{
  "schemaVersion": 1,
  "dataset": "llm-overall-index",
  "title": {
    "de": "Gradually Gesamtindex der LLMs",
    "en": "Gradually Overall LLM Index"
  },
  "generatedAt": "2026-11-10",
  "license": {
    "name": "CC BY 4.0",
    "url": "https://creativecommons.org/licenses/by/4.0/"
  },
  "attribution": {
    "de": "Quelle: gradually.ai, https://www.gradually.ai/ki-modelle/",
    "en": "Source: gradually.ai, https://www.gradually.ai/en/ai-models/"
  },
  "page": {
    "de": "https://www.gradually.ai/ki-modelle/",
    "en": "https://www.gradually.ai/en/ai-models/"
  },
  "files": {
    "csv": "https://www.gradually.ai/data/open/llm-overall-index.csv",
    "json": "https://www.gradually.ai/data/open/llm-overall-index.json"
  },
  "method": "Gradually benchmark meta-score: a factor model over published benchmark series. 100 is the mean of a fixed reference cohort, 15 points are one spread unit; the scale is open at both ends. Only models with a published score are listed; the place is empty when the score is not precise enough for one.",
  "details": {
    "methodVersion": "benchmark-meta-score-v5"
  },
  "fields": [
    {
      "key": "model",
      "description": "Stable model slug, the last part of the profile URL."
    },
    {
      "key": "name",
      "description": "Display name of the model."
    },
    {
      "key": "developer",
      "description": "Developer of the model."
    },
    {
      "key": "rank",
      "description": "Displayed place in score order; empty when the model has no place."
    },
    {
      "key": "score",
      "description": "Overall index value, one decimal."
    },
    {
      "key": "score_lower_95",
      "description": "Lower end of the 95 percent interval."
    },
    {
      "key": "score_upper_95",
      "description": "Upper end of the 95 percent interval."
    },
    {
      "key": "standard_error",
      "description": "Standard error of the score on the same scale."
    },
    {
      "key": "benchmark_series",
      "description": "Number of benchmark series that enter the score."
    },
    {
      "key": "profile_url",
      "description": "Model profile on gradually.ai."
    }
  ],
  "rows": [
    {
      "model": "claude-fable-5.2",
      "name": "Claude Fable 5.2",
      "developer": "Anthropic",
      "rank": 1,
      "score": 130.9,
      "score_lower_95": 122.6,
      "score_upper_95": 139.2,
      "standard_error": 4.25,
      "benchmark_series": 26,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-fable-5.2/"
    },
    {
      "model": "gemini-4-carbon",
      "name": "Gemini 4 Carbon",
      "developer": "Google DeepMind",
      "rank": 2,
      "score": 127,
      "score_lower_95": 119.6,
      "score_upper_95": 134.3,
      "standard_error": 3.74,
      "benchmark_series": 18,
      "profile_url": "https://www.gradually.ai/ki-modelle/gemini-4-carbon/"
    },
    {
      "model": "claude-opus-5.5",
      "name": "Claude Opus 5.5",
      "developer": "Anthropic",
      "rank": 3,
      "score": 125.6,
      "score_lower_95": 120.4,
      "score_upper_95": 130.9,
      "standard_error": 2.7,
      "benchmark_series": 45,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-opus-5.5/"
    },
    {
      "model": "claude-fable-5.1",
      "name": "Claude Fable 5.1",
      "developer": "Anthropic",
      "rank": 4,
      "score": 124.1,
      "score_lower_95": 119.8,
      "score_upper_95": 128.4,
      "standard_error": 2.2,
      "benchmark_series": 45,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-fable-5.1/"
    },
    {
      "model": "claude-sonnet-5.5",
      "name": "Claude Sonnet 5.5",
      "developer": "Anthropic",
      "rank": 5,
      "score": 121.8,
      "score_lower_95": 116.7,
      "score_upper_95": 126.8,
      "standard_error": 2.58,
      "benchmark_series": 41,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-sonnet-5.5/"
    },
    {
      "model": "gemini-4-argon",
      "name": "Gemini 4 Argon",
      "developer": "Google DeepMind",
      "rank": 6,
      "score": 121.4,
      "score_lower_95": 116.2,
      "score_upper_95": 126.6,
      "standard_error": 2.67,
      "benchmark_series": 47,
      "profile_url": "https://www.gradually.ai/ki-modelle/gemini-4-argon/"
    },
    {
      "model": "gpt-6-astra",
      "name": "GPT-6 Astra",
      "developer": "OpenAI",
      "rank": 7,
      "score": 120.2,
      "score_lower_95": 115.8,
      "score_upper_95": 124.5,
      "standard_error": 2.21,
      "benchmark_series": 48,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-6-astra/"
    },
    {
      "model": "meta-muse-wonder-full-1.0",
      "name": "Muse Wonder Full",
      "developer": "Meta",
      "rank": 8,
      "score": 118.1,
      "score_lower_95": 112.8,
      "score_upper_95": 123.4,
      "standard_error": 2.69,
      "benchmark_series": 39,
      "profile_url": "https://www.gradually.ai/ki-modelle/meta-muse-wonder-full-1.0/"
    },
    {
      "model": "gpt-6.1-sol",
      "name": "GPT-6.1 Sol",
      "developer": "OpenAI",
      "rank": 9,
      "score": 118,
