📊 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: 15. Oktober 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.

Sortieren

Quality Index Speed (Tokens/s)Latency (TTFT)Preis Input Preis Output

Vendor

Alle 200 OpenAI 41 Anthropic 22 Google 15 Meta 14 Inclusionai 13 xAI 11 DeepSeek 10 Mistral 10 NVIDIA 8 Xiaomi 6 MiniMax 5 Tencent 4

Modalität

Alle Text 200

Preis (Input)

Alle Gratis / Self-hosted 27 ≤ 1 USD/M 69 1–5 USD/M 50 > 5 USD/M 10

#	Modell	Vendor	Quality	Speed	Latency	Preis (USD/1M)
1	Google: Gemini 4 Argon google/gemini-4-argon	Google	52,6	0 t/s	0 ms	$2.00 in $10.00 out
2	Meta: Muse Wonder meta/muse-wonder	Meta	52,4	112,8 t/s	32,29 s	$4.00 in $20.00 out
3	Anthropic: Claude Fable 5 anthropic/claude-fable-5	Anthropic	49,6	0 t/s	0 ms	$10.00 in $50.00 out
4	Anthropic: Claude Fable 5.1 anthropic/claude-fable-5.1	Anthropic	46,8	49,1 t/s	676 ms	$10.00 in $50.00 out
5	Xiaomi: MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro	Xiaomi	46,3	45,8 t/s	2,88 s	$0.435 in $0.87 out
6	OpenAI: GPT-6 Astra openai/gpt-6-astra	OpenAI	45,8	41,7 t/s	1,83 s	$10.00 in $50.00 out
7	Meta: Muse Spark 1.3 meta/muse-spark-1.3	Meta	45,1	241,0 t/s	23,72 s	$1.25 in $4.25 out
8	Anthropic: Claude Opus 5.5 anthropic/claude-opus-5.5	Anthropic	42,3	71,7 t/s	3,77 s	$4.00 in $20.00 out
9	SpaceXAI: Grok 4.7 x-ai/grok-4.7	xAI	42,2	62,0 t/s	3,29 s	$2.00 in $6.00 out
10	OpenAI: GPT-6.1 Sol openai/gpt-6.1-sol	OpenAI	42,1	47,3 t/s	2,12 s	$2.00 in $10.00 out
11	Anthropic: Claude Opus 4.8 anthropic/claude-opus-4.8	Anthropic	41,8	0 t/s	0 ms	$5.00 in $25.00 out
12	inclusionAI: Ling 3.1 Flash inclusionai/ling-3.1-flash	Inclusionai	41,1	210,5 t/s	1,13 s	$0.30 in $0.90 out
13	Meta: Muse Spark 1.2 meta/muse-spark-1.2	Meta	39,6	0 t/s	0 ms	$1.25 in $4.25 out
14	Anthropic: Claude Opus 5 anthropic/claude-opus-5	Anthropic	39,4	0 t/s	0 ms	$5.00 in $25.00 out
15	SpaceXAI: Grok 4.5 x-ai/grok-4.5	xAI	38,8	0 t/s	0 ms	$2.00 in $6.00 out
16	Xiaomi: MiMo-V2.6-Flash xiaomi/mimo-v2.6-flash	Xiaomi	37,9	50,5 t/s	2,10 s	$0.14 in $0.28 out
17	Google: Gemini 3.7 Flash google/gemini-3.7-flash	Google	36,9	0 t/s	0 ms	$0.75 in $3.75 out
18	Anthropic: Claude Sonnet 5.5 anthropic/claude-sonnet-5.5	Anthropic	35,9	88,6 t/s	645 ms	$2.00 in $10.00 out
19	SpaceXAI: Grok 4.6 x-ai/grok-4.6	xAI	35,1	0 t/s	0 ms	$2.00 in $6.00 out
