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
Claude Opus 5.5 (max with fallback) und Claude Sonnet 5.5 (max with fallback) weisen die höchste Intelligenz auf, gefolgt von Claude Opus 5.5 (xhigh with fallback) und Muse Wonder Full (max).
Ausgabegeschwindigkeit
Celeris-1 und Mercury 2.5 sind die schnellsten Modelle, gefolgt von Gemini 3.5 Flash-Lite und Nemotron 3.5 Super VL.
Latenz
North Mini Code und Granite 4.2 3B weisen die niedrigsten Latenzwerte auf, gefolgt von Command A+ und Nemotron 3 Nano (non-reasoning).
Kosten pro Aufgabe
Gemma 4 31B und Command A+ haben die niedrigsten Kosten pro Aufgabe, gefolgt von Ling 3.0 Tiny und North Mini Code.
Kontextfenster
Llama 4 Scout und GPT-6 Sol (Daybreak Blue, max) unterstützen die größten Kontextfenster, gefolgt von Muse Wonder (max) und Kimi K3 (max).
Weitere Analyse | ||||||||
|---|---|---|---|---|---|---|---|---|
Claude Opus 5.5 (max with fallback) | 1M | Anthropic | 58 | $5.98 | 97 | 711.35 | 716.48 | |
Claude Sonnet 5.5 (max with fallback) | 1M | Anthropic | 56 | $5.46 | 143 | 471.38 | 474.88 | |
Claude Opus 5.5 (xhigh with fallback) | 1M | Anthropic | 56 | $3.46 | 89 | 139.63 | 145.26 | |
Muse Wonder Full (max) | 1M | Meta | 56 | -- | -- | -- | -- | |
Claude Opus 5.5 (high with fallback) | 1M | Anthropic | 54 | $1.82 | 83 | 38.90 | 44.89 | |
Claude Fable 5.1 (max with fallback) | 1M | Anthropic | 53 | $7.63 | 71 | 257.75 | 264.79 | |
Claude Fable 5.1 (xhigh with fallback) | 1M | Anthropic | 53 | $5.98 | 64 | 63.14 | 70.94 | |
GPT-6 Astra (max) | 1M | OpenAI | 53 | $3.26 | 57 | 279.10 | 287.81 | |
Gemini 4 Argon (high) | 1M | Google | 53 | $1.99 | -- | -- | -- | |
Muse Wonder (max) | 1.05M | Meta | 52 | $4.52 | 181 | 42.17 | 55.99 | |
GPT-6 Astra (xhigh) | 1M | OpenAI | 52 | $2.31 | 55 | 171.08 | 180.25 | |
Claude Sonnet 5.5 (xhigh with fallback) | 1M | Anthropic | 52 | $2.01 | 114 | 25.95 | 30.35 | |
GPT-6.1 Sol (max) | 1M | OpenAI | 52 | $0.72 | 66 | 324.19 | 331.76 | |
Claude Opus 5.5 (medium with fallback) | 1M | Anthropic | 51 | $1.34 | 86 | 18.34 | 24.17 | |
Claude Fable 5.1 (high with fallback) | 1M | Anthropic | 51 | $3.91 | 59 | 11.66 | 20.19 | |
GPT-6.1 Sol (xhigh) | 1M | OpenAI | 51 | $0.39 | 59 | 122.33 | 130.86 | |
GPT-6 Astra (high) | 1M | OpenAI | 51 | $1.73 | 53 | 51.63 | 61.08 | |
GPT-6.1 Sol (high) | 1M | OpenAI | 50 | $0.32 | 58 | 48.50 | 57.18 | |
GPT-6 Astra (medium) | 1M | OpenAI | 50 | $1.54 | 50 | 6.73 | 16.80 | |
Claude Fable 5.1 (medium with fallback) | 1M | Anthropic | 49 | $2.98 | 59 | 7.32 | 15.73 | |