      "score_lower_95": 113.9,
      "score_upper_95": 122.1,
      "standard_error": 2.08,
      "benchmark_series": 48,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-6.1-sol/"
    },
    {
      "model": "claude-opus-5",
      "name": "Claude Opus 5",
      "developer": "Anthropic",
      "rank": 10,
      "score": 117.4,
      "score_lower_95": 113.6,
      "score_upper_95": 121.1,
      "standard_error": 1.9,
      "benchmark_series": 50,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-opus-5/"
    },
    {
      "model": "meta-muse-wonder-1.0",
      "name": "Muse Wonder",
      "developer": "Meta",
      "rank": 11,
      "score": 113.3,
      "score_lower_95": 108.2,
      "score_upper_95": 118.5,
      "standard_error": 2.61,
      "benchmark_series": 38,
      "profile_url": "https://www.gradually.ai/ki-modelle/meta-muse-wonder-1.0/"
    },
    {
      "model": "claude-fable-5",
      "name": "Claude Fable 5",
      "developer": "Anthropic",
      "rank": 12,
      "score": 112.8,
      "score_lower_95": 107.5,
      "score_upper_95": 118.1,
      "standard_error": 2.71,
      "benchmark_series": 37,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-fable-5/"
    },
    {
      "model": "kimi-k3.1-pro",
      "name": "Kimi K3.1 Pro",
      "developer": "Moonshot AI",
      "rank": 13,
      "score": 112.6,
      "score_lower_95": 107,
      "score_upper_95": 118.2,
      "standard_error": 2.85,
      "benchmark_series": 27,
      "profile_url": "https://www.gradually.ai/ki-modelle/kimi-k3.1-pro/"
    },
    {
      "model": "meta-muse-ember-1.0",
      "name": "Muse Ember 1.0",
      "developer": "Meta",
      "rank": 14,
      "score": 110.4,
      "score_lower_95": 102.8,
      "score_upper_95": 118.1,
      "standard_error": 3.9,
      "benchmark_series": 16,
      "profile_url": "https://www.gradually.ai/ki-modelle/meta-muse-ember-1.0/"
    },
    {
      "model": "gpt-6-sol",
      "name": "GPT-6 Sol",
      "developer": "OpenAI",
      "rank": 15,
      "score": 109.1,
      "score_lower_95": 105,
      "score_upper_95": 113.2,
      "standard_error": 2.08,
      "benchmark_series": 40,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-6-sol/"
    },
    {
      "model": "gpt-5.6-sol",
      "name": "GPT-5.6 Sol",
      "developer": "OpenAI",
      "rank": 16,
      "score": 109.1,
      "score_lower_95": 104.9,
      "score_upper_95": 113.2,
      "standard_error": 2.13,
      "benchmark_series": 40,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-5.6-sol/"
    },
    {
      "model": "gemini-3.7-flash",
      "name": "Gemini 3.7 Flash",
      "developer": "Google",
      "rank": 17,
      "score": 107.9,
      "score_lower_95": 103.6,
      "score_upper_95": 112.2,
      "standard_error": 2.21,
      "benchmark_series": 36,
      "profile_url": "https://www.gradually.ai/ki-modelle/gemini-3.7-flash/"
    },
    {
      "model": "meta-muse-spark-1.3",
      "name": "Muse Spark 1.3",
      "developer": "Meta",
      "rank": 18,
      "score": 107.3,
      "score_lower_95": 102.3,
      "score_upper_95": 112.3,
      "standard_error": 2.55,
      "benchmark_series": 35,
      "profile_url": "https://www.gradually.ai/ki-modelle/meta-muse-spark-1.3/"
    },
    {
      "model": "gemini-3.8-flash",
      "name": "Gemini 3.8 Flash",
      "developer": "Google",
      "rank": 19,
      "score": 106.8,
      "score_lower_95": 103.4,
      "score_upper_95": 110.2,
      "standard_error": 1.73,
      "benchmark_series": 59,
      "profile_url": "https://www.gradually.ai/ki-modelle/gemini-3.8-flash/"
    },
    {
      "model": "deepseek-v4.1-flash-1017",
      "name": "DeepSeek V4.1 Flash 1017",
      "developer": "DeepSeek",
      "rank": 20,
      "score": 106.7,
      "score_lower_95": 100.4,
      "score_upper_95": 113,
      "standard_error": 3.21,
      "benchmark_series": 25,
      "profile_url": "https://www.gradually.ai/ki-modelle/deepseek-v4.1-flash-1017/"
    },
    {
      "model": "gpt-6.1-terra",
      "name": "GPT-6.1 Terra",
      "developer": "OpenAI",
      "rank": 21,
      "score": 106.5,
      "score_lower_95": 95.7,
      "score_upper_95": 117.2,
      "standard_error": 5.47,
      "benchmark_series": 19,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-6.1-terra/"
    },
    {
      "model": "grok-4.7",
      "name": "Grok 4.7",
      "developer": "xAI",
      "rank": 22,
      "score": 103.3,
      "score_lower_95": 99.8,
      "score_upper_95": 106.8,
      "standard_error": 1.77,
      "benchmark_series": 50,
      "profile_url": "https://www.gradually.ai/ki-modelle/grok-4.7/"
    },
    {
      "model": "claude-haiku-5.5",
      "name": "Claude Haiku 5.5",
      "developer": "Anthropic",
      "rank": 23,
      "score": 102.8,
      "score_lower_95": 97.2,
      "score_upper_95": 108.3,
      "standard_error": 2.84,
      "benchmark_series": 45,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-haiku-5.5/"
    },
    {
      "model": "grok-4.6",
      "name": "Grok 4.6",
      "developer": "xAI",
      "rank": 24,
      "score": 102.1,
