llm-orchestrator 1.0.0

package/models/model-thinking-data.json

@@ -0,0 +1,580 @@
+{
+  "_attribution": "llm-orchestrator · created by Bogdan-Gabriel Torcescu · https://www.linkedin.com/in/bogdantorcescu/ · keep this credit when copying or deriving",
+  "schema_version": 1,
+  "observed_at": "2026-09-22",
+  "benchmark": {
+    "name": "Artificial Analysis Intelligence Index",
+    "version": "v4.3.2",
+    "leaderboard_url": "https://artificialanalysis.ai/leaderboards/models",
+    "cost_unit": "USD weighted benchmark task cost"
+  },
+  "index_baselines": {
+    "benchmark_cost_usd": 0.5,
+    "token_basket": {
+      "input_mtok": 1,
+      "output_mtok": 0.25,
+      "baseline_usd": 9,
+      "description": "Synthetic 1M uncached input plus 250K output token basket; not a measured benchmark task."
+    }
+  },
+  "models": [
+    {
+      "key": "gpt-5-6-luna",
+      "display_name": "GPT-5.6 Luna",
+      "provider": "OpenAI",
+      "api_id": "gpt-5.6-luna",
+      "input_usd_per_mtok": 0.2,
+      "output_usd_per_mtok": 1.2,
+      "source": "https://artificialanalysis.ai/models/gpt-5-6-luna",
+      "measurements": [
+        [
+          "low",
+          21,
+          0.01
+        ],
+        [
+          "medium",
+          25,
+          0.02
+        ],
+        [
+          "high",
+          32,
+          0.04
+        ],
+        [
+          "xhigh",
+          35,
+          0.09
+        ],
+        [
+          "max",
+          37,
+          0.18
+        ]
+      ]
+    },
+    {
+      "key": "gpt-5-6-terra",
+      "display_name": "GPT-5.6 Terra",
+      "provider": "OpenAI",
+      "api_id": "gpt-5.6-terra",
+      "input_usd_per_mtok": 2,
+      "output_usd_per_mtok": 12,
+      "source": "https://artificialanalysis.ai/models/gpt-5-6-terra",
+      "measurements": [
+        [
+          "low",
+          27,
+          0.14
+        ],
+        [
+          "medium",
+          30,
+          0.18
+        ],
+        [
+          "high",
+          34,
+          0.34
+        ],
+        [
+          "xhigh",
+          38,
+          0.63
+        ],
+        [
+          "max",
+          42,
+          1.4
+        ]
+      ]
+    },
+    {
+      "key": "gpt-5-6-sol",
+      "display_name": "GPT-5.6 Sol",
+      "provider": "OpenAI",
+      "api_id": "gpt-5.6-sol",
+      "input_usd_per_mtok": 4,
+      "output_usd_per_mtok": 20,
+      "source": "https://artificialanalysis.ai/models/gpt-5-6-sol",
+      "measurements": [
+        [
+          "low",
+          33,
+          0.26
+        ],
+        [
+          "medium",
+          39,
+          0.5
+        ],
+        [
+          "high",
+          42,
+          0.81
+        ],
+        [
+          "xhigh",
+          44,
+          1.18
+        ],
+        [
+          "max",
+          47,
+          1.99
+        ]
+      ]
+    },
+    {
+      "key": "gpt-6-astra",
+      "display_name": "GPT-6 Astra",
+      "provider": "OpenAI",
+      "api_id": "gpt-6-astra",
+      "input_usd_per_mtok": 10,
+      "output_usd_per_mtok": 50,
+      "source": "https://artificialanalysis.ai/models/gpt-6-astra",
+      "measurements": [
+        [
+          "low",
+          46,
+          0.82
+        ],
+        [
+          "medium",
+          50,
+          1.54
+        ],
+        [
+          "high",
+          51,
+          1.73
+        ],
+        [
+          "xhigh",
+          52,
+          2.31
+        ],
+        [
+          "max",
+          53,
+          3.26
+        ]
+      ]
+    },
+    {
+      "key": "claude-sonnet-5",
+      "display_name": "Claude Sonnet 5",
+      "provider": "Anthropic",
+      "api_id": "claude-sonnet-5",
+      "input_usd_per_mtok": 2,
+      "output_usd_per_mtok": 10,
+      "source": "https://artificialanalysis.ai/models/claude-sonnet-5",
+      "measurements": [
+        [
+          "low",
+          24,
+          0.51
+        ],
+        [
+          "medium",
+          28,
+          1
+        ],
+        [
+          "high",
+          32,
+          1.79
+        ],
+        [
+          "xhigh",
+          34,
+          2.87
+        ],
+        [
+          "max",
+          38,
+          5.09
+        ]
+      ]
+    },
+    {
+      "key": "claude-opus-5",
