LLM-Bestenliste – Vergleich von KI-Modellen von OpenAI, Anthropic, Google, SpaceXAI und weiteren Anbietern
Vergleich und Rangliste der Leistung von über 250 KI-Modellen (LLMs) anhand zentraler Metriken wie Intelligenz, Preis, Leistung und Geschwindigkeit (Ausgabegeschwindigkeit in Tokens pro Sekunde und Latenz als TTFT), Kontextfenster und weiteren Kriterien.
Weitere Details, auch zu unserer Methodik, finden Sie in unseren FAQs.
Intelligenz
UpdatedClaude Fable 5.1 (max with fallback) und Claude Fable 5.1 (xhigh with fallback) weisen die höchste Intelligenz auf, gefolgt von GPT-6 Astra (max) und GPT-6 Astra (xhigh).
Ausgabegeschwindigkeit
Celeris-1 und Mercury 2 sind die schnellsten Modelle, gefolgt von Gemini 2.5 Flash-Lite und Gemini 3.5 Flash-Lite.
Latenz
Gemini 2.5 Flash-Lite (Non-reasoning) und Command A+ weisen die niedrigsten Latenzwerte auf, gefolgt von North Mini Code und Gemini 2.5 Flash (Non-reasoning).
Kosten pro Aufgabe
Granite 4.2 3B und GPT-5.6 Luna (low) haben die niedrigsten Kosten pro Aufgabe, gefolgt von GPT-5.6 Luna (Non-reasoning) und gpt-oss-20b (high).
Kontextfenster
Llama 4 Scout und Grok 4.20 0309 unterstützen die größten Kontextfenster, gefolgt von Gemini 1.5 Pro (May) und Grok 4.1 Fast.
Weitere Analyse | ||||||||
|---|---|---|---|---|---|---|---|---|
Claude Fable 5.1 (max with fallback) | 1M | Anthropic | 53 | $7.63 | 64 | 209.82 | 217.61 | |
Claude Fable 5.1 (xhigh with fallback) | 1M | Anthropic | 53 | $5.98 | 58 | 91.63 | 100.23 | |
GPT-6 Astra (max) | 1M | OpenAI | 53 | $3.26 | 53 | 336.77 | 346.22 | |
GPT-6 Astra (xhigh) | 1M | OpenAI | 53 | $2.31 | 51 | 120.43 | 130.26 | |
Claude Fable 5.1 (high with fallback) | 1M | Anthropic | 51 | $3.91 | 53 | 12.01 | 21.39 | |
GPT-6 Astra (high) | 1M | OpenAI | 51 | $1.72 | 51 | 37.22 | 46.96 | |
Claude Opus 5 (max) | 1M | Anthropic | 51 | $5.86 | 50 | 45.32 | 55.29 | |
Claude Fable 5 (with fallback) | 1M | Anthropic | 50 | $8.75 | 66 | 96.09 | 103.72 | |
GPT-6 Astra (medium) | 1M | OpenAI | 50 | $1.54 | 49 | 4.27 | 14.38 | |
Claude Opus 5 (xhigh) | 1M | Anthropic | 50 | $4.88 | 52 | 22.27 | 31.89 | |
Claude Fable 5.1 (medium with fallback) | 1M | Anthropic | 49 | $2.98 | 52 | 5.99 | 15.61 | |
Claude Opus 5 (high) | 1M | Anthropic | 48 | $3.61 | 51 | 12.18 | 21.91 | |
Muse Spark 1.3 (max) | 1M | Meta | 48 | $1.60 | 226 | 27.01 | 38.08 | |
GPT-5.6 Sol (max) | 1M | OpenAI | 47 | $1.99 | 66 | 99.25 | 106.77 | |
Claude Fable 5.1 (low with fallback) | 1M | Anthropic | 47 | $2.37 | 51 | 5.29 | 15.02 | |
GPT-6 Astra (low) | 1M | OpenAI | 46 | $0.82 | 51 | 2.82 | 12.69 | |
Qwen3.8 Max (0902) | 984k |  Alibaba | 45 | $5.41 | 41 | 2.78 | 63.54 | |
Muse Spark 1.3 (xhigh) | 1M | Meta | 45 | $1.37 | 232 | 22.56 | 33.35 | |
Claude Opus 5 (medium) | 1M | Anthropic | 45 | $2.19 | 49 | 5.24 | 15.35 | |
GLM-5.3 (max) | 1M |  Z AI | 45 | $2.01 | 67 | 3.00 | 40.55 | |
Grok 4.6 (high) | 500k | SpaceXAI | 44 | $1.86 | 60 | 38.63 | 47.03 | |
Grok 4.6 (xhigh) | 500k | SpaceXAI | 44 | $2.32 | 57 | 25.40 | 34.11 | |
GPT-5.6 Sol (xhigh) | 1M | OpenAI | 44 | $1.18 | 65 | 36.09 | 43.80 | |
Kimi K3 (max) | 1.05M |  Kimi | 44 | $2.00 | 36 | 4.57 | 73.26 | |