Muse Spark 1.3 (max) | 1M | Meta | 48 | $1.60 | 139 | 54.06 | 72.11 | |
GPT-6.1 Sol (medium) | 1M | OpenAI | 48 | $0.21 | 48 | 4.24 | 14.65 | |
Claude Fable 5.1 (low with fallback) | 1M | Anthropic | 47 | $2.37 | 60 | 1.93 | 10.28 | |
Claude Sonnet 5.5 (high with fallback) | 1M | Anthropic | 47 | $0.88 | 110 | 12.31 | 16.84 | |
Grok 4.7 (xhigh) | 500k |  SpaceXAI | 46 | $3.74 | 93 | 50.20 | 55.56 | |
Grok 4.7 (high) | 500k | SpaceXAI | 46 | $2.73 | 91 | 28.63 | 34.15 | |
MiMo-V2.6-Pro | 1M |  Xiaomi | 46 | $0.13 | 48 | 4.26 | 56.30 | |
GPT-6 Astra (low) | 1M | OpenAI | 46 | $0.82 | 53 | 2.48 | 11.88 | |
Qwen3.8 Max (0902) | 984k |  Alibaba | 45 | $5.41 | 39 | 3.10 | 67.51 | |
Muse Spark 1.3 (xhigh) | 1M | Meta | 45 | $1.37 | 294 | 23.82 | 32.33 | |
GLM-5.3 (max) | 1M |  Z AI | 45 | $2.01 | 77 | 2.74 | 35.30 | |
Step 5 Preview | 1M |  StepFun | 44 | $1.03 | 91 | 2.21 | 29.64 | |
Kimi K3 (max) | 1.05M | Kimi | 44 | $2.00 | 42 | 3.60 | 62.89 | |
Claude Haiku 5.5 (max) | 1M | Anthropic | 43 | $0.21 | 237 | 336.91 | 339.02 | |
Claude Opus 5.5 (low with fallback) | 1M | Anthropic | 42 | $0.55 | 84 | 7.70 | 13.65 | |
Grok 4.7 (low) | 500k | SpaceXAI | 42 | $1.25 | 75 | 4.54 | 11.18 | |
GPT-6.1 Sol (low) | 1M | OpenAI | 42 | $0.13 | 48 | 2.75 | 13.23 | |
GPT-5.6 Terra (max) | 1M | OpenAI | 42 | $1.40 | 136 | 105.40 | 109.06 | |
GLM-5.3-Flash | 1M | Z AI | 42 | $0.28 | 69 | 2.77 | 38.94 | |
Claude Haiku 5.5 (xhigh) | 1M | Anthropic | 41 | $0.12 | 195 | 75.02 | 77.58 | |
Ling 3.1 Flash | 1M | InclusionAI | 41 | $1.00 | 214 | 1.79 | 13.46 | |
Gemini 3.8 Flash (high) | 1M | Google | 41 | $1.24 | 147 | 23.07 | 26.47 | |
Claude Sonnet 5.5 (medium with fallback) | 1M | Anthropic | 41 | $0.48 | 112 | 1.80 | 6.25 | |
Qwen3.8 2.4T A95B | 262k | Alibaba | 40 | $2.16 | 39 | 2.86 | 66.74 | |
Qwen3.8-Flash-Next | 256k | Alibaba | 40 | $0.37 | 51 | 2.16 | 50.92 | |
Gemini 3.8 Flash (medium) | 1M | Google | 40 | $0.93 | -- | -- | -- | |
DeepSeek V4.1 Flash (max) | 1M |  DeepSeek | 39 | $0.27 | 176 | 1.23 | 15.45 | |
Muse Spark Open (xhigh) | 1.05M | Meta | 39 | $0.84 | 129 | 0.71 | 20.05 | |
Mistral Large 4 Preview | 524k |  Mistral | 38 | $1.13 | 75 | 1.67 | 35.16 | |
GPT-6 Luna (max) | 1M | OpenAI | 38 | $0.07 | 121 | 102.91 | 107.06 | |
GPT-5.6 Terra (xhigh) | 1M | OpenAI | 38 | $0.63 | 115 | 26.40 | 30.75 | |
MiMo-V2.6-Flash | 1M | Xiaomi | 38 | $0.06 | 53 | 5.06 | 52.19 | |
Claude Haiku 5.5 (high) | 1M | Anthropic | 38 | $0.08 | 188 | 26.05 | 28.71 | |
