Welches KI-Modell ist gerade das beste? Oben die schnellen Antworten, darunter die vollständigen Tabellen mit Quellen.
| Modell | Wert | Zusatzinfo |
|---|---|---|
|
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic Closed-API📰 4× News (7T) |
53.4 📎 | $160.00/Mtok |
|
GPT-6 Astra (max)OpenAI Closed-API📰 18× News (7T) |
52.8 📎 | $160.00/Mtok |
|
Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic Closed-API📰 1× News (7T) |
50.7 📎 | $80.00/Mtok |
|
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic Closed-API📰 4× News (7T) |
49.7 📎 | $160.00/Mtok |
|
Muse Spark 1.3 (max)Meta Open-Weights |
48.2 📎 | $14.00/Mtok |
|
GPT-5.6 Sol (max)OpenAI Closed-API📰 4× News (7T) |
47.1 📎 | $64.00/Mtok |
|
GLM-5.3 (max)Zhipu AI Open-Weights📰 2× News (7T) |
44.9 📎 | $14.60/Mtok |
|
Grok 4.6 (high)SpaceXAI Closed-API |
44.4 📎 | $20.00/Mtok |
|
Kimi K3 (max)Moonshot Open-Weights📰 1× News (7T) |
43.8 📎 | $48.00/Mtok |
|
DeepSeek V4 Pro (Reasoning, High Effort)DeepSeek Open-Weights |
43.7 📎 | $3.04/Mtok |
|
GPT-5.6 Terra (max)OpenAI Closed-API |
42.3 📎 | $38.00/Mtok |
|
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
42.0 📎 | $80.00/Mtok |
|
GLM-5.3-FlashZhipu AI Open-Weights📰 1× News (7T) |
41.9 📎 | $1.65/Mtok |
|
Gemini 3.8 Flash (high)Google Closed-API📰 3× News (7T) |
41.2 📎 | $12.00/Mtok |
|
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
40.7 📎 | $80.00/Mtok 📎 |
|
Qwen3.8 MaxAlibaba Open-Weights |
40.3 📎 | $20.00/Mtok |
|
Qwen3.8 2.4T A95BAlibaba Open-Weights |
40.0 📎 | $20.00/Mtok |
|
Qwen3.8-Flash-NextAlibaba Open-Weights |
39.9 📎 | $1.56/Mtok |
|
Muse Spark 1.2 (xhigh)Meta Open-Weights |
39.8 📎 | $14.00/Mtok |
|
Gemini 3.7 Flash (medium)Google Closed-API |
39.6 📎 | $12.00/Mtok |
|
DeepSeek V4.1 Flash (Reasoning, Max Effort)DeepSeek Open-Weights |
39.5 📎 | $3.90/Mtok |
|
Grok 4.5 (high)SpaceXAI Closed-API |
39.1 📎 | $20.00/Mtok |
|
GPT-5.4 (xhigh)OpenAI Closed-API |
39.0 📎 | $47.50/Mtok |
|
GPT-5.5 (xhigh)OpenAI Closed-API |
38.6 📎 | $95.00/Mtok 📎 |
|
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
38.4 📎 | $32.00/Mtok |
|
DeepSeek V4 Flash (Reasoning, High Effort)DeepSeek Open-Weights |
37.5 📎 | $0.98/Mtok |
|
GPT-5.6 Luna (max)OpenAI Closed-API |
37.5 📎 | $3.80/Mtok |
|
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek Open-WeightsMoEServer (880 GB) |
36.3 📎 | $13.20/Mtok 📎 |
|
JT-35B-FlashChina Mobile Closed-API |
36.1 📎 | $0.00/Mtok |
|
Agnes 3.0 FlashSapiens AI Closed-API |
35.5 📎 | $0.50/Mtok |
|
Agnes 2.5 Pro BetaSapiens AI Closed-API |
35.2 📎 | $1.00/Mtok |
|
DeepSeek V4 Flash Vision (Reasoning, Max Effort)DeepSeek Open-Weights |
35.0 📎 | $4.40/Mtok |
|
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek Open-WeightsMoE≤128 GB Unified (120 GB) |
34.5 📎 | $4.40/Mtok 📎 |
|
Gemini 3.6 Flash (high)Google Closed-API |
34.3 📎 | $12.00/Mtok |
|
Muse Spark 1.1 (xhigh)Meta Open-Weights |
34.3 📎 | $14.00/Mtok |
|
GLM-5.2 (max)Zhipu AI Open-Weights |
34.0 📎 | $14.60/Mtok |
|
Qwen3.8 27B (xhigh)Alibaba Open-Weights≤32 GB GPU (15 GB) |
33.9 📎 | $9.50/Mtok |
|
Gemini 3.5 Flash (medium)Google Closed-API |
33.6 📎 | $28.50/Mtok |
|
Motif 3Motif Technologies Closed-API |
33.6 📎 | $0.00/Mtok |
|
GPT-5.3 Codex (xhigh)OpenAI Closed-API |
32.5 📎 | $43.75/Mtok |
|
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
31.9 📎 | $80.00/Mtok |
|
Kimi K2.6Moonshot Open-WeightsMoEServer (584 GB) |
31.3 📎 | $12.95/Mtok 📎 |
|
Muse SparkMeta Open-Weights📰 1× News (7T) |
31.3 📎 | $0.00/Mtok |
|
K2 Horizon 375B A23BMBZUAI Institute of Foundation Models Open-Weights |
30.7 📎 | $0.00/Mtok |
|
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
30.5 📎 | $48.00/Mtok |
|
GPT-5.2 (xhigh)OpenAI Closed-API |
30.4 📎 | $43.75/Mtok |
|
Gemini 3.1 Pro PreviewGoogle Closed-API |
30.4 📎 | $38.00/Mtok |
|
Apodex 1.1Apodex Closed-API |
30.4 📎 | $9.30/Mtok |
|
Qwen3.7 MaxAlibaba Open-Weights |
29.9 📎 | $25.00/Mtok |
|
MiniMax-M3MiniMax Open-Weights |
29.6 📎 | $3.90/Mtok |
|
Claude Opus 4.5 (Reasoning)Anthropic Closed-API |
29.1 📎 | $80.00/Mtok |
|
MiMo-V2-ProXiaomi Open-Weights |
28.6 📎 | $0.00/Mtok |
|
GPT-5.2 Codex (xhigh)OpenAI Closed-API |
28.5 📎 | $43.75/Mtok |
|
Qwen3.6 Max PreviewAlibaba Open-Weights |
28.4 📎 | $24.70/Mtok |
|
Solar Pro 4Upstage Open-Weights |
28.2 📎 | $3.90/Mtok |
|
Nex-N2-ProNex AGI Closed-API |
28.2 📎 | $8.00/Mtok |
|
Gemini 3 Pro Preview (high)Google Closed-API |
28.0 📎 | $38.00/Mtok |
|
GLM-5 (Reasoning)Zhipu AI Open-WeightsMoEServer (241 GB)📰 2× News (7T) |
27.9 📎 | $10.60/Mtok 📎 |
|
Agnes 2.5 Pro AlphaSapiens AI Closed-API |
27.8 📎 | $3.15/Mtok |
|
JT-4.1 Flash 236B A21BChina Mobile Closed-API |
27.3 📎 | $0.00/Mtok |
|
Grok Build 0.1 0616xAI Closed-API |
27.2 📎 | $7.00/Mtok |
|
Quasar 438B (max, based on GLM-5.2)Multiverse Computing Closed-API |
27.1 📎 | $6.00/Mtok |
|
Qwen3.6 PlusAlibaba Open-Weights |
27.0 📎 | $9.50/Mtok |
|
GPT-5.5 Instant (June 2026)OpenAI Closed-API |
26.8 📎 | $95.00/Mtok |
|
GLM-5-TurboZhipu AI Open-Weights |
26.6 📎 | $0.00/Mtok |
|
MiMo-V2.5-ProXiaomi Open-Weights |
26.4 📎 | $3.04/Mtok |
|