      "score_lower_95": 98.4,
      "score_upper_95": 105.8,
      "standard_error": 1.89,
      "benchmark_series": 49,
      "profile_url": "https://www.gradually.ai/ki-modelle/grok-4.6/"
    },
    {
      "model": "gpt-5.5",
      "name": "GPT-5.5",
      "developer": "OpenAI",
      "rank": 25,
      "score": 101.5,
      "score_lower_95": 94.1,
      "score_upper_95": 109,
      "standard_error": 3.81,
      "benchmark_series": 36,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-5.5/"
    },
    {
      "model": "kimi-k3",
      "name": "Kimi K3",
      "developer": "Moonshot AI",
      "rank": 26,
      "score": 101.1,
      "score_lower_95": 97.2,
      "score_upper_95": 105.1,
      "standard_error": 2.02,
      "benchmark_series": 57,
      "profile_url": "https://www.gradually.ai/ki-modelle/kimi-k3/"
    },
    {
      "model": "gpt-5.6-terra",
      "name": "GPT-5.6 Terra",
      "developer": "OpenAI",
      "rank": 27,
      "score": 100.8,
      "score_lower_95": 96.8,
      "score_upper_95": 104.8,
      "standard_error": 2.05,
      "benchmark_series": 44,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-5.6-terra/"
    },
    {
      "model": "mistral-large-4",
      "name": "Mistral Large 4",
      "developer": "Mistral AI",
      "rank": 28,
      "score": 100.8,
      "score_lower_95": 93.5,
      "score_upper_95": 108.1,
      "standard_error": 3.71,
      "benchmark_series": 17,
      "profile_url": "https://www.gradually.ai/ki-modelle/mistral-large-4/"
    },
    {
      "model": "qwen-3.8-max",
      "name": "Qwen 3.8 Max 0902",
      "developer": "Alibaba",
      "rank": 29,
      "score": 100.8,
      "score_lower_95": 95.5,
      "score_upper_95": 106.1,
      "standard_error": 2.68,
      "benchmark_series": 48,
      "profile_url": "https://www.gradually.ai/ki-modelle/qwen-3.8-max/"
    },
    {
      "model": "glm-5.3",
      "name": "GLM-5.3",
      "developer": "Z.ai",
      "rank": 30,
      "score": 100.6,
      "score_lower_95": 96.2,
      "score_upper_95": 105,
      "standard_error": 2.25,
      "benchmark_series": 52,
      "profile_url": "https://www.gradually.ai/ki-modelle/glm-5.3/"
    },
    {
      "model": "mimo-v2.6-pro",
      "name": "MiMo V2.6 Pro",
      "developer": "Xiaomi",
      "rank": 31,
      "score": 100.4,
      "score_lower_95": 95.1,
      "score_upper_95": 105.7,
      "standard_error": 2.72,
      "benchmark_series": 37,
      "profile_url": "https://www.gradually.ai/ki-modelle/mimo-v2.6-pro/"
    },
    {
      "model": "minimax-m3.1-flash",
      "name": "MiniMax M3.1 Flash",
      "developer": "MiniMax",
      "rank": 32,
      "score": 100,
      "score_lower_95": 93.3,
      "score_upper_95": 106.8,
      "standard_error": 3.45,
      "benchmark_series": 21,
      "profile_url": "https://www.gradually.ai/ki-modelle/minimax-m3.1-flash/"
    },
    {
      "model": "claude-opus-4.8",
      "name": "Claude Opus 4.8",
      "developer": "Anthropic",
      "rank": 33,
      "score": 99.5,
      "score_lower_95": 92.4,
      "score_upper_95": 106.5,
      "standard_error": 3.6,
      "benchmark_series": 27,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-opus-4.8/"
    },
    {
      "model": "deepseek-v4.1-flash",
      "name": "DeepSeek-V4.1-Flash",
      "developer": "DeepSeek",
      "rank": 34,
      "score": 99.5,
      "score_lower_95": 92.8,
      "score_upper_95": 106.1,
      "standard_error": 3.39,
      "benchmark_series": 36,
      "profile_url": "https://www.gradually.ai/ki-modelle/deepseek-v4.1-flash/"
    },
    {
      "model": "gemini-3.5-flash",
      "name": "Gemini 3.5 Flash",
      "developer": "Google",
      "rank": 35,
      "score": 97.8,
      "score_lower_95": 93.4,
      "score_upper_95": 102.3,
      "standard_error": 2.27,
      "benchmark_series": 41,
      "profile_url": "https://www.gradually.ai/ki-modelle/gemini-3.5-flash/"
    },
    {
      "model": "gemini-3.6-flash",
      "name": "Gemini 3.6 Flash",
      "developer": "Google",
      "rank": 36,
      "score": 97.6,
      "score_lower_95": 92.4,
      "score_upper_95": 102.8,
      "standard_error": 2.67,
      "benchmark_series": 34,
      "profile_url": "https://www.gradually.ai/ki-modelle/gemini-3.6-flash/"
    },
    {
      "model": "meta-muse-spark-open",
      "name": "Muse Spark Open",
      "developer": "Meta",
      "rank": 37,
      "score": 97.5,
      "score_lower_95": 90.1,
      "score_upper_95": 105,
      "standard_error": 3.81,
      "benchmark_series": 24,
      "profile_url": "https://www.gradually.ai/ki-modelle/meta-muse-spark-open/"
    },
    {
      "model": "mimo-v2.6-flash",
      "name": "MiMo V2.6 Flash",
      "developer": "Xiaomi",
      "rank": 38,
      "score": 97.3,
      "score_lower_95": 91.9,
      "score_upper_95": 102.6,
      "standard_error": 2.73,
      "benchmark_series": 36,
      "profile_url": "https://www.gradually.ai/ki-modelle/mimo-v2.6-flash/"
    },
    {
      "model": "step-5-preview",
      "name": "Step 5 Preview",
      "developer": "StepFun",
      "rank": 39,