Grok 4.6 (medium) | 500k | SpaceXAI | 43 | $1.50 | 55 | 30.25 | 39.35 | |
GPT-5.6 Sol (high) | 1M | OpenAI | 42 | $0.81 | 58 | 9.67 | 18.29 | |
GPT-5.6 Terra (max) | 1M | OpenAI | 42 | $1.40 | 95 | 139.76 | 145.01 | |
GLM-5.3-Flash | 1M | Z AI | 42 | $0.25 | 116 | 2.26 | 23.78 | |
Gemini 3.8 Flash (high) | 1M | Google | 41 | $1.24 | 339 | 15.57 | 17.04 | |
Qwen3.8 Max | 1M | Alibaba | 40 | $2.67 | 40 | 2.61 | 64.52 | |
Qwen3.8 2.4T A95B | 984k | Alibaba | 40 | $2.16 | 41 | 2.77 | 64.19 | |
Gemini 3.8 Flash (medium) | 1M | Google | 40 | $0.93 | -- | -- | -- | |
Qwen3.8-Flash-Next | 256k | Alibaba | 40 | $0.37 | 52 | 2.69 | 50.35 | |
Muse Spark 1.2 (xhigh) | 1.05M | Meta | 40 | $0.97 | 182 | 15.37 | 29.14 | |
Claude Opus 5 (low) | 1M | Anthropic | 40 | $1.10 | 47 | 2.55 | 13.22 | |
Gemini 3.7 Flash (medium) | 1M | Google | 40* | -- | 290 | 4.77 | 6.49 | |
DeepSeek V4.1 Flash (max) | 1M |  DeepSeek | 40 | $0.27 | 215 | 1.21 | 12.85 | |
GPT-5.6 Sol (medium) | 1M | OpenAI | 39 | $0.50 | 61 | 3.45 | 11.70 | |
Gemini 3.7 Flash (high) | 1M | Google | 39 | $0.93 | 292 | 10.43 | 12.15 | |
Grok 4.5 (high) | 500k | SpaceXAI | 39 | $1.04 | 60 | 6.70 | 15.05 | |
Claude Sonnet 5 (max) | 1M | Anthropic | 38 | $5.09 | 75 | 153.59 | 160.25 | |
GPT-5.6 Terra (xhigh) | 1M | OpenAI | 38 | $0.63 | 91 | 14.46 | 19.96 | |
GPT-5.6 Luna (max) | 1M | OpenAI | 38 | $0.18 | 115 | 130.77 | 135.12 | |
Gemini 3.7 Flash (low) | 1M | Google | 37* | -- | 298 | 0.84 | 2.52 | |
DeepSeek V4 Pro 0813 (max) | 1M | DeepSeek | 36 | $0.67 | 94 | 1.74 | 28.21 | |
Agnes 3.0 Flash | 1M |  Sapiens AI | 36* | -- | 242 | 1.80 | 12.12 | |
Grok 4.6 (low) | 500k | SpaceXAI | 35 | $0.48 | 53 | 5.90 | 15.28 | |
Agnes 2.5 Pro Beta | 1M | Sapiens AI | 35* | -- | -- | -- | -- | |
DeepSeek V4 Flash Vision (max) | 1M | DeepSeek | 35 | $0.31 | 226 | 1.15 | 12.23 | |
GPT-5.6 Luna (xhigh) | 1M | OpenAI | 35 | $0.09 | 117 | 43.95 | 48.23 | |
Claude Sonnet 5 (xhigh) | 1M | Anthropic | 35 | $2.87 | 66 | 22.99 | 30.54 | |
DeepSeek V4 Flash 0731 (max) | 1M | DeepSeek | 35 | $0.22 | 215 | 1.53 | 13.16 | |
GPT-5.6 Terra (high) | 1M | OpenAI | 34 | $0.34 | 85 | 3.13 | 9.04 | |
Gemini 3.6 Flash | 1M | Google | 34 | $0.93 | 183 | 17.48 | 20.21 | |
GLM-5.2 (max) | 1M | Z AI | 34 | $0.96 | 69 | 8.38 | 44.69 | |
Qwen3.8 27B (xhigh) | 256k | Alibaba | 34 | $0.82 | 45 | 4.10 | 59.87 | |
GPT-5.6 Sol (low) | 1M | OpenAI | 34 | $0.26 | 62 | 3.17 | 11.29 | |
Gemini 3.8 Flash (low) | 1M | Google | 34 | -- | -- | -- | -- | |
Gemini 3.5 Flash (medium) | 1M | Google | 34* | -- | 216 | 13.12 | 15.44 | |
Motif 3 | 262k |  Motif Technologies | 34* | -- | -- | -- | -- | |
GPT-5.3 Codex (xhigh) | 400k | OpenAI | 33* | -- | 125 | 57.52 | 61.51 | |
GPT-5.6 Luna (high) | 1M | OpenAI | 32 | $0.04 | 115 | 8.87 | 13.20 | |
Motif 3 (Beta) | 262k | Motif Technologies | 32* | -- | -- | -- | -- | |
Claude Sonnet 5 (high) | 1M | Anthropic | 32 | $1.79 | 62 | 4.10 | 12.22 | |
DeepSeek V4 Pro (max) | 1M | DeepSeek | 31 | $0.12 | 86 | 1.61 | 58.61 | |
K2 Horizon 375B A23B | 524k |  MBZUAI Institute of Foundation Models | 31 | -- | -- | -- | -- | |
Kimi K3 (low) | 1.05M | Kimi | 30 | $1.15 | 34 | 3.85 | 77.21 | |