GLM-5.1 (Reasoning)Zhipu AI Open-Weights |
26.4 📎 | $14.40/Mtok |
|
Gemini 3 Flash Preview (Reasoning)Google Closed-API |
26.3 📎 | $9.50/Mtok |
|
Kimi K2.7 CodeMoonshot Open-Weights |
26.3 📎 | $12.95/Mtok |
|
Inkling SmallThinking Machines Closed-API |
26.1 📎 | $3.90/Mtok |
|
Hy3Tencent Closed-API |
25.8 📎 | $1.80/Mtok |
|
Qwen3.7 PlusAlibaba Open-Weights |
25.8 📎 | $5.20/Mtok |
|
Grok 4.20 0309 v2 (Reasoning)xAI Closed-API |
25.7 📎 | $8.75/Mtok |
|
Inkling (xhigh)Thinking Machines Closed-API |
25.5 📎 | $13.15/Mtok |
|
Grok 4.3 (high)xAI Closed-API |
25.4 📎 | $8.75/Mtok |
|
Grok 4.20 0309 (Reasoning)xAI Closed-API |
25.2 📎 | $20.00/Mtok |
|
MiMo-V2-Omni-0327Xiaomi Open-Weights |
25.1 📎 | $0.00/Mtok |
|
Ling 3.0 FlashInclusionAI Open-Weights |
24.9 📎 | $0.73/Mtok |
|
GPT-5 Codex (high)OpenAI Closed-API |
24.9 📎 | $31.25/Mtok |
|
Ling-3.0-flash-VLInclusionAI Open-Weights |
24.8 📎 | $0.00/Mtok |
|
GPT-5.1 (high)OpenAI Closed-API |
24.7 📎 | $31.25/Mtok |
|
Solar Open2 250BUpstage Open-WeightsServer (141 GB) |
24.7 📎 | $0.00/Mtok |
|
GPT-5.4 mini (xhigh)OpenAI Closed-API |
24.6 📎 | $14.25/Mtok |
|
MiMo-V2-OmniXiaomi Open-Weights |
23.9 📎 | $0.00/Mtok |
|
Ling 3.0 TinyInclusionAI Open-Weights |
23.9 📎 | $0.00/Mtok |
|
GPT-5.1 Codex (high)OpenAI Closed-API |
23.7 📎 | $31.25/Mtok |
|
Kimi K2.5 (Reasoning)Moonshot Open-Weights |
23.5 📎 | $8.85/Mtok |
|
GLM 5V Turbo (Reasoning)Zhipu AI Open-Weights |
23.5 📎 | $0.00/Mtok |
|
Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA Open-WeightsMoEServer (309 GB) |
23.4 📎 | $8.40/Mtok |
|
MiniMax-M2.7MiniMax Open-Weights |
23.2 📎 | $3.90/Mtok |
|
GPT-5 (high)OpenAI Closed-API📰 5× News (7T) |
23.0 📎 | $31.25/Mtok |
|
Qwen3.5 27B (Reasoning)Alibaba Open-Weights≤32 GB GPU (15 GB) |
22.9 📎 | $7.50/Mtok |
|
MiniMax-M2.5MiniMax Open-Weights |
22.8 📎 | $3.90/Mtok |
|
Claude 4.1 Opus (Reasoning)Anthropic Closed-API |
22.8 📎 | $240.00/Mtok |
|
Hy3-preview (Reasoning)Tencent Closed-API |
22.7 📎 | $0.69/Mtok |
|
A.X-K2SK Telecom Closed-API |
22.7 📎 | $0.00/Mtok |
|
Gemini 3.5 Flash-LiteGoogle Closed-API |
22.7 📎 | $7.80/Mtok |
|
Grok 4xAI Closed-API |
22.5 📎 | $48.00/Mtok |
|
MiMo-V2-Flash (Feb 2026)Xiaomi Open-Weights |
22.4 📎 | $0.00/Mtok |
|
MiMo-V2.5Xiaomi Open-Weights |
22.3 📎 | $0.98/Mtok |
| Modell | Wert | Zusatzinfo |
|---|---|---|
|
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic Closed-API📰 4× News (7T) |
81.6 📎 | $160.00/Mtok |
|
GPT-5.6 Sol (xhigh)OpenAI Closed-API📰 4× News (7T) |
78.3 📎 | $64.00/Mtok |
|
Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic Closed-API📰 1× News (7T) |
78.0 📎 | $80.00/Mtok |
|
GPT-6 Astra (high)OpenAI Closed-API📰 18× News (7T) |
77.1 📎 | $160.00/Mtok |
|
Grok 4.6 (high)SpaceXAI Closed-API |
76.8 📎 | $20.00/Mtok |
|
GPT-5.6 Terra (max)OpenAI Closed-API |
76.7 📎 | $38.00/Mtok |
|
Muse Spark 1.3 (xhigh)Meta Open-Weights |
76.5 📎 | $14.00/Mtok |
|
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic Closed-API📰 4× News (7T) |
76.5 📎 | $160.00/Mtok |
|
Gemini 3.8 Flash (high)Google Closed-API📰 3× News (7T) |
76.3 📎 | $12.00/Mtok |
|
Kimi K3 (max)Moonshot Open-Weights📰 1× News (7T) |
76.2 📎 | $48.00/Mtok |
|
Gemini 3.7 Flash (high)Google Closed-API |
76.1 📎 | $12.00/Mtok |
|
GPT-5.5 (xhigh)OpenAI Closed-API |
74.9 📎 | $95.00/Mtok 📎 |
|
GLM-5.3 (max)Zhipu AI Open-Weights📰 2× News (7T) |
74.8 📎 | $14.60/Mtok |
|
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
74.3 📎 | $80.00/Mtok |
|
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
73.6 📎 | $80.00/Mtok 📎 |
|
Qwen3.8-Flash-NextAlibaba Open-Weights |
73.1 📎 | $1.56/Mtok |
|
Grok 4.5 (high)SpaceXAI Closed-API |
72.4 📎 | $20.00/Mtok |
|
Muse Spark 1.2 (xhigh)Meta Open-Weights |
72.2 📎 | $14.00/Mtok |
|
Qwen3.8 2.4T A95BAlibaba Open-Weights |
71.9 📎 | $20.00/Mtok |
|
Qwen3.8 MaxAlibaba Open-Weights |
71.8 📎 | $20.00/Mtok |
|
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
71.5 📎 | $32.00/Mtok |
|
GLM-5.3-FlashZhipu AI Open-Weights📰 1× News (7T) |
71.5 📎 | $1.65/Mtok |
|
GPT-5.6 Luna (max)OpenAI Closed-API |
71.4 📎 | $3.80/Mtok |
|
Muse Spark 1.1 (xhigh)Meta Open-Weights |
71.3 📎 | $14.00/Mtok |
|
GPT-5.4 (xhigh)OpenAI Closed-API |
71.1 📎 | $47.50/Mtok |
|
Gemini 3.5 Flash (high)Google Closed-API |
70.1 📎 | $28.50/Mtok |
|
Gemini 3.6 Flash (high)Google Closed-API |
69.2 📎 | $12.00/Mtok |
|
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek Open-WeightsMoE≤128 GB Unified (120 GB) |
69.1 📎 | $4.40/Mtok 📎 |
|
Gemini 3.1 Pro PreviewGoogle Closed-API |
68.8 📎 | $38.00/Mtok |
|
GLM-5.2 (max)Zhipu AI Open-Weights |
68.8 📎 | $14.60/Mtok |
|
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek Open-WeightsMoEServer (880 GB) |
68.8 📎 | $13.20/Mtok 📎 |
|
Qwen3.8 27B (xhigh)Alibaba Open-Weights≤32 GB GPU (15 GB) |
68.1 📎 | $9.50/Mtok |
|
Qwen3.7 MaxAlibaba Open-Weights |
66.0 📎 | $25.00/Mtok |
|
DeepSeek V4 Flash Vision (Reasoning, Max Effort)DeepSeek Open-Weights |
65.0 📎 | $4.40/Mtok |
|
Motif 3Motif Technologies Closed-API |
63.5 📎 | $0.00/Mtok |
|
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