      "score": 97.1,
      "score_lower_95": 91.8,
      "score_upper_95": 102.4,
      "standard_error": 2.71,
      "benchmark_series": 34,
      "profile_url": "https://www.gradually.ai/ki-modelle/step-5-preview/"
    },
    {
      "model": "gpt-6-luna",
      "name": "GPT-6 Luna",
      "developer": "OpenAI",
      "rank": 40,
      "score": 95.8,
      "score_lower_95": 92.3,
      "score_upper_95": 99.3,
      "standard_error": 1.77,
      "benchmark_series": 48,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-6-luna/"
    },
    {
      "model": "claude-opus-4.7",
      "name": "Claude Opus 4.7",
      "developer": "Anthropic",
      "rank": 41,
      "score": 95.1,
      "score_lower_95": 87.5,
      "score_upper_95": 102.7,
      "standard_error": 3.86,
      "benchmark_series": 27,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-opus-4.7/"
    },
    {
      "model": "grok-4.5",
      "name": "Grok 4.5",
      "developer": "xAI",
      "rank": 42,
      "score": 94.8,
      "score_lower_95": 89.3,
      "score_upper_95": 100.4,
      "standard_error": 2.81,
      "benchmark_series": 37,
      "profile_url": "https://www.gradually.ai/ki-modelle/grok-4.5/"
    },
    {
      "model": "glm-5.3-flash",
      "name": "GLM-5.3-Flash",
      "developer": "Z.ai",
      "rank": 43,
      "score": 94.3,
      "score_lower_95": 90.1,
      "score_upper_95": 98.5,
      "standard_error": 2.15,
      "benchmark_series": 50,
      "profile_url": "https://www.gradually.ai/ki-modelle/glm-5.3-flash/"
    },
    {
      "model": "gpt-5.6-luna",
      "name": "GPT-5.6 Luna",
      "developer": "OpenAI",
      "rank": 44,
      "score": 93.8,
      "score_lower_95": 89.4,
      "score_upper_95": 98.3,
      "standard_error": 2.26,
      "benchmark_series": 44,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-5.6-luna/"
    },
    {
      "model": "claude-sonnet-5",
      "name": "Claude Sonnet 5",
      "developer": "Anthropic",
      "rank": 45,
      "score": 92.1,
      "score_lower_95": 87.1,
      "score_upper_95": 97.1,
      "standard_error": 2.55,
      "benchmark_series": 39,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-sonnet-5/"
    },
    {
      "model": "gemini-3.1-pro",
      "name": "Gemini 3.1 Pro Preview",
      "developer": "Google",
      "rank": 46,
      "score": 91.4,
      "score_lower_95": 85.7,
      "score_upper_95": 97.1,
      "standard_error": 2.9,
      "benchmark_series": 49,
      "profile_url": "https://www.gradually.ai/ki-modelle/gemini-3.1-pro/"
    },
    {
      "model": "glm-5.2",
      "name": "GLM-5.2",
      "developer": "Z.ai",
      "rank": 47,
      "score": 89,
      "score_lower_95": 83.6,
      "score_upper_95": 94.4,
      "standard_error": 2.74,
      "benchmark_series": 29,
      "profile_url": "https://www.gradually.ai/ki-modelle/glm-5.2/"
    },
    {
      "model": "deepseek-v4-pro",
      "name": "DeepSeek-V4-Pro",
      "developer": "DeepSeek",
      "rank": 48,
      "score": 87.2,
      "score_lower_95": 81.4,
      "score_upper_95": 92.9,
      "standard_error": 2.93,
      "benchmark_series": 37,
      "profile_url": "https://www.gradually.ai/ki-modelle/deepseek-v4-pro/"
    },
    {
      "model": "claude-sonnet-4.6",
      "name": "Claude Sonnet 4.6",
      "developer": "Anthropic",
      "rank": 49,
      "score": 86.7,
      "score_lower_95": 79.7,
      "score_upper_95": 93.7,
      "standard_error": 3.56,
      "benchmark_series": 28,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-sonnet-4.6/"
    },
    {
      "model": "gpt-5.4",
      "name": "GPT-5.4",
      "developer": "OpenAI",
      "rank": 50,
      "score": 86.5,
      "score_lower_95": 80.3,
      "score_upper_95": 92.7,
      "standard_error": 3.17,
      "benchmark_series": 27,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-5.4/"
    },
    {
      "model": "qwen-3.7-max",
      "name": "Qwen 3.7 Max",
      "developer": "Alibaba",
      "rank": 51,
      "score": 85.4,
      "score_lower_95": 77.4,
      "score_upper_95": 93.5,
      "standard_error": 4.11,
      "benchmark_series": 19,
      "profile_url": "https://www.gradually.ai/ki-modelle/qwen-3.7-max/"
    },
    {
      "model": "kimi-k2.6",
      "name": "Kimi K2.6",
      "developer": "Moonshot AI",
      "rank": 52,
      "score": 84.9,
      "score_lower_95": 78.9,
      "score_upper_95": 90.9,
      "standard_error": 3.07,
      "benchmark_series": 26,
      "profile_url": "https://www.gradually.ai/ki-modelle/kimi-k2.6/"
    },
    {
      "model": "claude-opus-4.6",
      "name": "Claude Opus 4.6",
      "developer": "Anthropic",
      "rank": 53,
      "score": 84.2,
      "score_lower_95": 71.7,
      "score_upper_95": 96.7,
      "standard_error": 6.38,
      "benchmark_series": 14,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-opus-4.6/"
    },
    {
      "model": "qwen-3.7-plus",
      "name": "Qwen 3.7 Plus",
      "developer": "Alibaba",
      "rank": 54,
      "score": 83.4,
      "score_lower_95": 72.9,
      "score_upper_95": 93.9,
      "standard_error": 5.36,
