📊 Live Benchmark

KI-Modelle Leaderboard 2026

Alle relevanten Large Language Models auf einen Blick — sortiert nach Quality Index, Geschwindigkeit, Latenz und Preis. Datenquelle: Artificial Analysis.

200 aktive Modelle aus 12 Vendor-Familien · Letzte Synchronisation: 09. Juni 2026

Wie liest du dieses Leaderboard?

Quality Index ist ein zusammengesetzter Wert von Artificial Analysis aus über zehn unabhängigen Benchmarks (MMLU-Pro, GPQA, HLE, LiveCodeBench, SciCode, AIME u. a.). Höher = besser. Speed misst Output-Tokens pro Sekunde im Median über alle Hosting-Provider. Latency ist die Time-to-First-Token in Sekunden — wichtig für Streaming-UIs. Preise sind US-Dollar pro 1 Million Tokens, separat für Input und Output. Sortiere nach deiner Priorität, filter nach Anbieter oder Preis-Bucket — und prüfe konkrete Kosten direkt im Token-Rechner oder zwei Modelle im Head-to-Head-Vergleich.

#	Modell	Vendor	Quality	Speed	Latency	Preis (USD/1M)
1	Anthropic: Claude Opus 4.8 anthropic/claude-opus-4.8	Anthropic	61,4	61,1 t/s	27,35 s	$6.25 in $25.00 out
2	OpenAI: GPT-5.5 openai/gpt-5.5	OpenAI	60,2	66,2 t/s	84,68 s	$5.00 in $30.00 out
3	Google: Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview	Google	57,2	127,0 t/s	22,14 s	$2.00 in $12.00 out
4	Google: Gemini 3.5 Flash google/gemini-3.5-flash	Google	54,8	201,9 t/s	12,44 s	$1.50 in $9.00 out
5	MiniMax: MiniMax M3 minimax/minimax-m3	MiniMax	54,7	39,0 t/s	2,65 s	$0.30 in $1.20 out
6	OpenAI: GPT-5.3-Codex openai/gpt-5.3-codex	OpenAI	53,6	97,5 t/s	60,44 s	$1.75 in $14.00 out
7	Anthropic: Claude Opus 4.7 anthropic/claude-opus-4.7	Anthropic	51,8	44,8 t/s	834 ms	$6.25 in $25.00 out
8	MiniMax: MiniMax M2.7 minimax/minimax-m2.7	MiniMax	49,6	62,3 t/s	1,28 s	$0.30 in $1.20 out
9	Xiaomi: MiMo-V2-Pro xiaomi/mimo-v2-pro	Xiaomi	49,2	44,8 t/s	2,11 s	$1.00 in $3.00 out
10	OpenAI: GPT-5.2-Codex openai/gpt-5.2-codex	OpenAI	49	131,8 t/s	1,70 s	$1.75 in $14.00 out
11	OpenAI: GPT-5.4 Mini openai/gpt-5.4-mini	OpenAI	48,9	169,8 t/s	8,96 s	$0.75 in $4.50 out
12	NVIDIA: Nemotron 3 Ultra nvidia/nemotron-3-ultra-550b-a55b	NVIDIA	47,7	173,1 t/s	729 ms	$0.60 in $2.60 out
13	OpenAI: GPT-5.2 openai/gpt-5.2	OpenAI	46,6	0 t/s	0 ms	$1.75 in $14.00 out
14	Anthropic: Claude Opus 4.6 anthropic/claude-opus-4.6	Anthropic	46,5	48,6 t/s	1,18 s	$6.25 in $25.00 out
15	OpenAI: GPT-5 Codex openai/gpt-5-codex	OpenAI	44,6	186,3 t/s	7,99 s	$1.25 in $10.00 out
16	Anthropic: Claude Sonnet 4.6 anthropic/claude-sonnet-4.6	Anthropic	44,4	55,3 t/s	1,07 s	$3.75 in $15.00 out
17	xAI: Grok 4.3 x-ai/grok-4.3	xAI	43,9	158,0 t/s	4,39 s	$1.25 in $2.50 out
18	Xiaomi: MiMo-V2-Omni xiaomi/mimo-v2-omni	Xiaomi	43,4	79,9 t/s	2,41 s	$0 in $0 out
19	OpenAI: GPT-5.1-Codex openai/gpt-5.1-codex	OpenAI	43,1	174,1 t/s	4,34 s	$1.25 in $10.00 out