DeepSeek V4 Pro 0813 (max) | 1M | DeepSeek | 36 | $0.67 | 79 | 1.68 | 33.42 | |
Claude Sonnet 5.5 (low with fallback) | 1M | Anthropic | 36 | $0.35 | 109 | 1.12 | 5.71 | |
Agnes 2.5 Pro Beta | 1M |  Sapiens AI | 35* | -- | 113 | 1.41 | 23.52 | |
DeepSeek V4 Flash Vision (max) | 1M | DeepSeek | 35 | $0.31 | 173 | 1.17 | 15.62 | |
GPT-6 Luna (xhigh) | 1M | OpenAI | 35 | $0.04 | 112 | 25.47 | 29.93 | |
Claude Haiku 5.5 (medium) | 1M | Anthropic | 34 | $0.05 | 181 | 11.45 | 14.21 | |
GLM-5.3 (low) | 1M | Z AI | 34 | $0.85 | 73 | 3.20 | 37.49 | |
GPT-5.6 Terra (high) | 1M | OpenAI | 34 | $0.34 | 111 | 2.68 | 7.19 | |
JT-4.1 Flash 236B A21B | 262k |  China Mobile | 34 | -- | -- | -- | -- | |
Qwen3.8 27B (xhigh) | 256k | Alibaba | 34 | $1.01 | 41 | 3.98 | 64.85 | |
Motif 3 | 262k |  Motif Technologies | 34* | -- | -- | -- | -- | |
Gemini 3.8 Flash (low) | 1M | Google | 33 | -- | -- | -- | -- | |
GPT-6 Luna (high) | 1M | OpenAI | 33 | $0.03 | 119 | 18.89 | 23.09 | |
GPT-5.3 Codex (xhigh) | 400k | OpenAI | 33* | -- | 99 | 70.43 | 75.46 | |
K2 Horizon 375B A23B | 524k |  Institute of Foundation Models | 31 | -- | -- | -- | -- | |
Beam 1.0 | 1.05M |  Reflection | 30 | -- | -- | -- | -- | |
GPT-5.6 Terra (medium) | 1M | OpenAI | 30 | $0.18 | 97 | 1.66 | 6.79 | |
Kimi K3 (low) | 1.05M | Kimi | 30 | $1.15 | 42 | 3.48 | 62.86 | |
GPT-6 Luna (medium) | 1M | OpenAI | 30 | $0.02 | -- | -- | -- | |
Gemini 3.1 Pro Preview | 1M | Google | 30 | $1.30 | 139 | 17.35 | 20.95 | |
Claude Haiku 5.5 (low) | 1M | Anthropic | 29 | $0.02 | 171 | 6.85 | 9.77 | |
MiniMax-M3 | 1M |  MiniMax | 29 | $0.51 | 93 | 1.24 | 28.01 | |
Nex-N2-Pro | 262k |  Nex AGI | 28* | -- | -- | -- | -- | |
Qwen3.8 27B (medium) | 256k | Alibaba | 28 | $1.13 | 43 | 3.98 | 62.48 | |
GPT-5.6 Terra (low) | 1M | OpenAI | 27 | $0.14 | 98 | 1.45 | 6.55 | |
JT-4.1 Flash 236B A21B (non-reasoning) | 262k | China Mobile | 27* | -- | -- | -- | -- | |
Quasar 438B (max) | 1M |  Multiverse Computing | 27 | $2.02 | 180 | 1.31 | 15.23 | |
Solar Pro 4 | 512k |  Upstage | 27 | $0.71 | 112 | 1.57 | 23.86 | |
Nemotron 3.5 Super VL | 1M | NVIDIA | 26 | $0.21 | 381 | 0.79 | 7.34 | |
Apodex 1.1 | 256k |  Apodex | 26 | $0.46 | -- | -- | -- | |
Qwen3.8 27B (low) | 256k | Alibaba | 26 | $1.05 | 49 | 3.92 | 55.32 | |
GPT-5.5 Instant (June 2026) | 400k | OpenAI | 26 | $0.69 | 153 | 0.81 | 17.13 | |
Kimi K2.7 Code | 256k | Kimi | 26 | $0.54 | 49 | 3.52 | 58.65 | |