GPT-5.6 Terra (medium) | 1M | OpenAI | 30 | $0.18 | 87 | 1.65 | 7.39 | |
Apodex 1.1 | 256k |  Apodex | 30* | -- | -- | -- | -- | |
Gemini 3.1 Pro Preview | 1M | Google | 30 | $0.67 | 111 | 28.74 | 33.25 | |
DeepSeek V4 Pro (high) | 1M | DeepSeek | 30* | -- | 90 | 1.71 | 29.28 | |
MiniMax-M3 | 1M |  MiniMax | 30 | $0.51 | 115 | 1.32 | 23.06 | |
Claude Sonnet 5 (Non-reasoning) | 1M | Anthropic | 29* | -- | 60 | 1.11 | 9.40 | |
Claude Sonnet 5 (medium) | 1M | Anthropic | 28 | $1.00 | 59 | 1.88 | 10.36 | |
GPT-5.6 Sol (Non-reasoning) | 1M | OpenAI | 28* | -- | 63 | 1.16 | 9.09 | |
Nex-N2-Pro | 262k |  Nex AGI | 28* | -- | -- | -- | -- | |
Solar Pro 4 | 512k |  Upstage | 28* | -- | 71 | 1.98 | 37.40 | |
GPT-5.6 Terra (low) | 1M | OpenAI | 28 | $0.14 | 90 | 1.62 | 7.18 | |
Qwen3.8 27B (medium) | 256k | Alibaba | 28 | $0.90 | 49 | 3.84 | 54.91 | |
Agnes 2.5 Pro Alpha | 1M | Sapiens AI | 28 | -- | 182 | 3.93 | 17.67 | |
JT-4.1 Flash 236B A21B | 256k |  China Mobile | 27* | -- | -- | -- | -- | |
Quasar 438B (max) | 1M |  Multiverse Computing | 27 | $2.02 | 146 | 1.13 | 18.22 | |
GPT-5.5 Instant (June 2026) | 400k | OpenAI | 27 | $0.69 | 135 | 1.01 | 19.57 | |
Qwen3.8 27B (low) | 256k | Alibaba | 26 | $0.83 | 49 | 3.99 | 54.56 | |
MiMo-V2.5-Pro | 1M |  Xiaomi | 26 | $0.05 | 48 | 4.16 | 55.87 | |
Kimi K2.7 Code | 256k | Kimi | 26 | $0.54 | 50 | 2.80 | 57.24 | |
Inkling Small | 1M |  Thinking Machines | 26 | $0.09 | 189 | 2.12 | 15.37 | |
Qwen3.7 Plus | 1M | Alibaba | 26 | $0.33 | 70 | 2.28 | 37.83 | |
Hy3 | 256k |  Tencent | 26 | $0.07 | 86 | 2.73 | 31.66 | |
K2 Horizon MoVA 36B A4B | 524k | MBZUAI Institute of Foundation Models | 26 | -- | -- | -- | -- | |
Inkling | 1M | Thinking Machines | 26 | $0.61 | 84 | 2.80 | 32.50 | |
GPT-5.6 Luna (medium) | 1M | OpenAI | 25 | $0.02 | 115 | 2.45 | 6.80 | |
MiMo-V2-Omni-0327 | 256k | Xiaomi | 25* | -- | -- | -- | -- | |
Ling-3.0-flash-VL | 262k |  InclusionAI | 25 | -- | 144 | 2.17 | 19.54 | |
Grok 4.3 (medium) | 1M | SpaceXAI | 25* | -- | 108 | 12.57 | 17.21 | |
Claude Sonnet 5 (low) | 1M | Anthropic | 25 | $0.51 | 56 | 1.30 | 10.18 | |
Solar Open2 250B | 1.05M | Upstage | 25* | -- | -- | -- | -- | |
Grok 4.3 (low) | 1M | SpaceXAI | 24* | -- | 102 | 4.55 | 9.43 | |
MiMo-V2-Omni | 256k | Xiaomi | 24* | -- | -- | -- | -- | |
Gemini 3.5 Flash (minimal) | 1M | Google | 24* | -- | 215 | 0.87 | 3.20 | |
Nemotron 3 Ultra | 262k |  NVIDIA | 23 | $0.58 | 188 | 1.99 | 16.73 | |
Claude Sonnet 4.6 (Non-reasoning, low) | 1M | Anthropic | 23* | -- | 40 | 1.41 | 13.77 | |
A.X-K2 | 262k |  SK Telecom | 23* | -- | -- | -- | -- | |
Gemini 3.5 Flash-Lite | 1M | Google | 23 | $0.12 | 381 | 8.68 | 10.00 | |
MiMo-V2-Flash (Feb 2026) | 256k | Xiaomi | 22* | -- | -- | -- | -- | |
GLM-5.2 (Non-reasoning) | 1M | Z AI | 22* | -- | 146 | 1.78 | 5.21 | |
Qwen3.8 27B | 256k | Alibaba | 22* | -- | 52 | 3.91 | 13.55 | |
MiMo-V2.5 | 1M | Xiaomi | 22 | $0.02 | 48 | 5.54 | 57.26 | |
Qwen3.6 27B | 262k | Alibaba | 22 | $0.62 | 57 | 3.63 | 112.20 | |
G9v3-39A5B | 131k |  AI9Stars | 22* | -- | -- | -- | -- | |
KAT-Coder-Pro V2 | 256k |  KwaiKAT | 22* | -- | -- | -- | -- | |
GPT-5.6 Luna (low) | 1M | OpenAI | 22 | $0.01 | 100 | 2.11 | 7.09 | |
