905",
      "total_valid_responses": 42072,
      "validity_rate": {
        "L4": 100.0,
        "L3": 100.0,
        "L2": 100.0
      },
      "files": {
        "report": "/data/aio-benchmark/trinity-large/report.json",
        "pcs_trr": {
          "L2": "/data/aio-benchmark/trinity-large/pcs-trr-L2.json",
          "L3": "/data/aio-benchmark/trinity-large/pcs-trr-L3.json",
          "L4": "/data/aio-benchmark/trinity-large/pcs-trr-L4.json"
        },
        "rankings": {
          "L2": "/data/aio-benchmark/trinity-large/rankings/L2.json",
          "L3": "/data/aio-benchmark/trinity-large/rankings/L3.json",
          "L4": "/data/aio-benchmark/trinity-large/rankings/L4.json"
        }
      }
    },
    {
      "slug": "gpt-5-nano",
      "model_id": "gpt-5-nano",
      "model_name": "gpt-5-nano",
      "vendor": "OpenAI",
      "evaluation_date": "2026-03-19",
      "generated_at": "2026-04-10T16:26:44.380417",
      "total_valid_responses": 42525,
      "validity_rate": {
        "L4": 100.0,
        "L3": 100.0,
        "L2": 100.0
      },
      "files": {
        "report": "/data/aio-benchmark/gpt-5-nano/report.json",
        "pcs_trr": {
          "L2": "/data/aio-benchmark/gpt-5-nano/pcs-trr-L2.json",
          "L3": "/data/aio-benchmark/gpt-5-nano/pcs-trr-L3.json",
          "L4": "/data/aio-benchmark/gpt-5-nano/pcs-trr-L4.json"
        },
        "rankings": {
          "L2": "/data/aio-benchmark/gpt-5-nano/rankings/L2.json",
          "L3": "/data/aio-benchmark/gpt-5-nano/rankings/L3.json",
          "L4": "/data/aio-benchmark/gpt-5-nano/rankings/L4.json"
        }
      }
    },
    {
      "slug": "gemini-3-flash-lite",
      "model_id": "gemini-3-flash-lite",
      "model_name": "gemini-3-flash-lite",
      "vendor": "Google",
      "evaluation_date": "2026-03-19",
      "generated_at": "2026-04-10T16:26:44.173497",
      "total_valid_responses": 42525,
      "validity_rate": {
        "L4": 100.0,
        "L3": 100.0,
        "L2": 100.0
      },
      "files": {
        "report": "/data/aio-benchmark/gemini-3-flash-lite/report.json",
        "pcs_trr": {
          "L2": "/data/aio-benchmark/gemini-3-flash-lite/pcs-trr-L2.json",
          "L3": "/data/aio-benchmark/gemini-3-flash-lite/pcs-trr-L3.json",
          "L4": "/data/aio-benchmark/gemini-3-flash-lite/pcs-trr-L4.json"
        },
        "rankings": {
          "L2": "/data/aio-benchmark/gemini-3-flash-lite/rankings/L2.json",
          "L3": "/data/aio-benchmark/gemini-3-flash-lite/rankings/L3.json",
          "L4": "/data/aio-benchmark/gemini-3-flash-lite/rankings/L4.json"
        }
      }
    },
    {
      "slug": "mimo-v2-flash",
      "model_id": "mimo-v2-flash",
      "model_name": "mimo-v2-flash",
      "vendor": "Xiaomi",
      "evaluation_date": "2026-03-18",
      "generated_at": "2026-04-10T16:26:44.054252",
      "total_valid_responses": 42525,
      "validity_rate": {
        "L4": 100.0,
        "L3": 100.0,
        "L2": 100.0
      },
      "files": {
        "report": "/data/aio-benchmark/mimo-v2-flash/report.json",
        "pcs_trr": {
          "L2": "/data/aio-benchmark/mimo-v2-flash/pcs-trr-L2.json",
          "L3": "/data/aio-benchmark/mimo-v2-flash/pcs-trr-L3.json",