63.0 📎 | $48.00/Mtok |
|
Agnes 2.5 Pro BetaSapiens AI Closed-API |
62.3 📎 | $1.00/Mtok |
|
Kimi K2.6Moonshot Open-WeightsMoEServer (584 GB) |
61.8 📎 | $12.95/Mtok 📎 |
|
K2 Horizon 375B A23BMBZUAI Institute of Foundation Models Open-Weights |
61.5 📎 | $0.00/Mtok |
|
Quasar 438B (max, based on GLM-5.2)Multiverse Computing Closed-API |
61.2 📎 | $6.00/Mtok |
|
Apodex 1.1Apodex Closed-API |
60.8 📎 | $9.30/Mtok |
|
Kimi K2.7 CodeMoonshot Open-Weights |
60.8 📎 | $12.95/Mtok |
|
MiMo-V2.5-ProXiaomi Open-Weights |
60.2 📎 | $3.04/Mtok |
|
KAT Coder Pro V2KwaiKAT Closed-API |
59.5 📎 | $3.90/Mtok |
|
DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek Open-Weights |
59.4 📎 | $3.04/Mtok |
|
Nex-N2-ProNex AGI Closed-API |
59.1 📎 | $8.00/Mtok |
|
KAT-Coder-Pro V1KwaiKAT Closed-API |
58.9 📎 | $0.00/Mtok |
|
Hy3Tencent Closed-API |
58.8 📎 | $1.80/Mtok |
|
Agnes 2.5 Pro AlphaSapiens AI Closed-API |
58.8 📎 | $3.15/Mtok |
|
MiniMax-M3MiniMax Open-Weights |
58.6 📎 | $3.90/Mtok |
|
Muse SparkMeta Open-Weights📰 1× News (7T) |
58.6 📎 | $0.00/Mtok |
|
Ling-3.0-flash-VLInclusionAI Open-Weights |
57.0 📎 | $0.00/Mtok |
|
MiMo-V2.5Xiaomi Open-Weights |
56.8 📎 | $0.98/Mtok |
|
DeepSeek V4 Flash (Reasoning, Max Effort)DeepSeek Open-Weights |
56.2 📎 | $0.97/Mtok |
|
GPT-5.4 nano (xhigh)OpenAI Closed-API |
56.1 📎 | $3.95/Mtok |
|
GPT-5.4 mini (xhigh)OpenAI Closed-API |
56.1 📎 | $14.25/Mtok |
|
Qwen3.7 PlusAlibaba Open-Weights |
55.9 📎 | $5.20/Mtok |
|
GLM-5.1 (Reasoning)Zhipu AI Open-Weights |
55.8 📎 | $14.40/Mtok |
|
Qwen3.6 PlusAlibaba Open-Weights |
54.5 📎 | $9.50/Mtok |
|
Qwen3.6 27B (Reasoning)Alibaba Open-Weights≤32 GB GPU (15 GB) |
53.7 📎 | $11.40/Mtok |
|
GPT-5.3 Codex (xhigh)OpenAI Closed-API |
53.1 📎 | $43.75/Mtok |
|
Inkling SmallThinking Machines Closed-API |
52.9 📎 | $3.90/Mtok |
|
Solar Pro 4Upstage Open-Weights |
52.7 📎 | $3.90/Mtok |
|
MiniMax-M2.7MiniMax Open-Weights |
52.6 📎 | $3.90/Mtok |
|
JT-4.1 Flash 236B A21BChina Mobile Closed-API |
52.4 📎 | $0.00/Mtok |
|
Inkling (xhigh)Thinking Machines Closed-API |
52.1 📎 | $13.15/Mtok |
|
Claude 4.5 Sonnet (Reasoning)Anthropic Closed-API |
52.1 📎 | $48.00/Mtok |
|
Grok Build 0.1 0616xAI Closed-API |
51.5 📎 | $7.00/Mtok |
|
Ling 3.0 FlashInclusionAI Open-Weights |
50.6 📎 | $0.73/Mtok |
|
MiMo-V2-Flash (Non-reasoning)Xiaomi Open-Weights |
49.8 📎 | $0.00/Mtok |
|
GPT-5.1 (high)OpenAI Closed-API |
49.4 📎 | $31.25/Mtok |
|
Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA Open-WeightsMoEServer (309 GB) |
49.3 📎 | $8.40/Mtok |
|
Gemini 3.5 Flash-LiteGoogle Closed-API |
49.3 📎 | $7.80/Mtok |
|
Muse Glimmer (high)Meta Open-Weights |
49.0 📎 | $4.85/Mtok |
|
GPT-5.2 (xhigh)OpenAI Closed-API |
48.7 📎 | $43.75/Mtok |
|
Qwen3.5 397B A17B (Reasoning)Alibaba Open-WeightsMoEServer (223 GB) |
48.2 📎 | $11.40/Mtok |
|
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
48.1 📎 | $80.00/Mtok |
|
Claude Opus 4.5 (Reasoning)Anthropic Closed-API |
47.8 📎 | $80.00/Mtok |
|
Mistral Medium 3.5Mistral Open-Weights |
46.9 📎 | $24.00/Mtok |
|
Kimi K2.5 (Reasoning)Moonshot Open-Weights |
46.8 📎 | $8.85/Mtok |
|
Gemini 2.5 Pro Preview (Mar' 25)Google Closed-API |
46.7 📎 | $0.00/Mtok |
|
Gemini 3 Pro Preview (high)Google Closed-API |
46.5 📎 | $38.00/Mtok |
|
GLM-4.6 (Reasoning)Zhipu AI Open-Weights |
45.8 📎 | $7.15/Mtok |
|
Qwen3.5 122B A10B (Reasoning)Alibaba Open-WeightsMoE≤128 GB Unified (69 GB) |
45.7 📎 | $10.00/Mtok |
|
GLM-4.7 (Reasoning)Zhipu AI Open-Weights |
45.3 📎 | $7.20/Mtok |
|
LongCat 2.0LongCat Closed-API |
45.3 📎 | $3.90/Mtok |
|
GPT-5.5 Instant (May 2026)OpenAI Closed-API |
45.1 📎 | $95.00/Mtok |
|
Solar Open2 250BUpstage Open-WeightsServer (141 GB) |
45.0 📎 | $0.00/Mtok |
|
Qwen3.6 Max PreviewAlibaba Open-Weights |
44.9 📎 | $24.70/Mtok |
|
DeepSeek V3.2 (Reasoning)DeepSeek Open-Weights |
44.2 📎 | $1.54/Mtok |
|
GLM-5 (Reasoning)Zhipu AI Open-WeightsMoEServer (241 GB)📰 2× News (7T) |
44.2 📎 | $10.60/Mtok 📎 |
|
Claude 4.5 Haiku (Reasoning)Anthropic Closed-API |
43.9 📎 | $16.00/Mtok |
|
DeepSeek V3.1 Terminus (Reasoning)DeepSeek Open-Weights |
43.5 📎 | $9.88/Mtok |
|
Gemma 4 31B (Reasoning)Google Closed-API |
43.4 📎 | $0.00/Mtok |
|
GPT-5.2 Codex (xhigh)OpenAI Closed-API |
43.0 📎 | $43.75/Mtok |
|
Ring-2.6-1TInclusionAI Open-Weights |
42.8 📎 | $7.80/Mtok |
|
Gemini 3 Flash Preview (Reasoning)Google Closed-API |
42.6 📎 | $9.50/Mtok |
|
Grok 4.20 0309 (Reasoning)xAI Closed-API |
42.2 📎 | $20.00/Mtok |
|
Grok 4.3 (high)xAI Closed-API |
42.2 📎 | $8.75/Mtok |
|
Qwen3.6 35B A3B (Reasoning)Alibaba Open-WeightsMoE≤32 GB GPU (20 GB) |
41.9 📎 | $7.12/Mtok |
| Modell | Wert | Zusatzinfo |
|---|---|---|
|
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic Closed-API📰 4× News (7T) |
58.0 📎 | $160.00/Mtok |
|
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)Anthropic Closed-API📰 1× News (7T) |
55.5 📎 | $80.00/Mtok |
|
GPT-6 Astra (max)OpenAI Closed-API📰 18× News (7T) |
51.5 📎 | $160.00/Mtok |
|
GLM-5.3-FlashZhipu AI Open-Weights📰 1× News (7T) |
51.2 📎 | $1.65/Mtok |
|
Grok 4.6 (medium)SpaceXAI Closed-API |