      "benchmark_series": 13,
      "profile_url": "https://www.gradually.ai/ki-modelle/qwen-3.7-plus/"
    },
    {
      "model": "minimax-m3",
      "name": "MiniMax M3",
      "developer": "MiniMax",
      "rank": 55,
      "score": 83,
      "score_lower_95": 78,
      "score_upper_95": 88,
      "standard_error": 2.56,
      "benchmark_series": 47,
      "profile_url": "https://www.gradually.ai/ki-modelle/minimax-m3/"
    },
    {
      "model": "glm-5.1",
      "name": "GLM-5.1",
      "developer": "Z.ai",
      "rank": 56,
      "score": 82.8,
      "score_lower_95": 76,
      "score_upper_95": 89.6,
      "standard_error": 3.47,
      "benchmark_series": 19,
      "profile_url": "https://www.gradually.ai/ki-modelle/glm-5.1/"
    },
    {
      "model": "qwen-3.8-27b",
      "name": "Qwen 3.8 27B",
      "developer": "Alibaba",
      "rank": 57,
      "score": 82.8,
      "score_lower_95": 76.2,
      "score_upper_95": 89.3,
      "standard_error": 3.36,
      "benchmark_series": 34,
      "profile_url": "https://www.gradually.ai/ki-modelle/qwen-3.8-27b/"
    },
    {
      "model": "reflection-beam",
      "name": "Reflection Beam",
      "developer": "Reflection AI",
      "rank": 58,
      "score": 82.4,
      "score_lower_95": 74.9,
      "score_upper_95": 90,
      "standard_error": 3.85,
      "benchmark_series": 24,
      "profile_url": "https://www.gradually.ai/ki-modelle/reflection-beam/"
    },
    {
      "model": "kimi-k2.7-code",
      "name": "Kimi K2.7 Code",
      "developer": "Moonshot AI",
      "rank": 59,
      "score": 81.3,
      "score_lower_95": 70.6,
      "score_upper_95": 92,
      "standard_error": 5.48,
      "benchmark_series": 9,
      "profile_url": "https://www.gradually.ai/ki-modelle/kimi-k2.7-code/"
    },
    {
      "model": "gemini-3-flash",
      "name": "Gemini 3 Flash Preview",
      "developer": "Google",
      "rank": 60,
      "score": 81,
      "score_lower_95": 71.2,
      "score_upper_95": 90.9,
      "standard_error": 5.02,
      "benchmark_series": 22,
      "profile_url": "https://www.gradually.ai/ki-modelle/gemini-3-flash/"
    },
    {
      "model": "gpt-5",
      "name": "GPT-5",
      "developer": "OpenAI",
      "rank": 61,
      "score": 77.5,
      "score_lower_95": 69.7,
      "score_upper_95": 85.4,
      "standard_error": 3.99,
      "benchmark_series": 35,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-5/"
    },
    {
      "model": "gpt-5.4-mini",
      "name": "GPT-5.4 mini",
      "developer": "OpenAI",
      "rank": 62,
      "score": 75.1,
      "score_lower_95": 68.6,
      "score_upper_95": 81.7,
      "standard_error": 3.33,
      "benchmark_series": 25,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-5.4-mini/"
    },
    {
      "model": "claude-opus-4.5",
      "name": "Claude Opus 4.5",
      "developer": "Anthropic",
      "rank": 63,
      "score": 74.4,
      "score_lower_95": 63.5,
      "score_upper_95": 85.3,
      "standard_error": 5.57,
      "benchmark_series": 18,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-opus-4.5/"
    },
    {
      "model": "o3",
      "name": "o3",
      "developer": "OpenAI",
      "rank": 64,
      "score": 74.2,
      "score_lower_95": 65.5,
      "score_upper_95": 83,
      "standard_error": 4.46,
      "benchmark_series": 28,
      "profile_url": "https://www.gradually.ai/ki-modelle/o3/"
    },
    {
      "model": "gemini-3.5-flash-lite",
      "name": "Gemini 3.5 Flash-Lite",
      "developer": "Google",
      "rank": 65,
      "score": 73.7,
      "score_lower_95": 67.5,
      "score_upper_95": 79.9,
      "standard_error": 3.16,
      "benchmark_series": 36,
      "profile_url": "https://www.gradually.ai/ki-modelle/gemini-3.5-flash-lite/"
    },
    {
      "model": "mimo-v2.5-pro",
      "name": "MiMo-V2.5-Pro",
      "developer": "Xiaomi",
      "rank": 66,
      "score": 73,
      "score_lower_95": 64.2,
      "score_upper_95": 81.8,
      "standard_error": 4.48,
      "benchmark_series": 23,
      "profile_url": "https://www.gradually.ai/ki-modelle/mimo-v2.5-pro/"
    },
    {
      "model": "glm-5",
      "name": "GLM-5",
      "developer": "Z.ai",
      "rank": 67,
      "score": 72.7,
      "score_lower_95": 65.1,
      "score_upper_95": 80.2,
      "standard_error": 3.87,
      "benchmark_series": 12,
      "profile_url": "https://www.gradually.ai/ki-modelle/glm-5/"
    },
    {
      "model": "inkling",
      "name": "Inkling",
      "developer": "Thinking Machines Lab",
      "rank": 68,
      "score": 72.1,
      "score_lower_95": 65.7,
      "score_upper_95": 78.4,
      "standard_error": 3.24,
      "benchmark_series": 45,
      "profile_url": "https://www.gradually.ai/ki-modelle/inkling/"
    },
    {
      "model": "grok-4.3",
      "name": "Grok 4.3",
      "developer": "xAI",
      "rank": 69,
      "score": 71.6,
      "score_lower_95": 63.8,
      "score_upper_95": 79.4,
      "standard_error": 3.99,
      "benchmark_series": 30,
      "profile_url": "https://www.gradually.ai/ki-modelle/grok-4.3/"
    },
    {
      "model": "kimi-k2.5",