          "L4": "/data/aio-benchmark/mimo-v2-flash/pcs-trr-L4.json"
        },
        "rankings": {
          "L2": "/data/aio-benchmark/mimo-v2-flash/rankings/L2.json",
          "L3": "/data/aio-benchmark/mimo-v2-flash/rankings/L3.json",
          "L4": "/data/aio-benchmark/mimo-v2-flash/rankings/L4.json"
        }
      }
    },
    {
      "slug": "grok-4.1-fast",
      "model_id": "grok-4.1-fast",
      "model_name": "grok-4.1-fast",
      "vendor": "xAI",
      "evaluation_date": "2026-03-16",
      "generated_at": "2026-04-10T16:26:43.951946",
      "total_valid_responses": 42525,
      "validity_rate": {
        "L4": 100.0,
        "L3": 100.0,
        "L2": 100.0
      },
      "files": {
        "report": "/data/aio-benchmark/grok-4.1-fast/report.json",
        "pcs_trr": {
          "L2": "/data/aio-benchmark/grok-4.1-fast/pcs-trr-L2.json",
          "L3": "/data/aio-benchmark/grok-4.1-fast/pcs-trr-L3.json",
          "L4": "/data/aio-benchmark/grok-4.1-fast/pcs-trr-L4.json"
        },
        "rankings": {
          "L2": "/data/aio-benchmark/grok-4.1-fast/rankings/L2.json",
          "L3": "/data/aio-benchmark/grok-4.1-fast/rankings/L3.json",
          "L4": "/data/aio-benchmark/grok-4.1-fast/rankings/L4.json"
        }
      }
    },
    {
      "slug": "deepseek-v3.2",
      "model_id": "deepseek-v3.2",
      "model_name": "deepseek-v3.2",
      "vendor": "DeepSeek",
      "evaluation_date": "2026-03-16",
      "generated_at": "2026-04-10T16:26:43.850186",
      "total_valid_responses": 42525,
      "validity_rate": {
        "L4": 100.0,
        "L3": 100.0,
        "L2": 100.0
      },
      "files": {
        "report": "/data/aio-benchmark/deepseek-v3.2/report.json",
        "pcs_trr": {
          "L2": "/data/aio-benchmark/deepseek-v3.2/pcs-trr-L2.json",
          "L3": "/data/aio-benchmark/deepseek-v3.2/pcs-trr-L3.json",
          "L4": "/data/aio-benchmark/deepseek-v3.2/pcs-trr-L4.json"
        },
        "rankings": {
          "L2": "/data/aio-benchmark/deepseek-v3.2/rankings/L2.json",
          "L3": "/data/aio-benchmark/deepseek-v3.2/rankings/L3.json",
          "L4": "/data/aio-benchmark/deepseek-v3.2/rankings/L4.json"
        }
      }
    },
    {
      "slug": "claude-haiku-4-5-20251001",
      "model_id": "claude-haiku-4-5-20251001",
      "model_name": "claude-haiku-4-5-20251001",
      "vendor": "Anthropic",
      "evaluation_date": "2026-03-16",
      "generated_at": "2026-04-10T16:26:43.750355",
      "total_valid_responses": 42136,
      "validity_rate": {
        "L4": 98.5,
        "L3": 100.0,
        "L2": 98.7
      },
      "files": {
        "report": "/data/aio-benchmark/claude-haiku-4-5-20251001/report.json",
        "pcs_trr": {
          "L2": "/data/aio-benchmark/claude-haiku-4-5-20251001/pcs-trr-L2.json",
          "L3": "/data/aio-benchmark/claude-haiku-4-5-20251001/pcs-trr-L3.json",
          "L4": "/data/aio-benchmark/claude-haiku-4-5-20251001/pcs-trr-L4.json"
        },
        "rankings": {
          "L2": "/data/aio-benchmark/claude-haiku-4-5-20251001/rankings/L2.json",
          "L3": "/data/aio-benchmark/claude-haiku-4-5-20251001/rankings/L3.json",
          "L4": "/data/aio-benchmark/claude-haiku-4-5-20251001/rankings/L4.json"
        }
      }
    }
  ]
}