Inkling Small | 1M |  Thinking Machines | 26 | $0.09 | 200 | 1.68 | 14.15 | |
K2 Horizon MoVA 36B A4B | 524k | Institute of Foundation Models | 25 | -- | -- | -- | -- | |
Hy3 | 256k |  Tencent | 25 | $0.07 | 85 | 2.80 | 32.26 | |
Qwen3.7 Plus | 1M | Alibaba | 25 | $0.22 | 56 | 2.26 | 46.80 | |
Inkling (xhigh) | 1M | Thinking Machines | 25 | -- | 197 | 1.81 | 14.50 | |
Solar Open2 250B | 1.05M | Upstage | 25* | -- | -- | -- | -- | |
DeepSeek V4.1 Flash (non-reasoning) | 1M | DeepSeek | 25 | $0.15 | 165 | 1.27 | 4.30 | |
Ling-3.0-flash-VL | 262k | InclusionAI | 25 | -- | -- | -- | -- | |
Solar Mini 4 | 1.05M | Upstage | 24 | $0.37 | 81 | 1.82 | 32.77 | |
Nemotron 3 Ultra | 262k | NVIDIA | 23 | $0.58 | 151 | 1.26 | 19.60 | |
Ling-3.0-flash-Fin | 262k | InclusionAI | 23 | -- | 241 | 1.73 | 12.11 | |
Gemini 3.5 Flash-Lite | 1M | Google | 22 | $0.19 | 449 | 6.90 | 8.01 | |
G9v3-39A5B | 131k |  AI9Stars | 22* | -- | -- | -- | -- | |
KAT-Coder-Pro V2 | 256k |  KwaiKAT | 22* | -- | -- | -- | -- | |
GPT-6 Luna (low) | 1M | OpenAI | 22 | $0.0045 | 120 | 2.14 | 6.29 | |
A.X-K2 | 262k |  SK Telecom | 21 | -- | -- | -- | -- | |
Qwen3.5 397B A17B (non-reasoning) | 262k | Alibaba | 21* | -- | 56 | 2.23 | 11.17 | |
Nemotron 3.5 Bolt 74B-A9B | 262k | NVIDIA | 21 | -- | -- | -- | -- | |
GPT-5.6 Terra (non-reasoning) | 1M | OpenAI | 21 | $0.14 | 98 | 0.79 | 5.88 | |
K2 Horizon 7B | 524k | Institute of Foundation Models | 21 | -- | -- | -- | -- | |
Qwen3.5 Omni Plus | 256k | Alibaba | 20* | -- | 77 | 2.13 | 8.63 | |
DeepSeek V4 Pro 0813 (non-reasoning) | 1M | DeepSeek | 20 | $0.36 | 80 | 1.68 | 7.97 | |
o3 | 200k | OpenAI | 20* | -- | 130 | 6.13 | 9.98 | |
Qwen3.8 27B (non-reasoning) | 256k | Alibaba | 20 | $2.49 | 44 | 3.91 | 15.24 | |
K-EXAONE 2.0 | 262k |  LG AI Research | 20* | -- | -- | -- | -- | |
LongCat 2.0 | 1M |  LongCat | 19 | $0.15 | 67 | 2.62 | 39.88 | |
JT-35B-Flash | 256k | China Mobile | 19* | -- | -- | -- | -- | |
GPT-6 Luna (non-reasoning) | 1M | OpenAI | 18 | $0.01 | 113 | 0.94 | 5.36 | |
Qwen3.5 397B A17B | 262k | Alibaba | 18 | $0.47 | 55 | 2.18 | 68.91 | |
Qwen3.6 35B A3B | 262k | Alibaba | 18 | $0.48 | 139 | 2.06 | 44.38 | |
Qwen3.5 122B A10B (non-reasoning) | 262k | Alibaba | 18* | -- | 140 | 2.35 | 5.93 | |
Muse Glimmer (high) | 131k | Meta | 17 | $0.06 | 128 | 1.14 | 20.65 | |
Doubao Seed Code | 256k |  ByteDance Seed | 17* | -- | -- | -- | -- | |
Gemma 4 26B A4B | 256k | Google | 17* | -- | 67 | 0.97 | 38.45 | |
Ring-2.6-1T | 262k | InclusionAI | 17 | $0.29 | 115 | 3.72 | 25.51 | |