      "name": "Kimi K2.5",
      "developer": "Moonshot AI",
      "rank": 70,
      "score": 70.3,
      "score_lower_95": 61.9,
      "score_upper_95": 78.8,
      "standard_error": 4.31,
      "benchmark_series": 18,
      "profile_url": "https://www.gradually.ai/ki-modelle/kimi-k2.5/"
    },
    {
      "model": "mimo-v2.5",
      "name": "MiMo-V2.5",
      "developer": "Xiaomi",
      "rank": 71,
      "score": 69.1,
      "score_lower_95": 63.3,
      "score_upper_95": 74.9,
      "standard_error": 2.97,
      "benchmark_series": 24,
      "profile_url": "https://www.gradually.ai/ki-modelle/mimo-v2.5/"
    },
    {
      "model": "inkling-small",
      "name": "Inkling Small",
      "developer": "Thinking Machines Lab",
      "rank": 72,
      "score": 68.7,
      "score_lower_95": 62.7,
      "score_upper_95": 74.7,
      "standard_error": 3.05,
      "benchmark_series": 43,
      "profile_url": "https://www.gradually.ai/ki-modelle/inkling-small/"
    },
    {
      "model": "nvidia-nemotron-3.5-super-vl-120b-a12b",
      "name": "Nemotron 3.5 Super VL 120B A12B",
      "developer": "NVIDIA",
      "rank": 73,
      "score": 68.1,
      "score_lower_95": 59.3,
      "score_upper_95": 76.8,
      "standard_error": 4.47,
      "benchmark_series": 19,
      "profile_url": "https://www.gradually.ai/ki-modelle/nvidia-nemotron-3.5-super-vl-120b-a12b/"
    },
    {
      "model": "nemotron-3-ultra",
      "name": "Nemotron 3 Ultra",
      "developer": "NVIDIA",
      "rank": 74,
      "score": 66.8,
      "score_lower_95": 58.4,
      "score_upper_95": 75.3,
      "standard_error": 4.31,
      "benchmark_series": 27,
      "profile_url": "https://www.gradually.ai/ki-modelle/nemotron-3-ultra/"
    },
    {
      "model": "claude-sonnet-4.5",
      "name": "Claude Sonnet 4.5",
      "developer": "Anthropic",
      "rank": 75,
      "score": 65.9,
      "score_lower_95": 52.9,
      "score_upper_95": 78.9,
      "standard_error": 6.63,
      "benchmark_series": 9,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-sonnet-4.5/"
    },
    {
      "model": "gpt-5-mini",
      "name": "GPT-5 mini",
      "developer": "OpenAI",
      "rank": 76,
      "score": 65.8,
      "score_lower_95": 56.3,
      "score_upper_95": 75.3,
      "standard_error": 4.87,
      "benchmark_series": 21,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-5-mini/"
    },
    {
      "model": "minimax-m2.7",
      "name": "MiniMax M2.7",
      "developer": "MiniMax",
      "rank": 77,
      "score": 65.1,
      "score_lower_95": 57.4,
      "score_upper_95": 72.8,
      "standard_error": 3.93,
      "benchmark_series": 23,
      "profile_url": "https://www.gradually.ai/ki-modelle/minimax-m2.7/"
    },
    {
      "model": "gpt-5.4-nano",
      "name": "GPT-5.4 nano",
      "developer": "OpenAI",
      "rank": 78,
      "score": 64,
      "score_lower_95": 55.4,
      "score_upper_95": 72.5,
      "standard_error": 4.35,
      "benchmark_series": 24,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-5.4-nano/"
    },
    {
      "model": "o4-mini",
      "name": "o4-mini",
      "developer": "OpenAI",
      "rank": 79,
      "score": 63.5,
      "score_lower_95": 55.6,
      "score_upper_95": 71.3,
      "standard_error": 4.01,
      "benchmark_series": 25,
      "profile_url": "https://www.gradually.ai/ki-modelle/o4-mini/"
    },
    {
      "model": "minimax-m2.5",
      "name": "MiniMax M2.5",
      "developer": "MiniMax",
      "rank": 80,
      "score": 61.5,
      "score_lower_95": 52.3,
      "score_upper_95": 70.7,
      "standard_error": 4.71,
      "benchmark_series": 12,
      "profile_url": "https://www.gradually.ai/ki-modelle/minimax-m2.5/"
    },
    {
      "model": "gemini-2.5-pro",
      "name": "Gemini 2.5 Pro",
      "developer": "Google",
      "rank": 81,
      "score": 61.4,
      "score_lower_95": 48.1,
      "score_upper_95": 74.7,
      "standard_error": 6.79,
      "benchmark_series": 21,
      "profile_url": "https://www.gradually.ai/ki-modelle/gemini-2.5-pro/"
    },
    {
      "model": "grok-4.20-reasoning",
      "name": "Grok 4.20 Reasoning",
      "developer": "xAI",
      "rank": 82,
      "score": 58.3,
      "score_lower_95": 44.3,
      "score_upper_95": 72.3,
      "standard_error": 7.14,
      "benchmark_series": 20,
      "profile_url": "https://www.gradually.ai/ki-modelle/grok-4.20-reasoning/"
    },
    {
      "model": "minimax-m2.1",
      "name": "MiniMax M2.1",
      "developer": "MiniMax",
      "rank": 83,
      "score": 57.3,
      "score_lower_95": 43.6,
      "score_upper_95": 71.1,
      "standard_error": 7.01,
      "benchmark_series": 13,
      "profile_url": "https://www.gradually.ai/ki-modelle/minimax-m2.1/"
    },
    {
      "model": "gemini-3.1-flash-lite",
      "name": "Gemini 3.1 Flash-Lite",
      "developer": "Google",
      "rank": 84,
      "score": 55.9,
      "score_lower_95": 45.3,
      "score_upper_95": 66.5,
      "standard_error": 5.42,
      "benchmark_series": 15,
      "profile_url": "https://www.gradually.ai/ki-modelle/gemini-3.1-flash-lite/"