20	Google: Gemini 3.6 Flash google/gemini-3.6-flash	Google	34	0 t/s	0 ms	$0.75 in $3.75 out
21	Meta: Muse Spark 1.1 meta/muse-spark-1.1	Meta	33,7	0 t/s	0 ms	$1.25 in $4.25 out
22	Google: Gemini 3.8 Flash google/gemini-3.8-flash	Google	33,5	0 t/s	0 ms	$0.75 in $3.75 out
23	Google: Gemini 3.5 Flash google/gemini-3.5-flash	Google	32,6	0 t/s	0 ms	$1.50 in $9.00 out
24	OpenAI: GPT-5.3-Codex openai/gpt-5.3-codex	OpenAI	32,5	87,4 t/s	40,27 s	$1.75 in $14.00 out
25	Anthropic: Claude Opus 4.7 anthropic/claude-opus-4.7	Anthropic	30,9	0 t/s	0 ms	$5.00 in $25.00 out
26	Google: Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview	Google	29,7	138,4 t/s	18,51 s	$2.00 in $12.00 out
27	Anthropic: Claude Haiku 5.5 anthropic/claude-haiku-5.5	Anthropic	29,5	145,7 t/s	4,53 s	$0.10 in $0.50 out
28	MiniMax: MiniMax M3 minimax/minimax-m3	MiniMax	29,2	99,1 t/s	835 ms	$0.30 in $1.20 out
29	Xiaomi: MiMo-V2-Pro xiaomi/mimo-v2-pro	Xiaomi	28,6	0 t/s	0 ms	$0 in $0 out
30	OpenAI: GPT-5.2-Codex openai/gpt-5.2-codex	OpenAI	28,5	0 t/s	0 ms	$1.75 in $14.00 out
31	OpenAI: GPT-6 Sol openai/gpt-6-sol	OpenAI	28,5	0 t/s	0 ms	$2.00 in $10.00 out
32	OpenAI: GPT-5.6 Sol openai/gpt-5.6-sol	OpenAI	28,3	0 t/s	0 ms	$4.00 in $20.00 out
33	Upstage: Solar Pro 4 upstage/solar-pro4	Upstage	28,2	85,5 t/s	1,00 s	$0.30 in $1.20 out
34	Anthropic: Claude Opus 4.6 anthropic/claude-opus-4.6	Anthropic	26,4	0 t/s	0 ms	$5.00 in $25.00 out
35	OpenAI: GPT-5 Codex openai/gpt-5-codex	OpenAI	24,9	0 t/s	0 ms	$1.25 in $10.00 out
36	Anthropic: Claude Sonnet 4.6 anthropic/claude-sonnet-4.6	Anthropic	24,7	0 t/s	0 ms	$3.00 in $15.00 out
37	DeepSeek: DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash	DeepSeek	24,7	160,3 t/s	881 ms	$0.30 in $1.20 out
38	inclusionAI: Ling 3.0 Flash VL inclusionai/ling-3.0-flash-vl	Inclusionai	24,6	0 t/s	0 ms	$0 in $0 out
39	DeepSeek: DeepSeek V4 Flash 0423 deepseek/deepseek-v4-flash	DeepSeek	24,2	0 t/s	0 ms	$0.112 in $0.234 out
40	Upstage: Solar Mini 4 upstage/solar-mini4	Upstage	24,1	76,1 t/s	1,03 s	$0.10 in $0.40 out
41	Xiaomi: MiMo-V2-Omni xiaomi/mimo-v2-omni	Xiaomi	23,9	0 t/s	0 ms	$0 in $0 out
42	Anthropic: Claude Opus 4.5 anthropic/claude-opus-4.5	Anthropic	23,7	0 t/s	0 ms	$5.00 in $25.00 out
43	OpenAI: GPT-5.1-Codex openai/gpt-5.1-codex	OpenAI	23,7	0 t/s	0 ms	$1.25 in $10.00 out