51.2 📎 | $20.00/Mtok |
|
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
44.3 📎 | $32.00/Mtok |
|
Muse Spark 1.2 (xhigh)Meta Open-Weights |
44.0 📎 | $14.00/Mtok |
|
GPT-5.6 Luna (max)OpenAI Closed-API |
42.7 📎 | $3.80/Mtok |
|
GPT-5.5 (xhigh)OpenAI Closed-API |
37.3 📎 | $95.00/Mtok 📎 |
|
Apodex 1.1Apodex Closed-API |
36.6 📎 | $9.30/Mtok |
|
Solar Pro 4Upstage Open-Weights |
33.6 📎 | $3.90/Mtok |
|
GPT-5.6 Sol (low)OpenAI Closed-API📰 4× News (7T) |
32.6 📎 | $64.00/Mtok |
|
GPT-5.6 Terra (medium)OpenAI Closed-API |
31.4 📎 | $38.00/Mtok |
|
Nex-N2-ProNex AGI Closed-API |
31.2 📎 | $8.00/Mtok |
|
MiniMax-M3MiniMax Open-Weights |
30.8 📎 | $3.90/Mtok |
|
Qwen3.8 27B (Non-reasoning)Alibaba Open-Weights≤32 GB GPU (15 GB) |
30.4 📎 | $9.50/Mtok |
|
Ling-3.0-flash-VLInclusionAI Open-Weights |
30.0 📎 | $0.00/Mtok |
|
Grok Build 0.1 0616xAI Closed-API |
28.9 📎 | $7.00/Mtok |
|
Gemini 3.5 Flash (high)Google Closed-API |
27.3 📎 | $28.50/Mtok |
|
GPT-5 (high)OpenAI Closed-API📰 5× News (7T) |
26.5 📎 | $31.25/Mtok |
|
MiniMax-M2.7MiniMax Open-Weights |
25.9 📎 | $3.90/Mtok |
|
Inkling (xhigh)Thinking Machines Closed-API |
24.3 📎 | $13.15/Mtok |
|
Qwen3.6 27B (Non-reasoning)Alibaba Open-Weights≤32 GB GPU (15 GB) |
23.6 📎 | $11.40/Mtok |
|
MiMo-V2.5-ProXiaomi Open-Weights |
22.7 📎 | $3.04/Mtok |
|
Kimi K2.6Moonshot Open-WeightsMoEServer (584 GB) |
22.1 📎 | $12.95/Mtok 📎 |
|
GPT-5.1 (high)OpenAI Closed-API |
21.6 📎 | $31.25/Mtok |
|
K-EXAONE 2.0LG AI Research Open-Weights |
19.7 📎 | $0.00/Mtok |
|
MiMo-V2.5Xiaomi Open-Weights |
17.4 📎 | $0.98/Mtok |
|
Qwen3.5 122B A10B (Non-reasoning)Alibaba Open-WeightsMoE≤128 GB Unified (69 GB) |
16.2 📎 | $10.00/Mtok |
|
Gemini 3.5 Flash-LiteGoogle Closed-API |
15.9 📎 | $7.80/Mtok |
|
Granite 4.2 30BIBM Open-Weights≤32 GB GPU (17 GB) |
13.9 📎 | $2.11/Mtok |
|
Qwen3.5 397B A17B (Reasoning)Alibaba Open-WeightsMoEServer (223 GB) |
10.6 📎 | $11.40/Mtok |
|
GPT-5 mini (high)OpenAI Closed-API |
8.9 📎 | $6.25/Mtok |
|
DeepSeek V3.1 Terminus (Reasoning)DeepSeek Open-Weights |
8.9 📎 | $9.88/Mtok |
|
Qwen3.5 9B (Reasoning)Alibaba Open-Weights≤32 GB GPU (5 GB) |
7.0 📎 | $0.74/Mtok |
|
Nemotron 3.5 LightningNVIDIA Open-Weights |
6.1 📎 | $0.66/Mtok |
|
Devstral 2Mistral Open-Weights |
4.9 📎 | $0.00/Mtok |
|
Mercury 2Inception Closed-API |
4.0 📎 | $2.50/Mtok |
|
Command A+Cohere Closed-API |
3.6 📎 | $0.00/Mtok |
|
Gemini 2.5 ProGoogle Closed-API |
3.5 📎 | $31.25/Mtok |
|
Mistral Medium 3.1Mistral Open-Weights |
3.1 📎 | $6.40/Mtok |
|
HyperNova 60B 2605 (high, based on gpt-oss-120b)Multiverse Computing Closed-API |
2.7 📎 | $0.46/Mtok |
|
Mistral Large 3Mistral Closed-API |
2.4 📎 | $5.00/Mtok 📎 |
|
Mistral Small 3.1Mistral Open-Weights |
2.1 📎 | $1.00/Mtok |
|
Mistral Small 4 (Reasoning)Mistral Open-Weights |
1.4 📎 | $1.95/Mtok |
|
gpt-oss-20b (high)OpenAI Closed-API |
1.4 📎 | $0.63/Mtok |
|
DeepSeek R1 (Jan '25)DeepSeek Open-Weights |
1.1 📎 | $14.00/Mtok |
|
North Mini CodeCohere Closed-API |
1.1 📎 | $0.00/Mtok |
|
Mistral Small 3.2Mistral Open-Weights |
1.0 📎 | $1.00/Mtok |
|
o3-mini (high)OpenAI Closed-API |
0.9 📎 | $14.30/Mtok |
|
Qwen3 14B (Reasoning)Alibaba Open-Weights≤32 GB GPU (8 GB) |
0.9 📎 | $12.95/Mtok |
|
Granite 4.2 3BIBM Open-Weights≤32 GB GPU (2 GB) |
0.9 📎 | $0.39/Mtok |
|
DeepSeek V3 (Dec '24)DeepSeek Open-Weights |
0.8 📎 | $2.99/Mtok |
|
Gemma 3 12B InstructGoogle Closed-API |
0.1 📎 | $0.00/Mtok |
|
Gemma 3 27B InstructGoogle Closed-API |
0.1 📎 | $0.00/Mtok |
| Modell | Wert | Zusatzinfo |
|---|---|---|
|
Agnes 2.5 Pro BetaSapiens AI Closed-API |
62.30 📎 | AA Coding Index 62.3, $1.00/Mtok blended |
|
HyperNova 60B 2605 (high, based on gpt-oss-120b)Multiverse Computing Closed-API |
50.43 📎 | AA Coding Index 23.2, $0.46/Mtok blended |
|
Hy3-preview (Non-reasoning)Tencent Closed-API |
49.49 📎 | AA Coding Index 34.3, $0.69/Mtok blended |
|
Step 3.5 Flash 2603StepFun Closed-API |
34.60 📎 | AA Coding Index 34.6, $1.00/Mtok blended |
|
gpt-oss-20b (high)OpenAI Closed-API |
32.86 📎 | AA Coding Index 20.7, $0.63/Mtok blended |
|
Hy3Tencent Closed-API |
32.70 📎 | AA Coding Index 58.8, $1.80/Mtok blended |
|
Gemma 4 26B A4B (Reasoning)Google Closed-API |
32.08 📎 | AA Coding Index 39.3, $1.22/Mtok blended |
|
Step 3.5 FlashStepFun Closed-API |
31.60 📎 | AA Coding Index 31.6, $1.00/Mtok blended |
|
Gemma 4 12B (Reasoning)Google Closed-API |
31.00 📎 | AA Coding Index 31.0, $1.00/Mtok blended |
|
Gemma 4 E4B (Reasoning)Google Closed-API |
29.37 📎 | AA Coding Index 9.4, $0.32/Mtok blended |
|
Gemma 4 31B (Non-reasoning)Google Closed-API |
24.78 📎 | AA Coding Index 33.2, $1.34/Mtok blended |
|
Sarvam 30B (high)Sarvam Closed-API |
22.19 📎 | AA Coding Index 7.9, $0.36/Mtok blended |
|
GPT-5.6 Luna (max)OpenAI Closed-API |
18.79 📎 | AA Coding Index 71.4, $3.80/Mtok blended |
|
Agnes 2.5 Pro AlphaSapiens AI Closed-API |
18.67 📎 | AA Coding Index 58.8, $3.15/Mtok blended |
|
GPT-5 nano (medium)OpenAI Closed-API |
18.32 📎 | AA Coding Index 22.9, $1.25/Mtok blended |
|
Sarvam 105B (high)Sarvam Closed-API |
17.75 📎 | AA Coding Index 9.8, $0.55/Mtok blended |