    },
    {
      "model": "claude-haiku-4.5",
      "name": "Claude Haiku 4.5",
      "developer": "Anthropic",
      "rank": 85,
      "score": 54.1,
      "score_lower_95": 43,
      "score_upper_95": 65.2,
      "standard_error": 5.67,
      "benchmark_series": 14,
      "profile_url": "https://www.gradually.ai/ki-modelle/claude-haiku-4.5/"
    },
    {
      "model": "kimi-k2-thinking",
      "name": "Kimi K2 Thinking",
      "developer": "Moonshot AI",
      "rank": 86,
      "score": 53.2,
      "score_lower_95": 42.8,
      "score_upper_95": 63.5,
      "standard_error": 5.28,
      "benchmark_series": 11,
      "profile_url": "https://www.gradually.ai/ki-modelle/kimi-k2-thinking/"
    },
    {
      "model": "glm-4.5",
      "name": "GLM-4.5",
      "developer": "Z.ai",
      "rank": 87,
      "score": 48.8,
      "score_lower_95": 36.6,
      "score_upper_95": 61,
      "standard_error": 6.24,
      "benchmark_series": 11,
      "profile_url": "https://www.gradually.ai/ki-modelle/glm-4.5/"
    },
    {
      "model": "mistral-medium-3",
      "name": "Mistral Medium 3.5",
      "developer": "Mistral AI",
      "rank": 88,
      "score": 46.3,
      "score_lower_95": 40.9,
      "score_upper_95": 51.6,
      "standard_error": 2.73,
      "benchmark_series": 32,
      "profile_url": "https://www.gradually.ai/ki-modelle/mistral-medium-3/"
    },
    {
      "model": "glm-4.6",
      "name": "GLM-4.6",
      "developer": "Z.ai",
      "rank": 89,
      "score": 45.9,
      "score_lower_95": 33.2,
      "score_upper_95": 58.7,
      "standard_error": 6.49,
      "benchmark_series": 13,
      "profile_url": "https://www.gradually.ai/ki-modelle/glm-4.6/"
    },
    {
      "model": "mercury-2.5",
      "name": "Mercury 2.5",
      "developer": "Inception",
      "rank": 90,
      "score": 45.3,
      "score_lower_95": 32.3,
      "score_upper_95": 58.3,
      "standard_error": 6.63,
      "benchmark_series": 17,
      "profile_url": "https://www.gradually.ai/ki-modelle/mercury-2.5/"
    },
    {
      "model": "deepseek-r1",
      "name": "DeepSeek-R1",
      "developer": "DeepSeek",
      "rank": 91,
      "score": 44.5,
      "score_lower_95": 30.2,
      "score_upper_95": 58.8,
      "standard_error": 7.29,
      "benchmark_series": 13,
      "profile_url": "https://www.gradually.ai/ki-modelle/deepseek-r1/"
    },
    {
      "model": "gpt-4.1",
      "name": "GPT-4.1",
      "developer": "OpenAI",
      "rank": 92,
      "score": 43.6,
      "score_lower_95": 31.1,
      "score_upper_95": 56.1,
      "standard_error": 6.38,
      "benchmark_series": 24,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-4.1/"
    },
    {
      "model": "gpt-oss-120b",
      "name": "GPT OSS 120B",
      "developer": "OpenAI",
      "rank": 93,
      "score": 43.4,
      "score_lower_95": 32.7,
      "score_upper_95": 54.1,
      "standard_error": 5.45,
      "benchmark_series": 26,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-oss-120b/"
    },
    {
      "model": "mistral-large-3",
      "name": "Mistral Large 3",
      "developer": "Mistral AI",
      "rank": 94,
      "score": 32.7,
      "score_lower_95": 19.5,
      "score_upper_95": 45.8,
      "standard_error": 6.71,
      "benchmark_series": 17,
      "profile_url": "https://www.gradually.ai/ki-modelle/mistral-large-3/"
    },
    {
      "model": "glm-4.7",
      "name": "GLM-4.7",
      "developer": "Z.ai",
      "rank": null,
      "score": 56.2,
      "score_lower_95": 41.3,
      "score_upper_95": 71.2,
      "standard_error": 7.63,
      "benchmark_series": 14,
      "profile_url": "https://www.gradually.ai/ki-modelle/glm-4.7/"
    },
    {
      "model": "o1",
      "name": "o1",
      "developer": "OpenAI",
      "rank": null,
      "score": 49.2,
      "score_lower_95": 32.9,
      "score_upper_95": 65.5,
      "standard_error": 8.32,
      "benchmark_series": 12,
      "profile_url": "https://www.gradually.ai/ki-modelle/o1/"
    },
    {
      "model": "deepseek-v3.2",
      "name": "DeepSeek-V3.2",
      "developer": "DeepSeek",
      "rank": null,
      "score": 48.5,
      "score_lower_95": 32,
      "score_upper_95": 65.1,
      "standard_error": 8.45,
      "benchmark_series": 11,
      "profile_url": "https://www.gradually.ai/ki-modelle/deepseek-v3.2/"
    },
    {
      "model": "ling-3.0-flash",
      "name": "Ling 3.0 Flash",
      "developer": "inclusionAI",
      "rank": null,
      "score": 47.9,
      "score_lower_95": 31.2,
      "score_upper_95": 64.7,
      "standard_error": 8.55,
      "benchmark_series": 17,
      "profile_url": "https://www.gradually.ai/ki-modelle/ling-3.0-flash/"
    },
    {
      "model": "o3-mini",
      "name": "o3-mini",
      "developer": "OpenAI",
      "rank": null,
      "score": 41.9,
      "score_lower_95": 23.9,
      "score_upper_95": 59.8,
      "standard_error": 9.14,
      "benchmark_series": 11,
      "profile_url": "https://www.gradually.ai/ki-modelle/o3-mini/"
    },
    {
      "model": "deepseek-v3-0324",
      "name": "DeepSeek-V3 0324",