44	OpenAI: GPT-5.5 openai/gpt-5.5	OpenAI	23,2	0 t/s	0 ms	$5.00 in $30.00 out
45	Anthropic: Claude Sonnet 5 anthropic/claude-sonnet-5	Anthropic	23,2	0 t/s	0 ms	$2.00 in $10.00 out
46	NVIDIA: Nemotron 3 Ultra nvidia/nemotron-3-ultra-550b-a55b	NVIDIA	22,9	148,4 t/s	881 ms	$0.60 in $2.50 out
47	MiniMax: MiniMax M2.5 minimax/minimax-m2.5	MiniMax	22,8	0 t/s	0 ms	$0.30 in $1.20 out
48	MiniMax: MiniMax M2.7 minimax/minimax-m2.7	MiniMax	22,8	0 t/s	0 ms	$0.30 in $1.20 out
49	Tencent: Hy3 preview tencent/hy3-preview	Tencent	22,7	0 t/s	0 ms	$0.063 in $0.21 out
50	inclusionAI: Ling 3.0 Flash Fin inclusionai/ling-3.0-flash-fin	Inclusionai	22,6	284,3 t/s	1,17 s	$0.075 in $0.22 out
51	xAI: Grok 4 x-ai/grok-4	xAI	22,5	0 t/s	0 ms	$3.00 in $15.00 out
52	Google: Gemini 3.5 Flash Lite google/gemini-3.5-flash-lite	Google	22,2	406,3 t/s	6,00 s	$0.30 in $2.50 out
53	OpenAI: o3 Pro openai/o3-pro	OpenAI	21,9	0 t/s	0 ms	$20.00 in $80.00 out
54	MiniMax: MiniMax M2.1 minimax/minimax-m2.1	MiniMax	20,9	0 t/s	0 ms	$0.30 in $1.20 out
55	OpenAI: GPT-5 openai/gpt-5	OpenAI	20,8	0 t/s	0 ms	$1.25 in $10.00 out
56	OpenAI: GPT-5.6 Terra openai/gpt-5.6-terra	OpenAI	20,8	89,1 t/s	736 ms	$2.00 in $12.00 out
57	OpenAI: GPT-5.1-Codex-Mini openai/gpt-5.1-codex-mini	OpenAI	20,4	0 t/s	0 ms	$0.25 in $2.00 out
58	DeepSeek: DeepSeek V4 Pro 0423 deepseek/deepseek-v4-pro	DeepSeek	20,4	88,5 t/s	1,07 s	$1.32 in $3.96 out
59	OpenAI: o3 openai/o3	OpenAI	20,2	115,1 t/s	5,40 s	$2.00 in $8.00 out
60	inclusionAI: Ling 3.0 Flash inclusionai/ling-3.0-flash	Inclusionai	20,1	0 t/s	0 ms	$0.075 in $0.22 out
61	StepFun: Step 3.7 Flash stepfun/step-3.7-flash	Stepfun	19,5	0 t/s	0 ms	$0.20 in $1.15 out
62	Anthropic: Claude Sonnet 4.5 anthropic/claude-sonnet-4.5	Anthropic	19,3	0 t/s	0 ms	$3.00 in $15.00 out
63	MiniMax: MiniMax M2 minimax/minimax-m2	MiniMax	18,6	0 t/s	0 ms	$0.30 in $1.20 out
64	Anthropic: Claude Opus 4.1 anthropic/claude-opus-4.1	Anthropic	18,6	0 t/s	0 ms	$15.00 in $75.00 out
65	OpenAI: GPT-6 Luna openai/gpt-6-luna	OpenAI	18,5	123,2 t/s	947 ms	$0.10 in $0.50 out
66	Xiaomi: MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro	Xiaomi	18,3	0 t/s	0 ms	$0.435 in $0.87 out
67	OpenAI: GPT-5.2 openai/gpt-5.2	OpenAI	17	0 t/s	0 ms	$1.75 in $14.00 out