|
Grok 4 Fast (Reasoning)xAI Closed-API |
16.12 📎 | AA Coding Index 27.4, $1.70/Mtok blended |
|
gpt-oss-120b (high)OpenAI Closed-API |
15.71 📎 | AA Coding Index 30.4, $1.93/Mtok blended |
|
KAT Coder Pro V2KwaiKAT Closed-API |
15.26 📎 | AA Coding Index 59.5, $3.90/Mtok blended |
|
GPT-5.4 nano (xhigh)OpenAI Closed-API |
14.20 📎 | AA Coding Index 56.1, $3.95/Mtok blended |
|
Grok 3 mini Reasoning (high)xAI Closed-API |
14.00 📎 | AA Coding Index 25.2, $1.80/Mtok blended |
|
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)Google Closed-API |
14.00 📎 | AA Coding Index 18.2, $1.30/Mtok blended |
|
Inkling SmallThinking Machines Closed-API |
13.56 📎 | AA Coding Index 52.9, $3.90/Mtok blended |
|
Mercury 2Inception Closed-API |
12.44 📎 | AA Coding Index 31.1, $2.50/Mtok blended |
|
LongCat 2.0LongCat Closed-API |
11.62 📎 | AA Coding Index 45.3, $3.90/Mtok blended |
|
Step 3.7 FlashStepFun Closed-API |
10.85 📎 | AA Coding Index 39.6, $3.65/Mtok blended |
|
Quasar 438B (max, based on GLM-5.2)Multiverse Computing Closed-API |
10.20 📎 | AA Coding Index 61.2, $6.00/Mtok blended |
|
Nova MicroAmazon Closed-API |
9.01 📎 | AA Coding Index 4.1, $0.46/Mtok blended |
|
Trinity Large ThinkingArcee AI Closed-API |
8.75 📎 | AA Coding Index 25.8, $2.95/Mtok blended |
|
Seed-OSS-36B-InstructByteDance Seed Closed-API |
8.70 📎 | AA Coding Index 16.7, $1.92/Mtok blended |
|
GPT-4.1 nanoOpenAI Closed-API |
8.54 📎 | AA Coding Index 11.1, $1.30/Mtok blended |
|
Nex-N2-ProNex AGI Closed-API |
7.39 📎 | AA Coding Index 59.1, $8.00/Mtok blended |
|
Grok Build 0.1 0616xAI Closed-API |
7.36 📎 | AA Coding Index 51.5, $7.00/Mtok blended |
|
Gemini 2.5 Flash-Lite (Reasoning)Google Closed-API |
7.31 📎 | AA Coding Index 9.5, $1.30/Mtok blended |
|
Gemini 3.1 Flash-LiteGoogle Closed-API |
7.31 📎 | AA Coding Index 34.7, $4.75/Mtok blended |
|
Nova LiteAmazon Closed-API |
6.54 📎 | AA Coding Index 5.1, $0.78/Mtok blended |
|
Apodex 1.1Apodex Closed-API |
6.54 📎 | AA Coding Index 60.8, $9.30/Mtok blended |
|
Gemini 3.8 Flash (high)Google Closed-API📰 3× News (7T) |
6.36 📎 | AA Coding Index 76.3, $12.00/Mtok blended |
|
Gemini 3.7 Flash (high)Google Closed-API |
6.34 📎 | AA Coding Index 76.1, $12.00/Mtok blended |
|
Gemini 3.5 Flash-LiteGoogle Closed-API |
6.32 📎 | AA Coding Index 49.3, $7.80/Mtok blended |
|
Celeris-1Celeris Closed-API |
6.26 📎 | AA Coding Index 14.4, $2.30/Mtok blended |
|
GPT-4o miniOpenAI Closed-API |
5.85 📎 | AA Coding Index 11.4, $1.95/Mtok blended |
|
GPT-5.1 Codex mini (high)OpenAI Closed-API |
5.82 📎 | AA Coding Index 36.4, $6.25/Mtok blended |
|
Gemini 3.6 Flash (high)Google Closed-API |
5.77 📎 | AA Coding Index 69.2, $12.00/Mtok blended |
|
GPT-5 mini (medium)OpenAI Closed-API |
5.25 📎 | AA Coding Index 32.8, $6.25/Mtok blended |
|
Cogito v2.1 (Reasoning)Deep Cogito Closed-API |
4.96 📎 | AA Coding Index 24.8, $5.00/Mtok blended |
|
Grok 4.3 (high)xAI Closed-API |
4.82 📎 | AA Coding Index 42.2, $8.75/Mtok blended |
|
Grok 4.20 0309 v2 (Reasoning)xAI Closed-API |
4.63 📎 | AA Coding Index 40.5, $8.75/Mtok blended |
|
Gemini 3 Flash Preview (Reasoning)Google Closed-API |
4.48 📎 | AA Coding Index 42.6, $9.50/Mtok blended |
|
ERNIE 4.5 300B A47BBaidu Closed-API |
4.05 📎 | AA Coding Index 14.5, $3.58/Mtok blended |
|
Mistral Large 3Mistral Closed-API |
4.02 📎 | AA Coding Index 20.1, $5.00/Mtok blended 📎 |
|
Inkling (xhigh)Thinking Machines Closed-API |
3.96 📎 | AA Coding Index 52.1, $13.15/Mtok blended |
|
GPT-5.4 mini (xhigh)OpenAI Closed-API |
3.94 📎 | AA Coding Index 56.1, $14.25/Mtok blended |
|
GPT-4.1 miniOpenAI Closed-API |
3.88 📎 | AA Coding Index 20.2, $5.20/Mtok blended |
|
Grok 4.6 (high)SpaceXAI Closed-API |
3.84 📎 | AA Coding Index 76.8, $20.00/Mtok blended |
|
Grok 4.5 (high)SpaceXAI Closed-API |
3.62 📎 | AA Coding Index 72.4, $20.00/Mtok blended |
|
Reka Flash 3Reka AI Closed-API |
3.42 📎 | AA Coding Index 8.9, $2.60/Mtok blended |
|
Nova 2.0 Lite (medium)Amazon Closed-API |
3.06 📎 | AA Coding Index 23.9, $7.80/Mtok blended |
|
Gemini 2.5 Flash (Reasoning)Google Closed-API |
2.85 📎 | AA Coding Index 22.2, $7.80/Mtok blended |
|
Claude 4.5 Haiku (Reasoning)Anthropic Closed-API |
2.74 📎 | AA Coding Index 43.9, $16.00/Mtok blended |
|
Gemini 3.5 Flash (high)Google Closed-API |
2.46 📎 | AA Coding Index 70.1, $28.50/Mtok blended |
|
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
2.23 📎 | AA Coding Index 71.5, $32.00/Mtok blended |
|
GPT-3.5 TurboOpenAI Closed-API |
2.14 📎 | AA Coding Index 10.7, $5.00/Mtok blended |
|
Grok 4.20 0309 (Reasoning)xAI Closed-API |
2.11 📎 | AA Coding Index 42.2, $20.00/Mtok blended |
|
GPT-5.6 Terra (max)OpenAI Closed-API |
2.02 📎 | AA Coding Index 76.7, $38.00/Mtok blended |
|
Apertus 8B InstructSwiss AI Initiative Closed-API |
2.00 📎 | AA Coding Index 1.4, $0.70/Mtok blended |
|
Nova 2.0 Omni (medium)Amazon Closed-API |
1.94 📎 | AA Coding Index 15.1, $7.80/Mtok blended |
|
Gemini 3.1 Pro PreviewGoogle Closed-API |
1.81 📎 | AA Coding Index 68.8, $38.00/Mtok blended |
|
o4-mini (high)OpenAI Closed-API |