20	Anthropic: Claude Opus 4.5 anthropic/claude-opus-4.5	Anthropic	43,1	61,0 t/s	1,22 s	$6.25 in $25.00 out
21	StepFun: Step 3.7 Flash stepfun/step-3.7-flash	Stepfun	42,6	145,1 t/s	912 ms	$0.20 in $1.15 out
22	MiniMax: MiniMax M2.5 minimax/minimax-m2.5	MiniMax	41,9	240,5 t/s	5,21 s	$0.30 in $1.20 out
23	DeepSeek: DeepSeek V3.2 deepseek/deepseek-v3.2	DeepSeek	41,7	0 t/s	0 ms	$0.30 in $0.45 out
24	xAI: Grok 4 x-ai/grok-4	xAI	41,5	0 t/s	0 ms	$5.50 in $27.50 out
25	OpenAI: o3 Pro openai/o3-pro	OpenAI	40,7	33,2 t/s	66,82 s	$20.00 in $80.00 out
26	MiniMax: MiniMax M2.1 minimax/minimax-m2.1	MiniMax	39,4	224,5 t/s	4,25 s	$0.30 in $1.20 out
27	DeepSeek: DeepSeek V4 Pro deepseek/deepseek-v4-pro	DeepSeek	39,3	65,4 t/s	1,22 s	$0.435 in $0.87 out
28	Mistral: Mistral Medium 3.5 mistralai/mistral-medium-3-5	Mistral	39,2	156,3 t/s	548 ms	$1.50 in $7.50 out
29	OpenAI: GPT-5 openai/gpt-5	OpenAI	39,2	72,5 t/s	11,36 s	$1.25 in $10.00 out
30	Xiaomi: MiMo-V2-Flash xiaomi/mimo-v2-flash	Xiaomi	39,2	144,8 t/s	1,23 s	$0.10 in $0.30 out
31	OpenAI: GPT-5 Mini openai/gpt-5-mini	OpenAI	38,9	88,6 t/s	19,07 s	$0.25 in $2.00 out
32	OpenAI: GPT-5.1-Codex-Mini openai/gpt-5.1-codex-mini	OpenAI	38,6	214,9 t/s	3,64 s	$0.25 in $2.00 out
33	inclusionAI: Ring-2.6-1T inclusionai/ring-2.6-1t	Inclusionai	38,5	122,2 t/s	1,94 s	$0.30 in $2.50 out
34	StepFun: Step 3.5 Flash stepfun/step-3.5-flash	Stepfun	38,5	166,2 t/s	10,69 s	$0.10 in $0.30 out
35	OpenAI: o3 openai/o3	OpenAI	38,4	140,4 t/s	7,34 s	$2.00 in $8.00 out
36	OpenAI: GPT-5.4 Nano openai/gpt-5.4-nano	OpenAI	38,1	165,1 t/s	3,84 s	$0.20 in $1.25 out
37	Anthropic: Claude Sonnet 4.5 anthropic/claude-sonnet-4.5	Anthropic	37,1	51,7 t/s	1,10 s	$3.75 in $15.00 out
38	DeepSeek: DeepSeek V4 Flash deepseek/deepseek-v4-flash	DeepSeek	36,5	107,1 t/s	1,01 s	$0.14 in $0.28 out
39	MiniMax: MiniMax M2 minimax/minimax-m2	MiniMax	36,1	120,8 t/s	1,07 s	$0.30 in $1.20 out
40	NVIDIA: Nemotron 3 Super nvidia/nemotron-3-super-120b-a12b	NVIDIA	36	155,1 t/s	1,04 s	$0.30 in $0.75 out
41	Anthropic: Claude Opus 4.1 anthropic/claude-opus-4.1	Anthropic	36	37,4 t/s	1,78 s	$18.75 in $75.00 out
42	Xiaomi: MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro	Xiaomi	35,6	56,0 t/s	1,89 s	$0.90 in $2.70 out
43	Google: Gemini 2.5 Pro google/gemini-2.5-pro	Google	34,6	135,3 t/s	17,66 s	$1.25 in $10.00 out
44	inclusionAI: Ling-2.6-1T inclusionai/ling-2.6-1t	Inclusionai	33,6	0 t/s	0 ms	$0.30 in $2.50 out
45	Google: Gemini 3.1 Flash Lite Preview google/gemini-3.1-flash-lite-preview	Google	33,5	289,7 t/s	5,25 s	$0.25 in $1.50 out
46	OpenAI: o4 Mini openai/o4-mini	OpenAI	33,1	176,0 t/s	19,07 s	$1.10 in $4.40 out
47	Anthropic: Claude Opus 4 anthropic/claude-opus-4	Anthropic	33	36,9 t/s	1,65 s	$18.75 in $75.00 out
48	Anthropic: Claude Sonnet 4 anthropic/claude-sonnet-4	Anthropic	33	52,3 t/s	1,02 s	$3.75 in $15.00 out