K2 Horizon 3.7B | 524k | Institute of Foundation Models | 16 | -- | -- | -- | -- | |
Qwen3.5 122B A10B | 262k | Alibaba | 16 | $0.32 | 133 | 2.36 | 21.19 | |
Qwen3.6 35B A3B (non-reasoning) | 262k | Alibaba | 15* | -- | 145 | 2.09 | 5.55 | |
Gemma 4 31B | 256k | Google | 15 | $0.00 | 35 | 1.03 | 64.51 | |
ERNIE 5.0 Thinking Preview | 128k |  Baidu | 14* | -- | -- | -- | -- | |
Mistral Medium 3.5 | 256k | Mistral | 14 | $0.50 | 165 | 2.33 | 17.48 | |
Gemma 4 12B | 262k | Google | 14* | -- | 119 | 2.43 | 23.37 | |
Nova 2.0 Pro Preview (medium) | 256k |  Amazon | 14* | -- | 127 | 12.54 | 32.18 | |
Gemma 4 31B (non-reasoning) | 256k | Google | 14* | -- | 50 | 1.83 | 11.91 | |
Nova 2.0 Omni (medium) | 1M | Amazon | 14* | -- | -- | -- | -- | |
Apriel-v1.6-15B-Thinker | 128k |  ServiceNow | 13* | -- | -- | -- | -- | |
Nova 2.0 Lite (high) | 1M | Amazon | 13* | -- | 183 | 17.38 | 31.04 | |
Qwen3.5 9B (non-reasoning) | 262k | Alibaba | 13* | -- | 99 | 0.73 | 5.79 | |
EXAONE 4.5 33B | 262k | LG AI Research | 13* | -- | -- | -- | -- | |
Command A+ | 192k | Cohere | 13 | $0.00 | 177 | 0.50 | 14.60 | |
Gemma 4 26B A4B (non-reasoning) | 256k | Google | 13* | -- | 99 | 1.04 | 6.11 | |
Qwen3.5 4B | 262k | Alibaba | 13* | -- | 12 | 0.88 | 209.21 | |
Nemotron 3.5 Lightning | 1M | NVIDIA | 13 | $0.09 | 300 | 0.57 | 8.91 | |
Nova 2.0 Pro Preview (low) | 256k | Amazon | 13* | -- | 126 | 7.44 | 27.26 | |
Granite 4.2 30B | 131k | IBM | 13 | $0.07 | 77 | 0.85 | 33.49 | |
Nova 2.0 Lite (medium) | 1M | Amazon | 12* | -- | 196 | 17.08 | 29.86 | |
Qwen3.5 Omni Flash | 256k | Alibaba | 12* | -- | 233 | 1.83 | 3.98 | |
MiniCPM5-2B | 131k |  OpenBMB | 12 | -- | -- | -- | -- | |
Mercury 2.5 | 260k | Inception | 12 | $0.12 | 777 | 3.09 | 3.74 | |
JT-MINI | 128k | China Mobile | 12* | -- | -- | -- | -- | |
Magistral Medium 1.2 | 128k | Mistral | 12* | -- | -- | -- | -- | |
Nova 2.0 Lite (low) | 1M | Amazon | 12* | -- | 183 | 10.72 | 24.37 | |
HyperNova 60B 2605 (high) | 131k | Multiverse Computing | 12* | -- | -- | -- | -- | |
Nemotron Cascade 2 30B A3B | 1M | NVIDIA | 12* | -- | -- | -- | -- | |
gpt-oss-120b (high) | 131k | OpenAI | 12 | $0.09 | 213 | 0.86 | 12.57 | |
K2 Think V2 | 262k | Institute of Foundation Models | 11* | -- | -- | -- | -- | |
LongCat Flash Lite | 256k | LongCat | 11* | -- | -- | -- | -- | |
HyperCLOVA X SEED Think (32B) | 128k |  Naver | 11* | -- | -- | -- | -- | |
Mistral Small 4 | 256k | Mistral | 11 | $0.02 | 169 | 0.82 | 15.61 | |