+      "display_name": "Claude Opus 5",
+      "provider": "Anthropic",
+      "api_id": "claude-opus-5",
+      "input_usd_per_mtok": 5,
+      "output_usd_per_mtok": 25,
+      "source": "https://artificialanalysis.ai/models/claude-opus-5",
+      "measurements": [
+        [
+          "low",
+          39,
+          1.1
+        ],
+        [
+          "medium",
+          45,
+          2.19
+        ],
+        [
+          "high",
+          48,
+          3.61
+        ],
+        [
+          "xhigh",
+          50,
+          4.88
+        ],
+        [
+          "max",
+          51,
+          5.86
+        ]
+      ]
+    },
+    {
+      "key": "claude-fable-5-1",
+      "display_name": "Claude Fable 5.1",
+      "provider": "Anthropic",
+      "api_id": "claude-fable-5-1",
+      "input_usd_per_mtok": 10,
+      "output_usd_per_mtok": 50,
+      "source": "https://artificialanalysis.ai/models/claude-fable-5-1",
+      "measurement_note": "All displayed scores include the benchmark default fallback and are not standalone scores.",
+      "measurements": [
+        [
+          "low",
+          47,
+          2.37
+        ],
+        [
+          "medium",
+          49,
+          2.98
+        ],
+        [
+          "high",
+          51,
+          3.91
+        ],
+        [
+          "xhigh",
+          53,
+          5.98
+        ],
+        [
+          "max",
+          53,
+          7.63
+        ]
+      ]
+    },
+    {
+      "key": "claude-fable-5",
+      "display_name": "Claude Fable 5",
+      "provider": "Anthropic",
+      "api_id": "claude-fable-5",
+      "input_usd_per_mtok": 10,
+      "output_usd_per_mtok": 50,
+      "source": "https://artificialanalysis.ai/models/claude-fable-5",
+      "measurement_note": "AA v4.3.2 max result uses Opus 4.8 default fallback. This legacy catalog model is not in the current leaderboard filter; segregate it from standalone cross-model comparisons.",
+      "measurements": [
+        [
+          "low",
+          null,
+          null
+        ],
+        [
+          "medium",
+          null,
+          null
+        ],
+        [
+          "high",
+          null,
+          null
+        ],
+        [
+          "xhigh",
+          null,
+          null
+        ],
+        [
+          "max",
+          50,
+          8.75
+        ]
+      ]
+    },
+    {
+      "key": "claude-4-5-haiku",
+      "display_name": "Claude Haiku 4.5",
+      "provider": "Anthropic",
+      "api_id": "claude-haiku-4-5",
+      "input_usd_per_mtok": 1,
+      "output_usd_per_mtok": 5,
+      "source": "https://artificialanalysis.ai/models/claude-4-5-haiku",
+      "measurement_note": "Its API thinking budget is not an effort enum. The disabled score 15 is incomplete and intentionally excluded.",
+      "measurements": [
+        [
+          "disabled",
+          null,
+          null
+        ],
+        [
+          "enabled",
+          17,
+          0.21
+        ]
+      ]
+    },
+    {
+      "key": "muse-spark-1-3",
+      "display_name": "Muse Spark 1.3",
+      "provider": "Muse",
+      "api_id": null,
+      "input_usd_per_mtok": 1.25,
+      "output_usd_per_mtok": 4.25,
+      "source": "https://artificialanalysis.ai/models/muse-spark-1-3",
+      "measurements": [
+        [
+          "xhigh",
+          45,
+          1.37
+        ],
+        [
+          "max",
+          48,
+          1.6
+        ]
+      ]
+    },
+    {
+      "key": "grok-4-7",
+      "display_name": "Grok 4.7",
+      "provider": "xAI",
+      "api_id": "grok-4.7",
+      "input_usd_per_mtok": 2,
+      "output_usd_per_mtok": 6,
+      "source": "https://artificialanalysis.ai/models/grok-4-7",
+      "price_note": "$2/$6 below 200K input; $4/$12 above 200K.",
+      "api_source": "https://docs.x.ai/developers/release-notes",
+      "measurements": [
+        [
+          "low",
+          null,
+          null
+        ],
+        [
+          "medium",
+          null,
+          null
+        ],
+        [
+          "high",
+          46,
+          2.73
+        ],
+        [
+          "xhigh",
+          46,
+          3.74
+        ]
+      ]
+    },
+    {
+      "key": "grok-4-6",
+      "display_name": "Grok 4.6",
+      "provider": "xAI",
+      "api_id": null,
+      "input_usd_per_mtok": 2,