49	Inception: Mercury 2 inception/mercury-2	Inception	32,8	1069,7 t/s	3,57 s	$0.25 in $0.75 out
50	xAI: Grok 3 Mini x-ai/grok-3-mini	xAI	32,1	60,4 t/s	596 ms	$0.30 in $0.50 out
51	Anthropic: Claude Haiku 4.5 anthropic/claude-haiku-4.5	Anthropic	31	118,8 t/s	598 ms	$1.25 in $5.00 out
52	Anthropic: Claude 3.7 Sonnet anthropic/claude-3.7-sonnet	Anthropic	30,8	0 t/s	0 ms	$3.75 in $15.00 out
53	OpenAI: o1 openai/o1	OpenAI	30,7	136,6 t/s	15,44 s	$15.00 in $60.00 out
54	DeepSeek: DeepSeek V3.2 Speciale deepseek/deepseek-v3.2-speciale	DeepSeek	29,4	0 t/s	0 ms	$0 in $0 out
55	xAI: Grok 4.20 x-ai/grok-4.20	xAI	29	188,0 t/s	573 ms	$2.00 in $6.00 out
56	xAI: Grok Code Fast 1 x-ai/grok-code-fast-1	xAI	28,7	0 t/s	0 ms	$0 in $0 out
57	DeepSeek: DeepSeek V3.1 Terminus deepseek/deepseek-v3.1-terminus	DeepSeek	28,5	0 t/s	0 ms	$0.27 in $1.00 out
58	OpenAI: GPT-5.1 openai/gpt-5.1	OpenAI	27,4	136,5 t/s	717 ms	$1.25 in $10.00 out
59	DeepSeek: R1 deepseek/deepseek-r1	DeepSeek	27,1	0 t/s	0 ms	$1.35 in $4.20 out
60	OpenAI: GPT-5 Nano openai/gpt-5-nano	OpenAI	26,8	154,8 t/s	93,82 s	$0.05 in $0.40 out
61	OpenAI: GPT-4.1 openai/gpt-4.1	OpenAI	26,3	149,7 t/s	583 ms	$2.00 in $8.00 out
62	inclusionAI: Ling-2.6-flash inclusionai/ling-2.6-flash	Inclusionai	26,2	0 t/s	0 ms	$0.10 in $0.30 out
63	OpenAI: o3 Mini openai/o3-mini	OpenAI	25,9	202,2 t/s	6,18 s	$1.10 in $4.40 out
64	Upstage: Solar Pro 3 upstage/solar-pro-3	Upstage	25,9	0 t/s	0 ms	$0 in $0 out
65	OpenAI: o1-pro openai/o1-pro	OpenAI	25,8	0 t/s	0 ms	$150.00 in $600.00 out
66	xAI: Grok 3 x-ai/grok-3	xAI	25,2	0 t/s	0 ms	$4.00 in $20.00 out
67	Perplexity: Sonar Reasoning Pro perplexity/sonar-reasoning-pro	Perplexity	24,6	0 t/s	0 ms	$0 in $0 out
68	OpenAI: gpt-oss-120b openai/gpt-oss-120b	OpenAI	24,5	373,5 t/s	494 ms	$0.15 in $0.60 out
69	NVIDIA: Nemotron 3 Nano 30B A3B nvidia/nemotron-3-nano-30b-a3b	NVIDIA	24,3	157,5 t/s	1,88 s	$0.055 in $0.22 out
70	xAI: Grok 4.1 Fast x-ai/grok-4.1-fast	xAI	23,6	0 t/s	0 ms	$0 in $0 out
71	xAI: Grok 4 Fast x-ai/grok-4-fast	xAI	23,1	0 t/s	0 ms	$0.20 in $0.50 out
72	OpenAI: GPT-4.1 Mini openai/gpt-4.1-mini	OpenAI	22,9	88,0 t/s	567 ms	$0.40 in $1.60 out
73	Prime Intellect: INTELLECT-3 prime-intellect/intellect-3	Prime-intellect	22,2	0 t/s	0 ms	$0 in $0 out
74	Mistral: Mistral Medium 3.1 mistralai/mistral-medium-3.1	Mistral	21,3	78,8 t/s	523 ms	$0.40 in $2.00 out
75	OpenAI: gpt-oss-20b openai/gpt-oss-20b	OpenAI	20,8	272,6 t/s	456 ms	$0.06 in $0.20 out
76	Google: Gemini 2.5 Flash google/gemini-2.5-flash	Google	20,6	184,3 t/s	531 ms	$0.30 in $2.50 out
77	OpenAI: GPT-5.4 openai/gpt-5.4	OpenAI	20	0 t/s	0 ms	$0 in $0 out
78	Google: Gemini 2.5 Flash Lite Preview 09-2025 google/gemini-2.5-flash-lite-preview-09-2025	Google	19,4	0 t/s	0 ms	$0.10 in $0.40 out