Qwen3 Next 80B A3B | 262k | Alibaba | 11* | -- | 162 | 0.68 | 16.09 | |
Qwen3.5 9B | 262k | Alibaba | 11 | $0.21 | 58 | 1.82 | 45.07 | |
Nova 2.0 Omni (low) | 1M | Amazon | 11* | -- | -- | -- | -- | |
Granite 4.2 8B | 131k | IBM | 11 | $0.02 | 132 | 0.66 | 19.59 | |
Ling 3.0 Tiny | 262k | InclusionAI | 11 | $0.00 | 15 | 30.24 | 193.40 | |
Mi:dm K 2.5 Pro | 128k |  Korea Telecom | 11* | -- | -- | -- | -- | |
G9v3-3B | 131k | AI9Stars | 11* | -- | -- | -- | -- | |
Trinity Large Thinking | 512k |  Arcee AI | 11 | $0.12 | 340 | 1.21 | 8.56 | |
Qwen3.5 4B (non-reasoning) | 262k | Alibaba | 11* | -- | 9 | 0.99 | 56.67 | |
INTELLECT-3 | 131k |  Prime Intellect | 11* | -- | -- | -- | -- | |
Solar Open 100B | 128k | Upstage | 10* | -- | -- | -- | -- | |
Nemotron 3 Nano Omni 30B A3B | 256k | NVIDIA | 10* | -- | 240 | 0.75 | 11.18 | |
gpt-oss-120b (low) | 131k | OpenAI | 10* | -- | 235 | 0.87 | 11.50 | |
Nova 2.0 Pro Preview (non-reasoning) | 256k | Amazon | 10* | -- | 105 | 0.98 | 5.75 | |
gpt-oss-20b (low) | 131k | OpenAI | 10* | -- | 296 | 0.72 | 9.16 | |
North Mini Code | 256k | Cohere | 10 | $0.00 | 87 | 0.46 | 29.31 | |
K2-V2 (high) | 512k | Institute of Foundation Models | 10* | -- | -- | -- | -- | |
Qwen3 Next 80B A3B | 262k | Alibaba | 10* | -- | 115 | 0.89 | 5.24 | |
DiffusionGemma 26B A4B | 256k | Google | 10* | -- | -- | -- | -- | |
Gemma 4 12B (non-reasoning) | 262k | Google | 9* | -- | 120 | 2.34 | 6.50 | |
Llama 4 Maverick | 1M | Meta | 9 | $0.04 | 56 | 1.10 | 10.04 | |
Qwen3 Coder Next | 256k | Alibaba | 9 | $0.47 | 68 | 1.34 | 8.71 | |
Motif-2-12.7B | 128k | Motif Technologies | 9* | -- | -- | -- | -- | |
Nova Premier | 1M | Amazon | 9* | -- | -- | -- | -- | |
Granite 4.2 3B | 131k | IBM | 9 | $0.01 | 218 | 0.47 | 11.93 | |
K2-V2 (medium) | 512k | Institute of Foundation Models | 9* | -- | -- | -- | -- | |
Mistral Small 4 (non-reasoning) | 256k | Mistral | 9* | -- | 153 | 0.92 | 4.18 | |
Tri-21B-Think | 32k |  Trillion Labs | 9* | -- | -- | -- | -- | |
gpt-oss-20b (high) | 131k | OpenAI | 9 | $0.01 | 225 | 0.70 | 11.79 | |
Gemma 4 E4B | 128k | Google | 9 | $0.01 | 44 | 0.92 | 57.16 | |
Nemotron 3 Nano | 1M | NVIDIA | 9 | $0.02 | 230 | 0.96 | 11.82 | |
MiniCPM5-1B | 128k | OpenBMB | 9* | -- | -- | -- | -- | |
Sarvam 105B (high) | 128k |  Sarvam | 9* | -- | -- | -- | -- | |
Nova 2.0 Lite (non-reasoning) | 1M | Amazon | 9* | -- | 160 | 1.14 | 4.27 | |
MiniCPM5-1B (non-reasoning) | 128k | OpenBMB | 9* | -- | -- | -- | -- | |