Qwen3.5 397B A17B (Non-reasoning) | 262k | Alibaba | 21* | -- | 82 | 2.16 | 8.24 | |
GPT-5.6 Terra (Non-reasoning) | 1M | OpenAI | 21 | $0.14 | 93 | 0.88 | 6.26 | |
K2 Horizon 7B | 524k | MBZUAI Institute of Foundation Models | 21 | -- | -- | -- | -- | |
DeepSeek V4 Pro (Non-reasoning) | 1M | DeepSeek | 21* | -- | 91 | 1.54 | 7.02 | |
Ling 3.0 Flash | 262k | InclusionAI | 21 | $0.03 | 332 | 2.48 | 10.01 | |
Qwen3.5 Omni Plus | 256k | Alibaba | 20* | -- | 99 | 2.14 | 7.18 | |
o3 | 200k | OpenAI | 20* | -- | 130 | 7.13 | 10.99 | |
Qwen3.6 27B (Non-reasoning) | 262k | Alibaba | 20* | -- | 60 | 3.65 | 12.03 | |
K-EXAONE 2.0 | 262k |  LG AI Research | 20* | -- | -- | -- | -- | |
LongCat 2.0 | 1M |  LongCat | 20 | $0.06 | -- | -- | -- | |
Step 3.7 Flash | 262k |  StepFun | 19* | -- | 141 | 2.55 | 20.33 | |
Qwen3.5 397B A17B | 262k | Alibaba | 19 | $0.47 | 83 | 2.16 | 46.57 | |
DeepSeek V4 Flash (Non-reasoning) | 1M | DeepSeek | 19* | -- | -- | -- | -- | |
Qwen3.6 35B A3B | 262k | Alibaba | 19 | $0.48 | 127 | 2.10 | 48.44 | |
JT-35B-Flash | 256k | China Mobile | 19* | -- | -- | -- | -- | |
MiMo-V2.5-Pro (Non-reasoning) | 1M | Xiaomi | 18* | -- | 38 | 4.40 | 17.67 | |
Muse Glimmer (high) | 131k | Meta | 18 | $0.06 | 98 | 1.01 | 26.40 | |
Qwen3.5 122B A10B (Non-reasoning) | 262k | Alibaba | 18* | -- | 142 | 2.34 | 5.86 | |
Claude 4.5 Haiku | 200k | Anthropic | 18 | $0.21 | 87 | 22.95 | 28.70 | |
Ring-2.6-1T | 262k | InclusionAI | 17 | $0.29 | 127 | 3.78 | 23.49 | |
Doubao Seed Code | 256k |  ByteDance Seed | 17* | -- | -- | -- | -- | |
Gemma 4 26B A4B | 256k | Google | 17* | -- | -- | -- | -- | |
Qwen3.5 122B A10B | 262k | Alibaba | 16 | $0.32 | 128 | 2.38 | 21.89 | |
K2 Horizon 3.7B | 524k | MBZUAI Institute of Foundation Models | 16 | -- | -- | -- | -- | |
GPT-5.6 Luna (Non-reasoning) | 1M | OpenAI | 16 | $0.01 | 110 | 0.85 | 5.38 | |
MiMo-V2-Flash (Non-reasoning) | 256k | Xiaomi | 16* | -- | -- | -- | -- | |
Gemma 4 31B | 256k | Google | 15 | $0.00 | 35 | 1.01 | 64.91 | |
Claude 4.5 Haiku (Non-reasoning) | 200k | Anthropic | 15* | -- | 83 | 0.67 | 6.66 | |
Qwen3.6 35B A3B (Non-reasoning) | 262k | Alibaba | 15* | -- | 132 | 2.05 | 5.85 | |
Qwen3.5 35B A3B (Non-reasoning) | 262k | Alibaba | 15* | -- | 164 | 2.05 | 5.10 | |
Mistral Medium 3.5 | 256k |  Mistral | 15 | $0.44 | 145 | 2.26 | 19.54 | |
Granite 4.2 30B | 131k | IBM | 15* | -- | 77 | 0.81 | 33.41 | |
Grok 4.3 (Non-reasoning) | 1M | SpaceXAI | 15 | $0.14 | 108 | 0.72 | 5.34 | |
K-EXAONE | 256k | LG AI Research | 14* | -- | -- | -- | -- | |
ERNIE 5.0 Thinking Preview | 128k |  Baidu | 14* | -- | -- | -- | -- | |
Gemma 4 12B | 256k | Google | 14* | -- | 110 | 2.42 | 25.15 | |
Nova 2.0 Pro Preview (medium) | 256k |  Amazon | 14* | -- | 112 | 14.40 | 36.63 | |
Command A+ | 192k | Cohere | 14 | $0.00 | 241 | 0.38 | 10.77 | |
Gemma 4 31B (Non-reasoning) | 256k | Google | 14* | -- | 45 | 1.95 | 13.17 | |
Qwen3.5 9B | 262k | Alibaba | 14* | -- | 85 | 1.95 | 31.43 | |
Nova 2.0 Omni (medium) | 1M | Amazon | 14* | -- | -- | -- | -- | |
Nemotron 3.5 Lightning | 1M | NVIDIA | 14 | $0.09 | 295 | 0.59 | 9.05 | |
Nemotron 3 Super | 1M | NVIDIA | 14 | $1.06 | 166 | 2.50 | 17.57 | |