79	Mistral: Mistral Medium 3 mistralai/mistral-medium-3	Mistral	18,8	49,3 t/s	519 ms	$0.40 in $2.00 out
80	Anthropic: Claude 3.5 Haiku anthropic/claude-3.5-haiku	Anthropic	18,7	0 t/s	0 ms	$1.00 in $4.00 out
81	OpenAI: GPT-4o (2024-08-06) openai/gpt-4o-2024-08-06	OpenAI	18,6	135,3 t/s	632 ms	$2.50 in $10.00 out
82	Meta: Llama 4 Maverick meta-llama/llama-4-maverick	Meta	18,4	119,4 t/s	626 ms	$0.35 in $0.85 out
83	Google: Gemini 2.5 Flash Lite google/gemini-2.5-flash-lite	Google	17,6	293,4 t/s	17,62 s	$0.10 in $0.40 out
84	OpenAI: GPT-4o openai/gpt-4o	OpenAI	17,3	136,1 t/s	482 ms	$2.50 in $10.00 out
85	DeepSeek: R1 Distill Qwen 32B deepseek/deepseek-r1-distill-qwen-32b	DeepSeek	17,2	0 t/s	0 ms	$0 in $0 out
86	DeepSeek: R1 Distill Llama 70B deepseek/deepseek-r1-distill-llama-70b	DeepSeek	16	44,9 t/s	371 ms	$0.70 in $1.05 out
87	Perplexity: Sonar perplexity/sonar	Perplexity	15,5	0 t/s	0 ms	$0 in $0 out
88	Mistral: Devstral Small 1.1 mistralai/devstral-small	Mistral	15,2	59,6 t/s	559 ms	$0.10 in $0.30 out
89	Perplexity: Sonar Pro perplexity/sonar-pro	Perplexity	15,2	0 t/s	0 ms	$0 in $0 out
90	Baidu: ERNIE 4.5 300B A47B baidu/ernie-4.5-300b-a47b	Baidu	15	0 t/s	0 ms	$0.28 in $1.10 out
91	NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 nvidia/llama-3.1-nemotron-ultra-253b-v1	NVIDIA	15	52,7 t/s	727 ms	$0.60 in $1.80 out
92	NVIDIA: Nemotron Nano 12B 2 VL nvidia/nemotron-nano-12b-v2-vl	NVIDIA	14,9	294,8 t/s	269 ms	$0.20 in $0.60 out
93	Google: Gemini 2.0 Flash Lite google/gemini-2.0-flash-lite-001	Google	14,7	0 t/s	0 ms	$0 in $0 out
94	Meta: Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct	Meta	14,5	94,1 t/s	628 ms	$0.58 in $0.71 out
95	OpenAI: GPT-4o (2024-05-13) openai/gpt-4o-2024-05-13	OpenAI	14,5	138,2 t/s	530 ms	$5.00 in $15.00 out
96	Mistral: Pixtral Large 2411 mistralai/pixtral-large-2411	Mistral	14	61,0 t/s	673 ms	$2.00 in $6.00 out
97	OpenAI: GPT-4 Turbo openai/gpt-4-turbo	OpenAI	13,7	33,8 t/s	1,47 s	$10.00 in $30.00 out
98	Cohere: Command A cohere/command-a	Cohere	13,5	72,8 t/s	292 ms	$2.50 in $10.00 out
99	Meta: Llama 4 Scout meta-llama/llama-4-scout	Meta	13,5	108,0 t/s	630 ms	$0.17 in $0.66 out
100	NVIDIA: Llama 3.1 Nemotron 70B Instruct nvidia/llama-3.1-nemotron-70b-instruct	NVIDIA	13,4	291,5 t/s	4,33 s	$1.20 in $1.20 out
101	NVIDIA: Nemotron Nano 9B V2 nvidia/nemotron-nano-9b-v2	NVIDIA	13,2	130,2 t/s	638 ms	$0.05 in $0.195 out
102	Mistral Large 2407 mistralai/mistral-large-2407	Mistral	13	0 t/s	0 ms	$2.00 in $6.00 out
103	OpenAI: GPT-4.1 Nano openai/gpt-4.1-nano	OpenAI	13	189,8 t/s	408 ms	$0.10 in $0.40 out
104	OpenAI: GPT-4 openai/gpt-4	OpenAI	12,8	45,9 t/s	987 ms	$30.00 in $60.00 out
105	OpenAI: GPT-4o-mini openai/gpt-4o-mini	OpenAI	12,6	70,5 t/s	478 ms	$0.15 in $0.60 out
106	Meta: Llama 3.1 70B Instruct meta-llama/llama-3.1-70b-instruct	Meta	12,5	35,6 t/s	573 ms	$0.56 in $0.56 out