1.79 📎 | AA Coding Index 25.6, $14.30/Mtok blended |
|
Claude 3 HaikuAnthropic Closed-API |
1.68 📎 | AA Coding Index 6.7, $4.00/Mtok blended |
|
GPT-5.1 (high)OpenAI Closed-API |
1.58 📎 | AA Coding Index 49.4, $31.25/Mtok blended |
|
GPT-5.4 (xhigh)OpenAI Closed-API |
1.50 📎 | AA Coding Index 71.1, $47.50/Mtok blended |
|
o3OpenAI Closed-API |
1.48 📎 | AA Coding Index 38.4, $26.00/Mtok blended |
|
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
1.31 📎 | AA Coding Index 63.0, $48.00/Mtok blended |
|
o3-miniOpenAI Closed-API |
1.25 📎 | AA Coding Index 17.9, $14.30/Mtok blended |
|
GPT-5 Codex (high)OpenAI Closed-API |
1.24 📎 | AA Coding Index 38.9, $31.25/Mtok blended |
|
GPT-5 (medium)OpenAI Closed-API📰 5× News (7T) |
1.24 📎 | AA Coding Index 38.9, $31.25/Mtok blended |
|
Gemini 3 Pro Preview (high)Google Closed-API |
1.22 📎 | AA Coding Index 46.5, $38.00/Mtok blended |
|
GPT-5.6 Sol (xhigh)OpenAI Closed-API📰 4× News (7T) |
1.22 📎 | AA Coding Index 78.3, $64.00/Mtok blended |
|
GPT-5.3 Codex (xhigh)OpenAI Closed-API |
1.21 📎 | AA Coding Index 53.1, $43.75/Mtok blended |
|
GPT-5.1 Codex (high)OpenAI Closed-API |
1.17 📎 | AA Coding Index 36.6, $31.25/Mtok blended |
|
GPT-5.2 (xhigh)OpenAI Closed-API |
1.11 📎 | AA Coding Index 48.7, $43.75/Mtok blended |
|
Nova 2.0 Pro Preview (medium)Amazon Closed-API |
1.09 📎 | AA Coding Index 34.0, $31.25/Mtok blended |
|
Claude 4.5 Sonnet (Reasoning)Anthropic Closed-API |
1.09 📎 | AA Coding Index 52.1, $48.00/Mtok blended |
|
Gemini 2.5 ProGoogle Closed-API |
1.07 📎 | AA Coding Index 33.3, $31.25/Mtok blended |
|
Nova ProAmazon Closed-API |
1.06 📎 | AA Coding Index 11.0, $10.40/Mtok blended |
|
GPT-5.2 Codex (xhigh)OpenAI Closed-API |
0.98 📎 | AA Coding Index 43.0, $43.75/Mtok blended |
|
Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic Closed-API📰 1× News (7T) |
0.97 📎 | AA Coding Index 78.0, $80.00/Mtok blended |
|
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
0.93 📎 | AA Coding Index 74.3, $80.00/Mtok blended |
|
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
0.92 📎 | AA Coding Index 73.6, $80.00/Mtok blended 📎 |
|
Grok 4xAI Closed-API |
0.84 📎 | AA Coding Index 40.5, $48.00/Mtok blended |
|
GPT-4.1OpenAI Closed-API |
0.84 📎 | AA Coding Index 21.8, $26.00/Mtok blended |
|
GPT-5.5 (xhigh)OpenAI Closed-API |
0.79 📎 | AA Coding Index 74.9, $95.00/Mtok blended 📎 |
|
Claude 4 Sonnet (Reasoning)Anthropic Closed-API |
0.78 📎 | AA Coding Index 37.6, $48.00/Mtok blended |
|
Claude 3.5 Sonnet (Oct '24)Anthropic Closed-API |
0.63 📎 | AA Coding Index 30.2, $48.00/Mtok blended |
|
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)Anthropic Closed-API |
0.60 📎 | AA Coding Index 48.1, $80.00/Mtok blended |
|
Claude Opus 4.5 (Reasoning)Anthropic Closed-API |
0.60 📎 | AA Coding Index 47.8, $80.00/Mtok blended |
|
Claude 3.7 Sonnet (Non-reasoning)Anthropic Closed-API |
0.56 📎 | AA Coding Index 26.7, $48.00/Mtok blended |
|
GPT-4o (Nov '24)OpenAI Closed-API |
0.51 📎 | AA Coding Index 16.7, $32.50/Mtok blended |
|
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic Closed-API📰 4× News (7T) |
0.51 📎 | AA Coding Index 81.6, $160.00/Mtok blended |
| Modell | Wert | Zusatzinfo |
|---|---|---|
|
Muse Spark 1.3 (max)Meta Open-Weights |
48.2 📎 | $14.00/Mtok |
|
GLM-5.3 (max)Zhipu AI Open-Weights📰 2× News (7T) |
44.9 📎 | $14.60/Mtok |
|
Kimi K3 (max)Moonshot Open-Weights📰 1× News (7T) |
43.8 📎 | $48.00/Mtok |
|
DeepSeek V4 Pro (Reasoning, High Effort)DeepSeek Open-Weights |
43.7 📎 | $3.04/Mtok |
|
GLM-5.3-FlashZhipu AI Open-Weights📰 1× News (7T) |
41.9 📎 | $1.65/Mtok |
|
Qwen3.8 MaxAlibaba Open-Weights |
40.3 📎 | $20.00/Mtok |
|
Qwen3.8 2.4T A95BAlibaba Open-Weights |
40.0 📎 | $20.00/Mtok |
|
Qwen3.8-Flash-NextAlibaba Open-Weights |
39.9 📎 | $1.56/Mtok |
|
Muse Spark 1.2 (xhigh)Meta Open-Weights |
39.8 📎 | $14.00/Mtok |
|
DeepSeek V4.1 Flash (Reasoning, Max Effort)DeepSeek Open-Weights |
39.5 📎 | $3.90/Mtok |
|
DeepSeek V4 Flash (Reasoning, High Effort)DeepSeek Open-Weights |
37.5 📎 | $0.98/Mtok |
|
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek Open-WeightsMoEServer (880 GB) |
36.3 📎 | $13.20/Mtok 📎 |
|
DeepSeek V4 Flash Vision (Reasoning, Max Effort)DeepSeek Open-Weights |
35.0 📎 | $4.40/Mtok |
|
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek Open-WeightsMoE≤128 GB Unified (120 GB) |
34.5 📎 | $4.40/Mtok 📎 |
|
Muse Spark 1.1 (xhigh)Meta Open-Weights |
34.3 📎 | $14.00/Mtok |
|
GLM-5.2 (max)Zhipu AI Open-Weights |
34.0 📎 | $14.60/Mtok |
|
Qwen3.8 27B (xhigh)Alibaba Open-Weights≤32 GB GPU (15 GB) |
33.9 📎 | $9.50/Mtok |
|
Kimi K2.6Moonshot Open-WeightsMoEServer (584 GB) |
31.3 📎 | $12.95/Mtok 📎 |
|
Muse SparkMeta Open-Weights📰 1× News (7T) |
31.3 📎 | $0.00/Mtok |
|
K2 Horizon 375B A23BMBZUAI Institute of Foundation Models Open-Weights |
30.7 📎 | $0.00/Mtok |
|
Qwen3.7 MaxAlibaba Open-Weights |
29.9 📎 | $25.00/Mtok |
|
MiniMax-M3MiniMax Open-Weights |
29.6 📎 | $3.90/Mtok |
|
MiMo-V2-ProXiaomi Open-Weights |
28.6 📎 | $0.00/Mtok |
|
Qwen3.6 Max PreviewAlibaba Open-Weights |
