Das umfassende KI Ranking
KI Ranking
Welches KI-Modell ist wirklich das Beste?
Wir haben die Antwort. Unser KI Weekly Score vereint die wichtigsten Benchmarks und weitere Quellen zu einem aussagekräftigen Gesamtranking.
Features | Intelligence | Preis | Speed | Latency | ||
|---|---|---|---|---|---|---|
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Anthropic | 1.000.000 | 60 | 20,00 $ | 0 | 0,00 |
Claude Opus 4.8 (Adaptive Reasoning, Max Effort) Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | Anthropic | 1.000.000 | 56 | 10,00 $ | 64 | 35,37 |
GPT-5.5 (xhigh) GPT-5.5 (xhigh) | OpenAI | 922.000 | 55 | 11,25 $ | 61 | 118,46 |
Claude Opus 4.7 (Adaptive Reasoning, Max Effort) Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | Anthropic | 1.000.000 | 54 | 10,00 $ | 50 | 18,45 |
GPT-5.5 (high) GPT-5.5 (high) | OpenAI | 922.000 | 53 | 11,25 $ | 54 | 58,08 |
GPT-5.4 (xhigh) GPT-5.4 (xhigh) | OpenAI | 1.050.000 | 51 | 5,63 $ | 147 | 126,87 |
Gemini 3.5 Flash (high) Gemini 3.5 Flash (high) | Google | 1.000.000 | 50 | 3,38 $ | 155 | 18,79 |
Claude Sonnet 4.6 (max) Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 1.000.000 | 47 | 6,00 $ | 50 | 120,26 |
GPT-5.5 (medium) GPT-5.5 (medium) | OpenAI | 922.000 | 47 | 11,25 $ | 54 | 10,24 |
Gemini 3.1 Pro Preview Gemini 3.1 Pro Preview | Google | 1.000.000 | 46 | 4,50 $ | 122 | 20,61 |
Qwen3.7 Max Qwen3.7 Max | Alibaba | 1.000.000 | 46 | 3,75 $ | 114 | 23,82 |
Gemini 3.5 Flash (medium) Gemini 3.5 Flash (medium) | Google | 1.000.000 | 45 | 3,38 $ | 157 | 16,51 |
MiniMax-M3 MiniMax-M3 | MiniMax | 1.000.000 | 44 | 0,53 $ | 62 | 35,26 |
DeepSeek V4 Pro (Reasoning, Max Effort) DeepSeek V4 Pro (Reasoning, Max Effort) | DeepSeek | 1.000.000 | 44 | 0,54 $ | 67 | 67,32 |
GPT-5.3 Codex (xhigh) GPT-5.3 Codex (xhigh) | OpenAI | 400.000 | 44 | 4,81 $ | 79 | 109,09 |
Claude Opus 4.6 (max) Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 1.000.000 | 44 | 10,00 $ | 43 | 21,16 |
Muse Spark Muse Spark | Meta | 262.144 | 43 | 0,00 $ | 0 | 0,00 |
Kimi K2.6 Kimi K2.6 | Kimi | 256.000 | 43 | 1,71 $ | 46 | 99,62 |
Claude Opus 4.7 (Non-reasoning, High Effort) Claude Opus 4.7 (Non-reasoning, High Effort) | Anthropic | 1.000.000 | 43 | 10,00 $ | 45 | 1,39 |
MiMo-V2.5-Pro MiMo-V2.5-Pro | Xiaomi | 1.000.000 | 42 | 0,54 $ | 34 | 61,66 |
GPT-5.2 (xhigh) GPT-5.2 (xhigh) | OpenAI | 400.000 | 42 | 4,81 $ | 75 | 155,77 |
Kimi K2.7 Code Kimi K2.7 Code | Kimi | 256.000 | 42 | 1,71 $ | 48 | 44,27 |
GPT-5.5 (low) GPT-5.5 (low) | OpenAI | 922.000 | 42 | 11,25 $ | 55 | 1,86 |
DeepSeek V4 Pro (Reasoning, High Effort) DeepSeek V4 Pro (Reasoning, High Effort) | DeepSeek | 1.000.000 | 41 | 0,54 $ | 70 | 30,42 |
Claude Opus 4.5 (Reasoning) Claude Opus 4.5 (Reasoning) | Anthropic | 200.000 | 41 | 10,00 $ | 49 | 15,35 |
540 Modelle