107	Anthropic: Claude 3 Haiku anthropic/claude-3-haiku	Anthropic	12,3	0 t/s	0 ms	$0.25 in $1.25 out
108	Mistral: Saba mistralai/mistral-saba	Mistral	12,1	0 t/s	0 ms	$0 in $0 out
109	Meta: Llama 3.1 8B Instruct meta-llama/llama-3.1-8b-instruct	Meta	11,8	197,7 t/s	502 ms	$0.10 in $0.10 out
110	Mistral Large mistralai/mistral-large	Mistral	9,9	0 t/s	0 ms	$4.00 in $12.00 out
111	Meta: Llama 3.2 3B Instruct meta-llama/llama-3.2-3b-instruct	Meta	9,7	51,7 t/s	663 ms	$0.15 in $0.15 out
112	Meta: Llama 3 70B Instruct meta-llama/llama-3-70b-instruct	Meta	8,9	44,5 t/s	690 ms	$0.65 in $2.75 out
113	Meta: Llama 3.2 11B Vision Instruct meta-llama/llama-3.2-11b-vision-instruct	Meta	8,7	86,8 t/s	495 ms	$0.245 in $0.245 out
114	Mistral: Mixtral 8x7B Instruct mistralai/mixtral-8x7b-instruct	Mistral	7,7	0 t/s	0 ms	$0.45 in $0.70 out
115	Meta: Llama 3 8B Instruct meta-llama/llama-3-8b-instruct	Meta	6,4	81,9 t/s	511 ms	$0.045 in $0.145 out
116	Meta: Llama 3.2 1B Instruct meta-llama/llama-3.2-1b-instruct	Meta	6,3	86,4 t/s	569 ms	$0.05 in $0.05 out
117	Elephant openrouter/elephant-alpha	Openrouter	—	— t/s	—	— in — out
118	NVIDIA: Nemotron 3 Nano Omni (free) nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free	NVIDIA	—	— t/s	—	— in — out
119	Qwen: Qwen3.7 Plus qwen/qwen3.7-plus	Alibaba / Qwen	—	— t/s	—	— in — out
120	Anthropic: Claude Opus 4.8 (Fast) anthropic/claude-opus-4.8-fast	Anthropic	—	— t/s	—	— in — out
121	NVIDIA: Nemotron 3.5 Content Safety (free) nvidia/nemotron-3.5-content-safety:free	NVIDIA	—	— t/s	—	— in — out
122	inclusionAI: Ring-2.6-1T (free) inclusionai/ring-2.6-1t:free	Inclusionai	—	— t/s	—	— in — out
123	NVIDIA: Nemotron 3 Ultra (free) nvidia/nemotron-3-ultra-550b-a55b:free	NVIDIA	—	— t/s	—	— in — out
124	Nex AGI: Nex-N2-Pro (free) nex-agi/nex-n2-pro:free	Nex-agi	—	— t/s	—	— in — out
125	Baidu Qianfan: CoBuddy (free) baidu/cobuddy:free	Baidu	—	— t/s	—	— in — out
126	DeepSeek: DeepSeek V4 Flash (free) deepseek/deepseek-v4-flash:free	DeepSeek	—	— t/s	—	— in — out
127	IBM: Granite 4.1 8B ibm-granite/granite-4.1-8b	Ibm-granite	—	— t/s	—	— in — out
128	OpenAI: GPT Chat Latest openai/gpt-chat-latest	OpenAI	—	— t/s	—	— in — out
129	Qwen: Qwen3.7 Max qwen/qwen3.7-max	Alibaba / Qwen	—	— t/s	—	— in — out
130	Google: Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite	Google	—	— t/s	—	— in — out
131	Owl Alpha openrouter/owl-alpha	Openrouter	—	— t/s	—	— in — out
132	xAI: Grok Build 0.1 x-ai/grok-build-0.1	xAI	—	— t/s	—	— in — out
133	Anthropic: Claude Opus 4.7 (Fast) anthropic/claude-opus-4.7-fast	Anthropic	—	— t/s	—	— in — out
134	OpenRouter: Fusion openrouter/fusion	Openrouter	—	— t/s	—	— in — out
135	Perceptron: Perceptron Mk1 perceptron/perceptron-mk1	Perceptron	—	— t/s	—	— in — out
136	inclusionAI: Ling-2.6-flash (free) inclusionai/ling-2.6-flash:free	Inclusionai	—	— t/s	—	— in — out