Magistral Small 1.2 | 128k | Mistral | 9* | -- | 74 | 1.52 | 35.09 | |
Nanbeige4.1-3B | 256k |  Nanbeige | 8* | -- | -- | -- | -- | |
LFM2.5-2.6B | 128k |  Liquid AI | 8* | -- | -- | -- | -- | |
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* | -- | -- | -- | -- | |
Gemma 4 E2B | 128k | Google | 8* | -- | -- | -- | -- | |
Qwen3 Omni 30B A3B | 65.5k | Alibaba | 8* | -- | 101 | 1.92 | 26.66 | |
Step3 VL 10B | 65.5k | StepFun | 8* | -- | -- | -- | -- | |
Llama 3.3 70B | 128k | Meta | 8* | -- | 93 | 1.71 | 7.09 | |
Llama Nemotron Ultra | 128k | NVIDIA | 8* | -- | -- | -- | -- | |
ERNIE 4.5 300B A47B | 131k | Baidu | 8* | -- | -- | -- | -- | |
Hermes 4 405B | 128k | Nous Research | 7* | -- | 33 | 2.41 | 77.48 | |
NVIDIA Nemotron Nano 12B v2 VL | 128k | NVIDIA | 7* | -- | -- | -- | -- | |
Gemma 4 E4B (non-reasoning) | 128k | Google | 7* | -- | 44 | 0.81 | 12.27 | |
NVIDIA Nemotron Nano 9B V2 | 131k | NVIDIA | 7* | -- | 194 | 0.56 | 13.45 | |
Hermes 4 405B (non-reasoning) | 128k | Nous Research | 7* | -- | 31 | 2.29 | 18.52 | |
K2-V2 (low) | 512k | 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* | -- | 64 | 1.70 | 9.53 | |
Qwen3.5 2B | 262k | Alibaba | 7* | -- | -- | -- | -- | |
Nemotron 3 Nano (non-reasoning) | 1M | NVIDIA | 7* | -- | 256 | 0.55 | 2.50 | |
NVIDIA Nemotron Nano 9B V2 (non-reasoning) | 131k | NVIDIA | 7* | -- | 168 | 1.06 | 4.04 | |
Hermes 4 70B (non-reasoning) | 128k | Nous Research | 7* | -- | -- | -- | -- | |
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 | $0.11 | 86 | 0.96 | 6.80 | |
R1 1776 | 128k |  Perplexity | 6* | -- | -- | -- | -- | |
Llama 3.2 90B (Vision) | 128k | Meta | 6* | -- | -- | -- | -- | |
Celeris-1 | 131k | Celeris | 6 | $0.05 | 1,380 | 0.57 | 0.93 | |
Phi-4 Mini | 128k |  Microsoft | 6* | -- | 45 | 0.82 | 11.84 | |
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 (non-reasoning) | 32k | Nous Research | 6* | -- | -- | -- | -- | |
Jamba 1.7 Large | 256k |  AI21 Labs | 6* | -- | -- | -- | -- | |
Granite 4.0 H Small | 128k | IBM | 6* | -- | -- | -- | -- | |
Ministral 3 14B | 256k | Mistral | 6 | $0.02 | 89 | 1.02 | 6.60 | |
Qwen3 Omni 30B A3B | 65.5k | Alibaba | 6* | -- | 97 | 1.86 | 7.03 | |
LFM2 24B A2B | 32.8k | Liquid AI | 6* | -- | -- | -- | -- | |
Phi-4 | 16k | Microsoft | 6* | -- | 42 | 2.55 | 14.58 | |
Nova Micro | 130k | Amazon | 6* | -- | 298 | 0.84 | 2.52 | |
NVIDIA Nemotron Nano 12B v2 VL (non-reasoning) | 128k | NVIDIA | 6* | -- | 204 | 1.10 | 3.55 | |
Phi-4 Multimodal | 128k | Microsoft | 6* | -- | -- | -- | -- | |