Apriel-v1.6-15B-Thinker | 128k |  ServiceNow | 13* | -- | -- | -- | -- | |
Nova 2.0 Lite (high) | 1M | Amazon | 13* | -- | 167 | 16.12 | 31.09 | |
Qwen3.5 9B (Non-reasoning) | 262k | Alibaba | 13* | -- | 91 | 0.78 | 6.28 | |
EXAONE 4.5 33B | 262k | LG AI Research | 13* | -- | -- | -- | -- | |
MiniCPM5-2B | 131k |  OpenBMB | 13 | -- | -- | -- | -- | |
Gemma 4 26B A4B (Non-reasoning) | 256k | Google | 13* | -- | 66 | 1.47 | 9.10 | |
Qwen3.5 4B | 262k | Alibaba | 13* | -- | 20 | 0.73 | 123.64 | |
Nova 2.0 Pro Preview (low) | 256k | Amazon | 13* | -- | 114 | 10.88 | 32.87 | |
Nova 2.0 Lite (medium) | 1M | Amazon | 12* | -- | 167 | 15.63 | 30.60 | |
Qwen3.5 Omni Flash | 256k | Alibaba | 12* | -- | 236 | 1.84 | 3.95 | |
gpt-oss-120b (high) | 131k | OpenAI | 12 | $0.11 | 200 | 0.84 | 13.37 | |
JT-MINI | 128k | China Mobile | 12* | -- | -- | -- | -- | |
Ling 3.0 Tiny | 262k | InclusionAI | 12 | $0.00 | 168 | 2.62 | 17.49 | |
Magistral Medium 1.2 | 128k | Mistral | 12* | -- | -- | -- | -- | |
Granite 4.2 8B | 131k | IBM | 12 | $0.02 | 67 | 0.64 | 37.89 | |
Nova 2.0 Lite (low) | 1M | Amazon | 12* | -- | 171 | 7.78 | 22.42 | |
HyperNova 60B 2605 (high) | 131k | Multiverse Computing | 12* | -- | 354 | 0.57 | 7.63 | |
Nemotron Cascade 2 30B A3B | 1M | NVIDIA | 12* | -- | -- | -- | -- | |
Mercury 2 | 128k | Inception | 12 | $0.07 | 661 | 4.86 | 5.62 | |
K2 Think V2 | 262k | MBZUAI Institute of Foundation Models | 11* | -- | -- | -- | -- | |
LongCat Flash Lite | 256k | LongCat | 11* | -- | -- | -- | -- | |
Mistral Small 4 | 256k | Mistral | 11 | $0.05 | 168 | 0.77 | 15.65 | |
HyperCLOVA X SEED Think (32B) | 128k |  Naver | 11* | -- | -- | -- | -- | |
K-EXAONE (Non-reasoning) | 256k | LG AI Research | 11* | -- | -- | -- | -- | |
Qwen3 Next 80B A3B (Reasoning) | 262k | Alibaba | 11* | -- | 197 | 2.43 | 15.10 | |
Nova 2.0 Omni (low) | 1M | Amazon | 11* | -- | -- | -- | -- | |
Mi:dm K 2.5 Pro | 128k |  Korea Telecom | 11* | -- | -- | -- | -- | |
Trinity Large Thinking | 512k |  Arcee AI | 11 | $0.35 | 319 | 1.29 | 9.12 | |
G9v3-3B | 131k | AI9Stars | 11* | -- | -- | -- | -- | |
Qwen3.5 4B (Non-reasoning) | 262k | Alibaba | 11* | -- | 15 | 0.78 | 33.42 | |
INTELLECT-3 | 131k |  Prime Intellect | 11* | -- | -- | -- | -- | |
Solar Open 100B | 128k | Upstage | 10* | -- | -- | -- | -- | |
Nemotron 3 Nano Omni 30B A3B | 256k | NVIDIA | 10* | -- | -- | -- | -- | |
gpt-oss-120b (low) | 131k | OpenAI | 10* | -- | 192 | 0.85 | 13.88 | |
Qwen3 Coder Next | 256k | Alibaba | 10 | $0.55 | 100 | 1.18 | 6.19 | |
Nova 2.0 Pro Preview (Non-reasoning) | 256k | Amazon | 10* | -- | 105 | 1.02 | 5.79 | |
gpt-oss-20b (low) | 131k | OpenAI | 10* | -- | 253 | 0.83 | 10.71 | |
North Mini Code | 256k | Cohere | 10 | $0.00 | 80 | 0.40 | 31.75 | |
K2-V2 (high) | 512k | MBZUAI Institute of Foundation Models | 10* | -- | -- | -- | -- | |
Mistral Large 3 | 256k | Mistral | 10 | $0.10 | 78 | 1.04 | 7.44 | |
Qwen3 Next 80B A3B | 262k | Alibaba | 10* | -- | 184 | 2.22 | 4.94 | |
DiffusionGemma 26B A4B | 256k | Google | 10* | -- | -- | -- | -- | |
Devstral 2 | 256k | Mistral | 9 | $0.00 | 138 | 2.26 | 5.89 | |