137	Qwen: Qwen3.6 Flash qwen/qwen3.6-flash	Alibaba / Qwen	—	— t/s	—	— in — out
138	Qwen: Qwen3.5 Plus 2026-04-20 qwen/qwen3.5-plus-20260420	Alibaba / Qwen	—	— t/s	—	— in — out
139	inclusionAI: Ling-2.6-1T (free) inclusionai/ling-2.6-1t:free	Inclusionai	—	— t/s	—	— in — out
140	Tencent: Hy3 preview (free) tencent/hy3-preview:free	Tencent	—	— t/s	—	— in — out
141	MoonshotAI Kimi Latest ~moonshotai/kimi-latest	~moonshotai	—	— t/s	—	— in — out
142	Google Gemini Flash Latest ~google/gemini-flash-latest	~google	—	— t/s	—	— in — out
143	Poolside: Laguna XS.2 (free) poolside/laguna-xs.2:free	Poolside	—	— t/s	—	— in — out
144	Poolside: Laguna M.1 (free) poolside/laguna-m.1:free	Poolside	—	— t/s	—	— in — out
145	OpenAI GPT Mini Latest ~openai/gpt-mini-latest	~openai	—	— t/s	—	— in — out
146	Anthropic Claude Sonnet Latest ~anthropic/claude-sonnet-latest	~anthropic	—	— t/s	—	— in — out
147	OpenAI GPT Latest ~openai/gpt-latest	~openai	—	— t/s	—	— in — out
148	Google Gemini Pro Latest ~google/gemini-pro-latest	~google	—	— t/s	—	— in — out
149	Anthropic Claude Haiku Latest ~anthropic/claude-haiku-latest	~anthropic	—	— t/s	—	— in — out
150	Xiaomi: MiMo-V2.5 xiaomi/mimo-v2.5	Xiaomi	—	— t/s	—	— in — out
151	OpenAI: GPT-5.4 Image 2 openai/gpt-5.4-image-2	OpenAI	—	— t/s	—	— in — out
152	Baidu: Qianfan-OCR-Fast baidu/qianfan-ocr-fast	Baidu	—	— t/s	—	— in — out
153	Qwen: Qwen3.6 35B A3B qwen/qwen3.6-35b-a3b	Alibaba / Qwen	—	— t/s	—	— in — out
154	Qwen: Qwen3.6 Max Preview qwen/qwen3.6-max-preview	Alibaba / Qwen	—	— t/s	—	— in — out
155	Baidu: Qianfan-OCR-Fast (free) baidu/qianfan-ocr-fast:free	Baidu	—	— t/s	—	— in — out
156	Qwen: Qwen3.6 27B qwen/qwen3.6-27b	Alibaba / Qwen	—	— t/s	—	— in — out
157	Tencent: Hy3 preview tencent/hy3-preview	Tencent	—	— t/s	—	— in — out
158	Arcee AI: Trinity Large Thinking (free) arcee-ai/trinity-large-thinking:free	Arcee-ai	—	— t/s	—	— in — out
159	Anthropic: Claude Opus Latest ~anthropic/claude-opus-latest	~anthropic	—	— t/s	—	— in — out
160	Qwen: Qwen3.6 Plus (free) qwen/qwen3.6-plus:free	Alibaba / Qwen	—	— t/s	—	— in — out
161	Anthropic: Claude Opus 4.6 (Fast) anthropic/claude-opus-4.6-fast	Anthropic	—	— t/s	—	— in — out
162	Pareto Code Router openrouter/pareto-code	Openrouter	—	— t/s	—	— in — out
163	MoonshotAI: Kimi K2.6 (free) moonshotai/kimi-k2.6:free	Moonshot AI	—	— t/s	—	— in — out
164	Google: Gemma 4 26B A4B (free) google/gemma-4-26b-a4b-it:free	Google	—	— t/s	—	— in — out
165	MoonshotAI: Kimi K2.6 moonshotai/kimi-k2.6	Moonshot AI	—	— t/s	—	— in — out
166	Z.ai: GLM 5.1 z-ai/glm-5.1	Z-ai	—	— t/s	—	— in — out
167	Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it	Google	—	— t/s	—	— in — out
168	Google: Gemma 4 31B (free) google/gemma-4-31b-it:free	Google	—	— t/s	—	— in — out