28.4 📎 | $24.70/Mtok |
|
Solar Pro 4Upstage Open-Weights |
28.2 📎 | $3.90/Mtok |
|
GLM-5 (Reasoning)Zhipu AI Open-WeightsMoEServer (241 GB)📰 2× News (7T) |
27.9 📎 | $10.60/Mtok 📎 |
|
Qwen3.6 PlusAlibaba Open-Weights |
27.0 📎 | $9.50/Mtok |
|
GLM-5-TurboZhipu AI Open-Weights |
26.6 📎 | $0.00/Mtok |
|
MiMo-V2.5-ProXiaomi Open-Weights |
26.4 📎 | $3.04/Mtok |
|
GLM-5.1 (Reasoning)Zhipu AI Open-Weights |
26.4 📎 | $14.40/Mtok |
|
Kimi K2.7 CodeMoonshot Open-Weights |
26.3 📎 | $12.95/Mtok |
|
Qwen3.7 PlusAlibaba Open-Weights |
25.8 📎 | $5.20/Mtok |
|
MiMo-V2-Omni-0327Xiaomi Open-Weights |
25.1 📎 | $0.00/Mtok |
|
Ling 3.0 FlashInclusionAI Open-Weights |
24.9 📎 | $0.73/Mtok |
|
Ling-3.0-flash-VLInclusionAI Open-Weights |
24.8 📎 | $0.00/Mtok |
|
Solar Open2 250BUpstage Open-WeightsServer (141 GB) |
24.7 📎 | $0.00/Mtok |
|
Ling 3.0 TinyInclusionAI Open-Weights |
23.9 📎 | $0.00/Mtok |
|
MiMo-V2-OmniXiaomi Open-Weights |
23.9 📎 | $0.00/Mtok |
|
Kimi K2.5 (Reasoning)Moonshot Open-Weights |
23.5 📎 | $8.85/Mtok |
|
GLM 5V Turbo (Reasoning)Zhipu AI Open-Weights |
23.5 📎 | $0.00/Mtok |
|
Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA Open-WeightsMoEServer (309 GB) |
23.4 📎 | $8.40/Mtok |
|
MiniMax-M2.7MiniMax Open-Weights |
23.2 📎 | $3.90/Mtok |
|
Qwen3.5 27B (Reasoning)Alibaba Open-Weights≤32 GB GPU (15 GB) |
22.9 📎 | $7.50/Mtok |
|
MiniMax-M2.5MiniMax Open-Weights |
22.8 📎 | $3.90/Mtok |
|
MiMo-V2-Flash (Feb 2026)Xiaomi Open-Weights |
22.4 📎 | $0.00/Mtok |
|
MiMo-V2.5Xiaomi Open-Weights |
22.3 📎 | $0.98/Mtok |
|
GLM-4.7 (Reasoning)Zhipu AI Open-Weights |
22.2 📎 | $7.20/Mtok |
|
Kimi K2 ThinkingMoonshot Open-Weights |
22.0 📎 | $8.10/Mtok |
|
Qwen3.6 27B (Reasoning)Alibaba Open-Weights≤32 GB GPU (15 GB) |
21.9 📎 | $11.40/Mtok |
|
DeepSeek V3.2 (Reasoning)DeepSeek Open-Weights |
21.5 📎 | $1.54/Mtok |
|
Qwen3.5 397B A17B (Non-reasoning)Alibaba Open-WeightsMoEServer (223 GB) |
21.4 📎 | $11.40/Mtok |
|
Qwen3 Max ThinkingAlibaba Open-Weights |
21.3 📎 | $0.00/Mtok |
|
MiniMax-M2.1MiniMax Open-Weights |
20.9 📎 | $3.90/Mtok |
|
Qwen3.5 Omni PlusAlibaba Open-Weights |
20.4 📎 | $14.80/Mtok |
|
K-EXAONE 2.0LG AI Research Open-Weights |
19.7 📎 | $0.00/Mtok |
|
Qwen3.5 35B A3B (Reasoning)Alibaba Open-WeightsMoE≤32 GB GPU (20 GB) |
19.3 📎 | $6.25/Mtok |
|
Qwen3.6 35B A3B (Reasoning)Alibaba Open-WeightsMoE≤32 GB GPU (20 GB) |
18.8 📎 | $7.12/Mtok |
|
MiniMax-M2MiniMax Open-Weights |
18.6 📎 | $3.90/Mtok |
|
GLM-4.6 (Reasoning)Zhipu AI Open-Weights |
18.5 📎 | $7.15/Mtok |
|
Muse Glimmer (high)Meta Open-Weights |
18.1 📎 | $4.85/Mtok |
|
Qwen3.5 122B A10B (Non-reasoning)Alibaba Open-WeightsMoE≤128 GB Unified (69 GB) |
17.7 📎 | $10.00/Mtok |
|
Ring-2.6-1TInclusionAI Open-Weights |
17.3 📎 | $7.80/Mtok |
|
Ling-2.6-1TInclusionAI Open-Weights |
17.0 📎 | $7.80/Mtok |
|
DeepSeek V3.2 Exp (Reasoning)DeepSeek Open-Weights |
16.6 📎 | $1.54/Mtok |
|
Qwen3 MaxAlibaba Open-Weights |
15.6 📎 | $19.20/Mtok |
|
DeepSeek V3.1 Terminus (Reasoning)DeepSeek Open-Weights |
15.4 📎 | $9.88/Mtok |
|
Kimi K2 0905Moonshot Open-Weights |
15.3 📎 | $8.10/Mtok |
|
GLM-4.7-Flash (Reasoning)Zhipu AI Open-Weights |
14.9 📎 | $1.27/Mtok |
|
Mistral Medium 3.5Mistral Open-Weights |
14.9 📎 | $24.00/Mtok |
|
Granite 4.2 30BIBM Open-Weights≤32 GB GPU (17 GB) |
14.8 📎 | $2.11/Mtok |
|
DeepSeek V3.2 SpecialeDeepSeek Open-Weights |
14.5 📎 | $0.00/Mtok |
|
K-EXAONE (Reasoning)LG AI Research Open-Weights |
14.4 📎 | $0.00/Mtok |
|
Qwen3.5 9B (Reasoning)Alibaba Open-Weights≤32 GB GPU (5 GB) |
13.7 📎 | $0.74/Mtok |
|
DeepSeek V3.1 (Non-reasoning)DeepSeek Open-Weights |
13.7 📎 | $5.61/Mtok |
|
Nemotron 3 Super 120B A12B (Reasoning)NVIDIA Open-WeightsMoE≤128 GB Unified (68 GB) |
13.6 📎 | $2.14/Mtok |
|
Nemotron 3.5 LightningNVIDIA Open-Weights |
13.6 📎 | $0.66/Mtok |
|
Qwen3 VL 235B A22B (Reasoning)Alibaba Open-WeightsMoEServer (132 GB) |
13.4 📎 | $12.40/Mtok |
|
EXAONE 4.5 33BLG AI Research Open-Weights≤32 GB GPU (19 GB) |
13.2 📎 | $0.00/Mtok |
|
DeepSeek R1 0528 (May '25)DeepSeek Open-Weights |
13.1 📎 | $10.35/Mtok |
|
Qwen3.5 4B (Reasoning)Alibaba Open-Weights≤32 GB GPU (2 GB) |
13.1 📎 | $0.48/Mtok |
|
GLM-4.5 (Reasoning)Zhipu AI Open-Weights |
12.8 📎 | $0.00/Mtok |
|
Kimi K2Moonshot Open-Weights |
12.7 📎 | $7.47/Mtok |
|
Qwen3 235B A22B 2507 (Reasoning)Alibaba Open-WeightsMoEServer (132 GB) |
12.7 📎 | $7.13/Mtok |
|
Qwen3.5 Omni FlashAlibaba Open-Weights |
12.5 📎 | $2.50/Mtok |
|
Qwen3 235B A22B 2507 InstructAlibaba Open-WeightsMoEServer (132 GB) |
12.0 📎 | $2.99/Mtok |
|
Qwen3 Coder 480B A35B InstructAlibaba Open-WeightsMoEServer (270 GB) |
11.9 📎 | $24.00/Mtok |
|
Qwen3 VL 32B (Reasoning)Alibaba Open-Weights≤32 GB GPU (18 GB) |
11.9 📎 | $2.08/Mtok |
|
Magistral Medium 1.2Mistral Open-Weights |
11.8 📎 | $0.00/Mtok |
|
Granite 4.2 8BIBM Open-Weights≤32 GB GPU (4 GB) |
11.8 📎 | $0.81/Mtok |
|
Nemotron Cascade 2 30B A3BNVIDIA Open-WeightsMoE≤32 GB GPU (17 GB) |
11.7 📎 | $0.00/Mtok |
|
MiniMax M1 80kMiniMax Open-Weights |
11.7 📎 | $7.15/Mtok |
|
Mistral Small 4 (Reasoning)Mistral Open-Weights |