Gemma 4 12B (Non-reasoning) | 262k | Google | 9* | -- | 106 | 2.40 | 7.10 | |
Llama 4 Maverick | 1M | Meta | 9 | $0.04 | 105 | 0.87 | 5.61 | |
Motif-2-12.7B | 128k | Motif Technologies | 9* | -- | -- | -- | -- | |
Nova Premier | 1M | Amazon | 9* | -- | 33 | 2.81 | 17.98 | |
Granite 4.2 3B | 131k | IBM | 9 | $0.01 | 208 | 0.44 | 12.43 | |
gpt-oss-20b (high) | 131k | OpenAI | 9 | $0.01 | 219 | 0.76 | 12.16 | |
K2-V2 (medium) | 512k | MBZUAI Institute of Foundation Models | 9* | -- | -- | -- | -- | |
Llama Nemotron Super 49B v1.5 | 128k | NVIDIA | 9* | -- | 69 | 4.86 | 41.28 | |
Mistral Small 4 (Non-reasoning) | 256k | Mistral | 9* | -- | 156 | 0.74 | 3.95 | |
Tri-21B-Think | 32k |  Trillion Labs | 9* | -- | -- | -- | -- | |
Gemma 4 E4B | 128k | Google | 9* | -- | 46 | 0.83 | 55.47 | |
Nemotron 3 Nano | 1M | NVIDIA | 9 | $0.02 | 137 | 1.42 | 19.71 | |
MiniCPM5-1B | 128k | OpenBMB | 9* | -- | -- | -- | -- | |
Sarvam 105B (high) | 128k |  Sarvam | 9* | -- | -- | -- | -- | |
Nova 2.0 Lite (Non-reasoning) | 1M | Amazon | 9* | -- | 154 | 1.01 | 4.25 | |
MiniCPM5-1B (Non-reasoning) | 128k | OpenBMB | 9* | -- | -- | -- | -- | |
Magistral Small 1.2 | 128k | Mistral | 9* | -- | -- | -- | -- | |
Nanbeige4.1-3B | 256k |  Nanbeige | 8* | -- | -- | -- | -- | |
LFM2.5-2.6B | 128k |  Liquid AI | 8* | -- | -- | -- | -- | |
Devstral Small 2 | 256k | Mistral | 8 | $0.00 | 133 | 2.27 | 6.02 | |
EXAONE 4.0 32B | 131k | LG AI Research | 8* | -- | -- | -- | -- | |
Nova 2.0 Omni (Non-reasoning) | 1M | Amazon | 8* | -- | -- | -- | -- | |
Hermes 4 70B | 128k |  Nous Research | 8* | -- | -- | -- | -- | |
Falcon-H1R-7B | 256k |  TII UAE | 8* | -- | -- | -- | -- | |
Solar Pro 3 | 128k | Upstage | 8 | $0.08 | 146 | 2.47 | 19.59 | |
Gemma 4 E2B | 128k | Google | 8* | -- | -- | -- | -- | |
Qwen3 Omni 30B A3B (Reasoning) | 65.5k | Alibaba | 8* | -- | 100 | 1.89 | 26.83 | |
Step3 VL 10B | 65.5k | StepFun | 8* | -- | -- | -- | -- | |
Llama 3.3 70B | 128k | Meta | 8* | -- | 86 | 1.66 | 7.45 | |
Llama Nemotron Ultra | 128k | NVIDIA | 8* | -- | -- | -- | -- | |
ERNIE 4.5 300B A47B | 131k | Baidu | 8* | -- | -- | -- | -- | |
Hermes 4 405B | 128k | Nous Research | 7* | -- | 43 | 2.46 | 60.99 | |
NVIDIA Nemotron Nano 12B v2 VL | 128k | NVIDIA | 7* | -- | 109 | 3.84 | 26.79 | |
Gemma 4 E4B (Non-reasoning) | 128k | Google | 7* | -- | 43 | 0.76 | 12.27 | |
Granite 4.1 30B | 131k | IBM | 7* | -- | -- | -- | -- | |
NVIDIA Nemotron Nano 9B V2 | 131k | NVIDIA | 7* | -- | 95 | 9.25 | 35.58 | |
Hermes 4 405B (Non-reasoning) | 128k | Nous Research | 7* | -- | 43 | 2.36 | 13.86 | |
Nemotron 3 Nano 4B | 262k | NVIDIA | 7* | -- | -- | -- | -- | |
Llama Nemotron Super 49B v1.5 (Non-reasoning) | 128k | NVIDIA | 7* | -- | 93 | 7.18 | 12.55 | |
K2-V2 (low) | 512k | MBZUAI Institute of Foundation Models | 7* | -- | -- | -- | -- | |
Kimi Linear 48B A3B Instruct | 1M | Kimi | 7* | -- | -- | -- | -- | |
Llama 3.1 405B | 128k | Meta | 7* | -- | -- | -- | -- | |
LFM2.5-8B-A1B | 32.8k | Liquid AI | 7* | -- | -- | -- | -- | |
Ring-flash-2.0 | 128k | InclusionAI | 7* | -- | -- | -- | -- | |
Olmo 3.1 32B Think | 65.5k |  Allen Institute for AI | 7* | -- | -- | -- | -- | |
Command A | 256k | Cohere | 7* | -- | 51 | 1.75 | 11.50 | |