169	Qwen: Qwen3.5 Plus 2026-02-15 qwen/qwen3.5-plus-02-15	Alibaba / Qwen	—	— t/s	—	— in — out
170	Arcee AI: Trinity Large Thinking arcee-ai/trinity-large-thinking	Arcee-ai	—	— t/s	—	— in — out
171	Qwen: Qwen3.5 397B A17B qwen/qwen3.5-397b-a17b	Alibaba / Qwen	—	— t/s	—	— in — out
172	Google: Gemma 4 31B google/gemma-4-31b-it	Google	—	— t/s	—	— in — out
173	Z.ai: GLM 5V Turbo z-ai/glm-5v-turbo	Z-ai	—	— t/s	—	— in — out
174	MiniMax: MiniMax M2.5 (free) minimax/minimax-m2.5:free	MiniMax	—	— t/s	—	— in — out
175	Arcee AI: Trinity Large Preview arcee-ai/trinity-large-preview	Arcee-ai	—	— t/s	—	— in — out
176	AllenAI: Olmo 3.1 32B Instruct allenai/olmo-3.1-32b-instruct	Allenai	—	— t/s	—	— in — out
177	Qwen: Qwen3.6 Plus qwen/qwen3.6-plus	Alibaba / Qwen	—	— t/s	—	— in — out
178	Qwen: Qwen3 235B A22B qwen/qwen3-235b-a22b	Alibaba / Qwen	—	— t/s	—	— in — out
179	OpenAI: o4 Mini High openai/o4-mini-high	OpenAI	—	— t/s	—	— in — out
180	xAI: Grok 4.20 Multi-Agent x-ai/grok-4.20-multi-agent	xAI	—	— t/s	—	— in — out
181	Deep Cogito: Cogito v2.1 671B deepcogito/cogito-v2.1-671b	Deepcogito	—	— t/s	—	— in — out
182	MoonshotAI: Kimi K2.5 moonshotai/kimi-k2.5	Moonshot AI	—	— t/s	—	— in — out
183	Z.ai: GLM 4.7 z-ai/glm-4.7	Z-ai	—	— t/s	—	— in — out
184	Google: Gemini 3 Flash Preview google/gemini-3-flash-preview	Google	—	— t/s	—	— in — out
185	Z.ai: GLM 4.7 Flash z-ai/glm-4.7-flash	Z-ai	—	— t/s	—	— in — out
186	ByteDance Seed: Seed 1.6 Flash bytedance-seed/seed-1.6-flash	Bytedance-seed	—	— t/s	—	— in — out
187	Google: Gemma 3 27B google/gemma-3-27b-it	Google	—	— t/s	—	— in — out
188	Meituan: LongCat Flash Chat meituan/longcat-flash-chat	Meituan	—	— t/s	—	— in — out
189	Google: Lyria 3 Pro Preview google/lyria-3-pro-preview	Google	—	— t/s	—	— in — out
190	Inception: Mercury inception/mercury	Inception	—	— t/s	—	— in — out
191	AllenAI: Olmo 3 32B Think allenai/olmo-3-32b-think	Allenai	—	— t/s	—	— in — out
192	Google: Nano Banana Pro (Gemini 3 Pro Image Preview) google/gemini-3-pro-image-preview	Google	—	— t/s	—	— in — out
193	Google: Gemma 3n 4B google/gemma-3n-e4b-it	Google	—	— t/s	—	— in — out
194	Google: Gemma 3 4B (free) google/gemma-3-4b-it:free	Google	—	— t/s	—	— in — out
195	Microsoft: Phi 4 Mini Instruct microsoft/phi-4-mini-instruct	Microsoft	—	— t/s	—	— in — out
196	Venice: Uncensored (free) cognitivecomputations/dolphin-mistral-24b-venice-edition:free	Cognitivecomputations	—	— t/s	—	— in — out
197	Qwen: Qwen3 VL 235B A22B Instruct qwen/qwen3-vl-235b-a22b-instruct	Alibaba / Qwen	—	— t/s	—	— in — out
198	Mistral: Mistral Small 3.2 24B mistralai/mistral-small-3.2-24b-instruct	Mistral	—	— t/s	—	— in — out
199	Google: Lyria 3 Clip Preview google/lyria-3-clip-preview	Google	—	— t/s	—	— in — out
200	Kwaipilot: KAT-Coder-Pro V2 kwaipilot/kat-coder-pro-v2	Kwaipilot	—	— t/s	—	— in — out