11.5 📎 | $1.95/Mtok |
|
K2 Think V2MBZUAI Institute of Foundation Models Open-Weights |
11.5 📎 | $0.00/Mtok |
|
DeepSeek R1 (Jan '25)DeepSeek Open-Weights |
11.4 📎 | $14.00/Mtok |
|
Qwen3 Next 80B A3B (Reasoning)Alibaba Open-WeightsMoE≤128 GB Unified (45 GB) |
11.2 📎 | $3.75/Mtok |
|
GLM-4.6V (Reasoning)Zhipu AI Open-Weights |
11.2 📎 | $3.00/Mtok |
|
GLM-4.5-AirZhipu AI Open-Weights |
11.1 📎 | $3.11/Mtok |
|
Ring-1TInclusionAI Open-Weights |
10.9 📎 | $0.00/Mtok |
|
Solar Open 100B (Reasoning)Upstage Open-Weights≤128 GB Unified (56 GB) |
10.4 📎 | $0.00/Mtok |
|
Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA Open-WeightsMoE≤32 GB GPU (17 GB) |
10.3 📎 | $1.17/Mtok |
| Modell | Coding-Index | Memory |
|---|---|---|
|
Qwen3.5 9B (Reasoning)Alibaba Open-Weights≤32 GB GPU (5 GB) |
28.7 📎 | Q4: 5 GB (geschätzt) 📎 |
|
Qwen3.5 4B (Reasoning)Alibaba Open-Weights≤32 GB GPU (2 GB) |
22.6 📎 | Q4: 2 GB (geschätzt) 📎 |
|
Granite 4.2 8BIBM Open-Weights≤32 GB GPU (4 GB) |
22.4 📎 | Q4: 4 GB (geschätzt) 📎 |
| Modell | Coding-Index | Memory |
|---|---|---|
|
Qwen3.8 27B (xhigh)Alibaba Open-Weights≤32 GB GPU (15 GB) |
68.1 📎 | Q4: 15 GB 📎 |
|
Qwen3.6 27B (Reasoning)Alibaba Open-Weights≤32 GB GPU (15 GB) |
53.7 📎 | Q4: 15 GB (geschätzt) 📎 |
|
Qwen3.6 35B A3B (Reasoning)Alibaba Open-WeightsMoE≤32 GB GPU (20 GB) |
41.9 📎 | Q4: 20 GB (geschätzt) 📎 |
| Modell | Coding-Index | Memory |
|---|---|---|
|
Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA Open-Weights≤32 GB GPU (28 GB) |
15.1 📎 | Q4: 28 GB (geschätzt) 📎 |
|
Kimi Linear 48B A3B InstructMoonshot Open-WeightsMoE≤32 GB GPU (27 GB) |
14.2 📎 | Q4: 27 GB (geschätzt) 📎 |
|
Llama 3.3 Nemotron Super 49B v1 (Reasoning)NVIDIA Open-Weights≤32 GB GPU (28 GB) |
9.4 📎 | Q4: 28 GB (geschätzt) 📎 |
| Modell | Coding-Index | Memory |
|---|---|---|
|
Qwen3 Next 80B A3B (Reasoning)Alibaba Open-WeightsMoE≤128 GB Unified (45 GB) |
17.4 📎 | Q4: 45 GB (geschätzt) 📎 |
|
Qwen3 Next 80B A3B InstructAlibaba Open-WeightsMoE≤128 GB Unified (45 GB) |
15.3 📎 | Q4: 45 GB (geschätzt) 📎 |
|
Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research Open-Weights≤128 GB Unified (39 GB) |
14.4 📎 | Q4: 39 GB (geschätzt) 📎 |
| Modell | Coding-Index | Memory |
|---|---|---|
|
Qwen3.5 122B A10B (Reasoning)Alibaba Open-WeightsMoE≤128 GB Unified (69 GB) |
45.7 📎 | Q4: 69 GB (geschätzt) 📎 |
|
Nemotron 3 Super 120B A12B (Reasoning)NVIDIA Open-WeightsMoE≤128 GB Unified (68 GB) |
37.7 📎 | Q4: 68 GB (geschätzt) 📎 |
|
Solar Open 100B (Reasoning)Upstage Open-Weights≤128 GB Unified (56 GB) |
10.5 📎 | Q4: 56 GB (geschätzt) 📎 |
| Modell | Coding-Index | Memory |
|---|---|---|
|
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek Open-WeightsMoE≤128 GB Unified (120 GB) |
69.1 📎 | Q4: 120 GB 📎 |
| Modell | Coding-Index | Memory |
|---|---|---|
|
Qwen3.5 397B A17B (Reasoning)Alibaba Open-WeightsMoEServer (223 GB) |
48.2 📎 | Q4: 223 GB (geschätzt) 📎 |
|
Solar Open2 250BUpstage Open-WeightsServer (141 GB) |
45.0 📎 | Q4: 141 GB (geschätzt) 📎 |
|
GLM-5 (Reasoning)Zhipu AI Open-WeightsMoEServer (241 GB)📰 2× News (7T) |
44.2 📎 | Q4: 241 GB 📎 |
| Modell | Coding-Index | Memory |
|---|---|---|
|
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek Open-WeightsMoEServer (880 GB) |
68.8 📎 | Q4: 880 GB 📎 |
|
Kimi K2.6Moonshot Open-WeightsMoEServer (584 GB) |
61.8 📎 | Q4: 584 GB 📎 |
|
Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA Open-WeightsMoEServer (309 GB) |
49.3 📎 | Q4: 309 GB (geschätzt) 📎 |
| Modell | Wert | Zusatzinfo |
|---|---|---|
|
GPT Image 2 (high)OpenAI Closed-API |
1334.0 📎 | $0.211/Bild 📎 |
|
GPT Image 1.5 (high)OpenAI Closed-API |
1272.0 📎 | $0.040/Bild 📎 |
|
Gemini 3.1 Flash Image (Nano Banana 2)Google Closed-API |
1261.0 📎 | $0.080/Bild 📎 |
|
Gemini 3 Pro Image (Nano Banana Pro)Google Closed-API |
1216.0 📎 | |
|
FLUX.2 [max]Black Forest Labs Closed-API |
1202.0 📎 | |
|
FLUX.2 [dev]Black Forest Labs Open-Weights |
1160.0 📎 | $0.030/Bild 📎 |
|
Qwen Image Max 2512Alibaba Closed-API |
1159.0 📎 |
| Modell | Wert | Zusatzinfo |
|---|---|---|
|
FLUX.2 [dev]Black Forest Labs Open-Weights |
38666.67 📎 | Image-Arena-ELO 1160.0, $0.030/Bild 📎 |
|
GPT Image 1.5 (high)OpenAI Closed-API |
31800.00 📎 | Image-Arena-ELO 1272.0, $0.040/Bild 📎 |
|
Gemini 3.1 Flash Image (Nano Banana 2)Google Closed-API |
15762.50 📎 | Image-Arena-ELO 1261.0, $0.080/Bild 📎 |
|
GPT Image 2 (high)OpenAI Closed-API |
6322.27 📎 | Image-Arena-ELO 1334.0, $0.211/Bild 📎 |
| Modell | Wert | Zusatzinfo |
|---|---|---|
|
FLUX.2 [dev]Black Forest Labs Open-Weights |
$0.030/Bild 📎 | Arena-ELO 1160 📎 |
|
GPT Image 1.5 (high)OpenAI Closed-API |
$0.040/Bild 📎 | Arena-ELO 1272 📎 |
|
Recraft V3Recraft Closed-API |
$0.040/Bild 📎 | |
|
Imagen 4 UltraGoogle Closed-API |
$0.060/Bild 📎 | |
|
Gemini 3.1 Flash Image (Nano Banana 2)Google Closed-API |
$0.080/Bild 📎 | Arena-ELO 1261 📎 |
|
GPT Image 2 (high)OpenAI Closed-API |
$0.211/Bild 📎 | Arena-ELO 1334 📎 |
Hallo! Ich bin dein KI-Tutor.
Melde dich an, um mit mir zu chatten — ich erinnere mich dann auch an eure letzten Gespräche.