+      "output_usd_per_mtok": 6,
+      "source": "https://artificialanalysis.ai/models/grok-4-6",
+      "measurements": [
+        [
+          "low",
+          35,
+          0.48
+        ],
+        [
+          "medium",
+          43,
+          1.5
+        ],
+        [
+          "high",
+          44,
+          1.86
+        ],
+        [
+          "xhigh",
+          44,
+          2.32
+        ]
+      ]
+    },
+    {
+      "key": "mimo-v2-6-pro",
+      "display_name": "MiMo V2.6 Pro",
+      "provider": "Xiaomi",
+      "api_id": "mimo-v2.6-pro",
+      "input_usd_per_mtok": 0.435,
+      "output_usd_per_mtok": 0.87,
+      "source": "https://artificialanalysis.ai/models/mimo-v2-6-pro",
+      "price_source": "https://mimo.mi.com/docs/en-US/quick-start/usage-guide/text-generation/batch-api",
+      "api_source": "https://mimo.mi.com/docs/en-US/quick-start/usage-guide/text-generation/batch-api",
+      "measurements": [
+        [
+          "default",
+          46,
+          0.13
+        ]
+      ]
+    },
+    {
+      "key": "qwen3-8-max",
+      "display_name": "Qwen3.8 Max",
+      "provider": "Alibaba",
+      "api_id": null,
+      "input_usd_per_mtok": 2,
+      "output_usd_per_mtok": 6,
+      "source": "https://artificialanalysis.ai/models/qwen3-8-max",
+      "measurements": [
+        [
+          "default",
+          45,
+          5.41
+        ]
+      ]
+    },
+    {
+      "key": "glm-5-3",
+      "display_name": "GLM 5.3",
+      "provider": "Z.ai",
+      "api_id": null,
+      "input_usd_per_mtok": 1.4,
+      "output_usd_per_mtok": 4.4,
+      "source": "https://artificialanalysis.ai/models/glm-5-3",
+      "measurements": [
+        [
+          "max",
+          45,
+          2.01
+        ]
+      ]
+    },
+    {
+      "key": "glm-5-3-flash",
+      "display_name": "GLM 5.3 Flash",
+      "provider": "Z.ai",
+      "api_id": null,
+      "input_usd_per_mtok": 0.15,
+      "output_usd_per_mtok": 0.5,
+      "source": "https://artificialanalysis.ai/models/glm-5-3-flash",
+      "measurements": [
+        [
+          "default",
+          42,
+          0.25
+        ]
+      ]
+    },
+    {
+      "key": "step-5",
+      "display_name": "Step 5",
+      "provider": "StepFun",
+      "api_id": null,
+      "input_usd_per_mtok": 1,
+      "output_usd_per_mtok": 2.7,
+      "source": "https://artificialanalysis.ai/models/step-5",
+      "measurements": [
+        [
+          "default",
+          44,
+          0.72
+        ]
+      ]
+    },
+    {
+      "key": "kimi-k3",
+      "display_name": "Kimi K3",
+      "provider": "Moonshot AI",
+      "api_id": null,
+      "input_usd_per_mtok": 3,
+      "output_usd_per_mtok": 15,
+      "source": "https://artificialanalysis.ai/models/kimi-k3",
+      "measurements": [
+        [
+          "low",
+          null,
+          null
+        ],
+        [
+          "max",
+          44,
+          2
+        ]
+      ]
+    },
+    {
+      "key": "gemini-3-8-flash",
+      "display_name": "Gemini 3.8 Flash",
+      "provider": "Google",
+      "api_id": null,
+      "input_usd_per_mtok": 0.75,
+      "output_usd_per_mtok": 3.75,
+      "source": "https://artificialanalysis.ai/models/gemini-3-8-flash",
+      "measurements": [
+        [
+          "low",
+          33,
+          null
+        ],
+        [
+          "medium",
+          40,
+          0.93
+        ],
+        [
+          "high",
+          41,
+          1.24
+        ]
+      ]
+    },
+    {
+      "key": "deepseek-v4-1-flash",
+      "display_name": "DeepSeek V4.1 Flash",
+      "provider": "DeepSeek",
+      "api_id": null,
+      "input_usd_per_mtok": 0.3,
+      "output_usd_per_mtok": 1.2,
+      "source": "https://artificialanalysis.ai/models/deepseek-v4-1-flash",
+      "measurements": [
+        [
+          "max",
+          39,
+          0.27
+        ]
+      ]
+    },
+    {
+      "key": "minimax-m3",
+      "display_name": "MiniMax M3",
+      "provider": "MiniMax",
+      "api_id": null,
+      "input_usd_per_mtok": 0.3,
+      "output_usd_per_mtok": 1.2,
+      "source": "https://artificialanalysis.ai/models/minimax-m3",
+      "measurements": [
+        [
+          "default",
+          29,
+          0.51
+        ]
+      ]
+    }
+  ]
+}