🧮 Tool

Pricing-Calculator

Schätze deine monatlichen API-Kosten — gib dein erwartetes Token-Volumen ein, wir rechnen für die Top-15 Modelle.

Input Tokens (Mio./Monat) Output Tokens (Mio./Monat)

#	Modell	Vendor	Quality	Kosten/Monat (USD)

📈 Tool

Quality vs. Preis (Pareto-Chart)

Wo liegt der beste Tradeoff? Modelle oben-links sind die Pareto-Optima: hohe Quality, niedriger Preis.

Pareto-Optimum Andere Modelle

❓ Häufige Fragen zum KI-Modelle-Leaderboard

Woher stammen die Leaderboard-Daten?

Quality Index, Speed (Output-Tokens/s), Latenz (Time-to-First-Token) und Preise (USD pro 1 Mio. Tokens) kommen direkt von Artificial Analysis. Synchronisation täglich um 04:00 UTC. Wir speichern keine eigenen Benchmark-Werte und führen keine eigene Bewertung durch.

Was misst der Quality Index genau?

Der Artificial-Analysis-Intelligence-Index ist ein zusammengesetzter Score aus über zehn unabhängigen Benchmarks: MMLU-Pro (Wissen), GPQA & HLE (Reasoning), LiveCodeBench & SciCode (Coding), AIME (Mathematik), IFBench (Instruction-Following), LCR (Long-Context-Recall) und τ² (Tool-Use). Skala 0–100 — höher = besser.

Warum sind manche bekannte Modelle nicht im Leaderboard?

Wir zeigen nur Modelle, die in der Registry als is_active=true markiert sind und für die Artificial Analysis vollständige Benchmark-Daten liefert. Reine Bild- oder Audio-Modelle, deprecatete Versionen sowie Closed-Beta-Modelle ohne öffentliche API erscheinen nicht.

Wie nutze ich Sortierung und Filter sinnvoll?

Sortiere nach Quality für maximale Genauigkeit, nach Speed für hohen Durchsatz, nach Latency für reaktive Streaming-UIs und nach Preis für kostensensitive Workloads. Kombiniere die Vendor- und Preis-Filter, um z. B. „nur OpenAI unter 5 USD/Mio. Output“ zu finden.

Wie berechne ich konkrete Token-Kosten?

Im Token-Kostenrechner kannst du Input- und Output-Volumen einsetzen und die monatlichen Kosten für jedes Modell live durchspielen. Für direkten Head-to-Head-Vergleich zweier Modelle nutze die Vergleichs-Seiten.