Qwen3.5 2B | 262k | Alibaba | 7* | -- | -- | -- | -- | |
Llama 3.1 Nemotron 70B | 128k | NVIDIA | 7* | -- | 123 | 3.59 | 7.65 | |
Nemotron 3 Nano (Non-reasoning) | 1M | NVIDIA | 7* | -- | 153 | 0.97 | 4.24 | |
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | 131k | NVIDIA | 7* | -- | 143 | 1.61 | 5.11 | |
Hermes 4 70B (Non-reasoning) | 128k | Nous Research | 7* | -- | -- | -- | -- | |
Granite 4.1 8B | 131k | IBM | 7* | -- | 125 | 0.78 | 4.78 | |
Sarvam 30B (high) | 65.5k | Sarvam | 7* | -- | -- | -- | -- | |
Olmo 3.1 32B Instruct | 65.5k | Allen Institute for AI | 6* | -- | -- | -- | -- | |
Gemma 4 E2B (Non-reasoning) | 128k | Google | 6* | -- | -- | -- | -- | |
Llama 4 Scout | 10M | Meta | 6 | $0.12 | 106 | 0.85 | 5.59 | |
R1 1776 | 128k |  Perplexity | 6* | -- | -- | -- | -- | |
Llama 3.2 90B (Vision) | 128k | Meta | 6* | -- | -- | -- | -- | |
Celeris-1 | 131k | Celeris | 6 | $0.05 | 1,397 | 0.59 | 0.94 | |
Phi-4 Mini | 128k |  Microsoft | 6* | -- | 46 | 0.87 | 11.85 | |
EXAONE 4.0 32B (Non-reasoning) | 131k | LG AI Research | 6* | -- | -- | -- | -- | |
Qwen3.5 2B (Non-reasoning) | 262k | Alibaba | 6* | -- | -- | -- | -- | |
Qwen3.5 0.8B | 262k | Alibaba | 6* | -- | -- | -- | -- | |
DeepHermes 3 - Mistral 24B | 32k | Nous Research | 6* | -- | -- | -- | -- | |
Jamba 1.7 Large | 256k |  AI21 Labs | 6* | -- | -- | -- | -- | |
Granite 4.0 H Small | 128k | IBM | 6* | -- | 25 | 21.88 | 41.64 | |
Ministral 3 14B | 256k | Mistral | 6 | $0.14 | 86 | 0.90 | 6.74 | |
Qwen3 Omni 30B A3B | 65.5k | Alibaba | 6* | -- | 97 | 1.86 | 7.01 | |
LFM2 24B A2B | 32.8k | Liquid AI | 6* | -- | -- | -- | -- | |
Phi-4 | 16k | Microsoft | 6* | -- | 41 | 2.49 | 14.65 | |
Nova Micro | 130k | Amazon | 6* | -- | 289 | 0.85 | 2.58 | |
Granite 4.1 3B | 131k | IBM | 6* | -- | -- | -- | -- | |
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | 128k | NVIDIA | 6* | -- | 198 | 1.62 | 4.15 | |
Phi-4 Multimodal | 128k | Microsoft | 6* | -- | 17 | 0.87 | 30.21 | |
MiniCPM-V 4.6 1.3B | 262k | OpenBMB | 6* | -- | -- | -- | -- | |
Jamba Reasoning 3B | 262k | AI21 Labs | 6* | -- | -- | -- | -- | |
Reka Flash 3 | 128k |  Reka AI | 6* | -- | -- | -- | -- | |
Olmo 3 7B Think | 65.5k | Allen Institute for AI | 6* | -- | -- | -- | -- | |
Molmo 7B-D | 4.1k | Allen Institute for AI | 6* | -- | -- | -- | -- | |
Ministral 3 8B | 256k | Mistral | 5 | $0.07 | 92 | 0.74 | 6.20 | |
Llama 3.2 11B (Vision) | 128k | Meta | 5* | -- | 19 | 1.31 | 28.06 | |
Qwen3.5 0.8B (Non-reasoning) | 262k | Alibaba | 5* | -- | -- | -- | -- | |
Exaone 4.0 1.2B | 64k | LG AI Research | 5* | -- | -- | -- | -- | |
Olmo 3 7B | 65.5k | Allen Institute for AI | 5* | -- | -- | -- | -- | |
Exaone 4.0 1.2B (Non-reasoning) | 64k | LG AI Research | 5* | -- | -- | -- | -- | |
LFM2.5-1.2B-Thinking | 32k | Liquid AI | 5* | -- | -- | -- | -- | |
Jamba 1.7 Mini | 258k | AI21 Labs | 5* | -- | -- | -- | -- | |
LFM2 2.6B | 32.8k | Liquid AI | 5* | -- | -- | -- | -- | |
LFM2.5-1.2B-Instruct | 32k | Liquid AI | 5* | -- | -- | -- | -- | |
Granite 4.0 H 1B | 128k | IBM | 5* | -- | -- | -- | -- | |
Gemma 3 270M | 32k | Google | 5* | -- | -- | -- | -- | |