      "developer": "DeepSeek",
      "rank": null,
      "score": 33.6,
      "score_lower_95": 18.2,
      "score_upper_95": 49.1,
      "standard_error": 7.89,
      "benchmark_series": 11,
      "profile_url": "https://www.gradually.ai/ki-modelle/deepseek-v3-0324/"
    },
    {
      "model": "gpt-5-nano",
      "name": "GPT-5 nano",
      "developer": "OpenAI",
      "rank": null,
      "score": 32.4,
      "score_lower_95": 15.9,
      "score_upper_95": 49,
      "standard_error": 8.46,
      "benchmark_series": 16,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-5-nano/"
    },
    {
      "model": "gpt-4.1-mini",
      "name": "GPT-4.1 mini",
      "developer": "OpenAI",
      "rank": null,
      "score": 32.3,
      "score_lower_95": 17.1,
      "score_upper_95": 47.5,
      "standard_error": 7.77,
      "benchmark_series": 15,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-4.1-mini/"
    },
    {
      "model": "nemotron-3.5-lightning",
      "name": "Nemotron 3.5 Lightning",
      "developer": "NVIDIA",
      "rank": null,
      "score": 31.1,
      "score_lower_95": 13.2,
      "score_upper_95": 49,
      "standard_error": 9.14,
      "benchmark_series": 22,
      "profile_url": "https://www.gradually.ai/ki-modelle/nemotron-3.5-lightning/"
    },
    {
      "model": "gpt-oss-20b",
      "name": "GPT OSS 20B",
      "developer": "OpenAI",
      "rank": null,
      "score": 30.9,
      "score_lower_95": 14.5,
      "score_upper_95": 47.2,
      "standard_error": 8.34,
      "benchmark_series": 13,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-oss-20b/"
    },
    {
      "model": "cohere-command-a-plus-05-2026",
      "name": "Command A Plus",
      "developer": "Cohere",
      "rank": null,
      "score": 30.7,
      "score_lower_95": 13.5,
      "score_upper_95": 47.9,
      "standard_error": 8.76,
      "benchmark_series": 17,
      "profile_url": "https://www.gradually.ai/ki-modelle/cohere-command-a-plus-05-2026/"
    },
    {
      "model": "mistral-small-4",
      "name": "Mistral Small 4",
      "developer": "Mistral AI",
      "rank": null,
      "score": 23.3,
      "score_lower_95": 7.1,
      "score_upper_95": 39.6,
      "standard_error": 8.29,
      "benchmark_series": 13,
      "profile_url": "https://www.gradually.ai/ki-modelle/mistral-small-4/"
    },
    {
      "model": "deepseek-v3",
      "name": "DeepSeek-V3",
      "developer": "DeepSeek",
      "rank": null,
      "score": 19.7,
      "score_lower_95": 0.8,
      "score_upper_95": 38.6,
      "standard_error": 9.64,
      "benchmark_series": 16,
      "profile_url": "https://www.gradually.ai/ki-modelle/deepseek-v3/"
    },
    {
      "model": "mistral-magistral-small-2509",
      "name": "Magistral Small 1.2",
      "developer": "Mistral AI",
      "rank": null,
      "score": 8,
      "score_lower_95": -15.3,
      "score_upper_95": 31.3,
      "standard_error": 11.9,
      "benchmark_series": 13,
      "profile_url": "https://www.gradually.ai/ki-modelle/mistral-magistral-small-2509/"
    },
    {
      "model": "llama-4-maverick",
      "name": "Llama 4 Maverick",
      "developer": "Meta",
      "rank": null,
      "score": 5.1,
      "score_lower_95": -15.4,
      "score_upper_95": 25.7,
      "standard_error": 10.49,
      "benchmark_series": 9,
      "profile_url": "https://www.gradually.ai/ki-modelle/llama-4-maverick/"
    },
    {
      "model": "llama-4-scout",
      "name": "Llama 4 Scout",
      "developer": "Meta",
      "rank": null,
      "score": 4.7,
      "score_lower_95": -12.1,
      "score_upper_95": 21.4,
      "standard_error": 8.54,
      "benchmark_series": 17,
      "profile_url": "https://www.gradually.ai/ki-modelle/llama-4-scout/"
    },
    {
      "model": "command-a",
      "name": "Command A",
      "developer": "Cohere",
      "rank": null,
      "score": 0.4,
      "score_lower_95": -22,
      "score_upper_95": 22.9,
      "standard_error": 11.47,
      "benchmark_series": 11,
      "profile_url": "https://www.gradually.ai/ki-modelle/command-a/"
    },
    {
      "model": "mistral-small-3.1",
      "name": "Mistral Small 3.1",
      "developer": "Mistral AI",
      "rank": null,
      "score": -3,
      "score_lower_95": -25.6,
      "score_upper_95": 19.7,
      "standard_error": 11.54,
      "benchmark_series": 13,
      "profile_url": "https://www.gradually.ai/ki-modelle/mistral-small-3.1/"
    },
    {
      "model": "gpt-4o-mini",
      "name": "GPT-4o mini",
      "developer": "OpenAI",
      "rank": null,
      "score": -7.3,
      "score_lower_95": -29.1,
      "score_upper_95": 14.4,
      "standard_error": 11.08,
      "benchmark_series": 15,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-4o-mini/"
    },
    {
      "model": "gpt-4.1-nano",
      "name": "GPT-4.1 nano",
      "developer": "OpenAI",
      "rank": null,
      "score": -15.8,
      "score_lower_95": -38.9,
      "score_upper_95": 7.3,
      "standard_error": 11.8,
      "benchmark_series": 15,
      "profile_url": "https://www.gradually.ai/ki-modelle/gpt-4.1-nano/"
    }
  ]
}