MiniCPM-V 4.6 1.3B | 262k | OpenBMB | 6* | -- | -- | -- | -- | |
Jamba Reasoning 3B | 262k | AI21 Labs | 6* | -- | -- | -- | -- | |
Reka Flash 3 | 128k |  Reka AI | 6* | -- | 86 | 1.46 | 30.39 | |
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 | $0.01 | 102 | 0.81 | 5.69 | |
Llama 3.2 11B (Vision) | 128k | Meta | 5* | -- | 22 | 1.50 | 23.94 | |
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* | -- | -- | -- | -- | |
LFM2.5-1.2B-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 (non-reasoning) | 128k | Nous Research | 5* | -- | -- | -- | -- | |
Molmo2-8B | 36.9k | Allen Institute for AI | 5* | -- | -- | -- | -- | |
Ministral 3 3B | 256k | Mistral | 5 | $0.01 | 217 | 0.71 | 3.01 | |
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* | -- | 118 | 3.10 | 7.35 | |
Granite 4.0 H 350M | 32.8k | IBM | 5* | -- | -- | -- | -- | |
Nemotron 3 Nano 4B | 262k | NVIDIA | 5 | -- | -- | -- | -- | |
K2 Horizon 0.9B | 131k | Institute of Foundation Models | 3 | -- | -- | -- | -- | |
EXAONE 4.5 33B (non-reasoning) | 262k | LG AI Research | -- | -- | -- | -- | -- | |
GPT-6 Sol (Daybreak Blue, max) | 1.05M | OpenAI | -- | -- | -- | -- | -- | |
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 Opus 5.5 (Max, Default Fallback) belegt derzeit Platz 1 der Artificial Analysis LLM-Bestenliste. Das Modell erreicht im Intelligence Index einen Wert von 58; insgesamt werden 134 Modelle gelistet.
Die nach dem Intelligence Index führenden Modelle sind: 1. Claude Opus 5.5 (Max, Default Fallback) (58), 2. Claude Sonnet 5.5 (Max, Default Fallback) (56), 3. Claude Opus 5.5 (Xhigh, Default Fallback) (56), 4. Muse Wonder Full (Max) (56), 5. Claude Opus 5.5 (High, Default Fallback) (54).
Celeris-1 ist mit 1,380.4 Tokens pro Sekunde am schnellsten, gefolgt von Mercury 2.5 (777.1 t/s) und Gemini 3.5 Flash-Lite (448.9 t/s).
Gemma 4 31B (Reasoning) hat mit $0.00 die niedrigsten Kosten pro Aufgabe des Intelligence Index, gefolgt von Command A+ ($0.00) und Ling 3.0 Tiny ($0.00).
MiMo-V2.6-Pro ist mit einem Wert von 46 im Intelligence Index das am höchsten platzierte Modell mit offenen Gewichten. Von insgesamt 134 Modellen in der Bestenliste haben 67 offene Gewichte.
Die nach dem Intelligence Index führenden Modelle mit offenen Gewichten sind: 1. MiMo-V2.6-Pro (46), 2. GLM-5.3 (Max) (45), 3. Step 5 Preview (44).
Claude Opus 5.5 (Max, Default Fallback) führt mit einem Wert von 58 im Intelligence Index unter 122 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