Apertus 70B Instruct | 65.5k |  Swiss AI Initiative | 5* | -- | -- | -- | -- | |
Granite 4.0 Micro | 128k | IBM | 5* | -- | -- | -- | -- | |
DeepHermes 3 - Llama-3.1 8B | 128k | Nous Research | 5* | -- | -- | -- | -- | |
Granite 4.0 1B | 128k | IBM | 5* | -- | -- | -- | -- | |
Molmo2-8B | 36.9k | Allen Institute for AI | 5* | -- | -- | -- | -- | |
LFM2 8B A1B | 32.8k | Liquid AI | 5* | -- | -- | -- | -- | |
Ministral 3 3B | 256k | Mistral | 5 | $0.04 | 222 | 0.64 | 2.90 | |
LFM2.5-VL-1.6B | 32k | Liquid AI | 5* | -- | -- | -- | -- | |
Granite 4.0 350M | 32.8k | IBM | 5* | -- | -- | -- | -- | |
Tiny Aya Global | 8.19k | Cohere | 5* | -- | -- | -- | -- | |
Apertus 8B Instruct | 65.5k | Swiss AI Initiative | 5* | -- | -- | -- | -- | |
Granite 4.0 H 350M | 32.8k | IBM | 5* | -- | -- | -- | -- | |
K2 Horizon 0.9B | 131k | MBZUAI Institute of Foundation Models | 3 | -- | -- | -- | -- | |
EXAONE 4.5 33B (Non-reasoning) | 262k | LG AI Research | -- | -- | -- | -- | -- | |
Gemini 3 Deep Think | 128k | Google | -- | -- | -- | -- | -- | |
GPT-5.5 Pro (xhigh) | 922k | OpenAI | -- | -- | -- | -- | -- | |
Cogito v2.1 | 128k |  Deep Cogito | -- | -- | -- | -- | -- | |
Wichtige Definitionen
Häufig gestellte Fragen
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) belegt derzeit Platz 1 der Artificial Analysis LLM-Bestenliste. Das Modell erreicht im Intelligence Index einen Wert von 53; insgesamt werden 160 Modelle gelistet.
Die nach dem Intelligence Index führenden Modelle sind: 1. Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) (53), 2. Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) (53), 3. GPT-6 Astra (max) (53), 4. GPT-6 Astra (xhigh) (53), 5. Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) (51).
Celeris-1 ist mit 1,397.2 Tokens pro Sekunde am schnellsten, gefolgt von Mercury 2 (660.7 t/s) und Gemini 2.5 Flash-Lite (Reasoning) (416.3 t/s).
Granite 4.2 3B hat mit $0.01 die niedrigsten Kosten pro Aufgabe des Intelligence Index, gefolgt von GPT-5.6 Luna (low) ($0.01) und GPT-5.6 Luna (Non-reasoning) ($0.01).
GLM-5.3 (max) ist mit einem Intelligence-Index-Wert von 45 das am höchsten platzierte Modell mit offenen Gewichten. Von insgesamt 160 Modellen in der Bestenliste haben 79 offene Gewichte.
Die nach dem Intelligence Index führenden Modelle mit offenen Gewichten sind: 1. GLM-5.3 (max) (45), 2. Kimi K3 (max) (44), 3. GLM-5.3-Flash (42).
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) führt mit einem Intelligence-Index-Wert von 53 unter 140 Reasoning-Modellen. Reasoning-Modelle nutzen ausführliches Schlussfolgern, um komplexe Probleme vor der Antwort zu lösen.
Die Bestenliste bietet Filter nach Modelltyp (Reasoning oder kein Reasoning), Offenheit (offene Gewichte oder proprietär) und weiteren Kriterien. Sie können außerdem die Prompt-Optionen anpassen, um zu sehen, wie sich die Leistung bei unterschiedlichen Eingabelängen verändert.
Klicken Sie in der Bestenliste auf einen Modellnamen, um die zugehörige Vergleichsseite mit detaillierten Diagrammen zu Intelligenz, Preisen, Geschwindigkeit, Latenz und weiteren Metriken aufzurufen. Sie können außerdem die API-Anbieter jedes Modells vergleichen. Alle Modelle anzeigen