68	StepFun: Step 3.5 Flash stepfun/step-3.5-flash	Stepfun	17	0 t/s	0 ms	$0.10 in $0.30 out
69	inclusionAI: Ling-2.6-1T inclusionai/ling-2.6-1t	Inclusionai	17	0 t/s	0 ms	$0.30 in $2.50 out
70	Tencent: Hy3 tencent/hy3	Tencent	17	0 t/s	0 ms	$0.063 in $0.21 out
71	OpenAI: GPT-5 Mini openai/gpt-5-mini	OpenAI	16,8	0 t/s	0 ms	$0.25 in $2.00 out
72	OpenAI: o4 Mini openai/o4-mini	OpenAI	16,7	0 t/s	0 ms	$1.10 in $4.40 out
73	Anthropic: Claude Sonnet 4 anthropic/claude-sonnet-4	Anthropic	16,6	0 t/s	0 ms	$0 in $0 out
74	Anthropic: Claude Opus 4 anthropic/claude-opus-4	Anthropic	16,6	0 t/s	0 ms	$15.00 in $75.00 out
75	inclusionAI: Ring-2.6-1T inclusionai/ring-2.6-1t	Inclusionai	16,6	112,0 t/s	2,12 s	$0.30 in $2.50 out
76	Google: Gemini 2.5 Pro google/gemini-2.5-pro	Google	16,1	0 t/s	0 ms	$1.25 in $10.00 out
77	DeepSeek: DeepSeek V3.2 deepseek/deepseek-v3.2	DeepSeek	16	0 t/s	0 ms	$0.28 in $0.42 out
78	Xiaomi: MiMo-V2-Flash xiaomi/mimo-v2-flash	Xiaomi	16	0 t/s	0 ms	$0 in $0 out
79	Google: Gemini 3.1 Flash Lite Preview google/gemini-3.1-flash-lite-preview	Google	15,6	0 t/s	0 ms	$0.25 in $1.50 out
80	OpenAI: GPT-5.6 Luna openai/gpt-5.6-luna	OpenAI	15,5	0 t/s	0 ms	$0.20 in $1.20 out
81	Anthropic: Claude Haiku 4.5 anthropic/claude-haiku-4.5	Anthropic	15,4	0 t/s	0 ms	$1.00 in $5.00 out
82	Anthropic: Claude 3.7 Sonnet anthropic/claude-3.7-sonnet	Anthropic	15,3	0 t/s	0 ms	$3.00 in $15.00 out
83	OpenAI: o1 openai/o1	OpenAI	15,2	0 t/s	0 ms	$15.00 in $60.00 out
84	xAI: Grok 3 Mini x-ai/grok-3-mini	xAI	14,6	0 t/s	0 ms	$0.30 in $0.50 out
85	DeepSeek: DeepSeek V3.2 Speciale deepseek/deepseek-v3.2-speciale	DeepSeek	14,5	0 t/s	0 ms	$0 in $0 out
86	Mistral: Mistral Medium 3.5 mistralai/mistral-medium-3-5	Mistral	14,2	166,7 t/s	609 ms	$1.50 in $7.50 out
87	SpaceXAI: Grok 4.20 x-ai/grok-4.20	xAI	14,2	0 t/s	0 ms	$1.25 in $2.50 out
88	xAI: Grok Code Fast 1 x-ai/grok-code-fast-1	xAI	14,1	0 t/s	0 ms	$0 in $0 out
89	SpaceXAI: Grok 4.3 x-ai/grok-4.3	xAI	14	0 t/s	0 ms	$1.25 in $2.50 out
90	DeepSeek: DeepSeek V3.1 Terminus deepseek/deepseek-v3.1-terminus	DeepSeek	13,9	0 t/s	0 ms	$0.27 in $1.00 out
91	OpenAI: GPT-5.1 openai/gpt-5.1	OpenAI	13,3	0 t/s	0 ms	$1.25 in $10.00 out
92	Cohere: Command A+ cohere/command-a-plus	Cohere	13,1	157,2 t/s	248 ms	$0 in $0 out
93	DeepSeek: R1 deepseek/deepseek-r1	DeepSeek	13,1	0 t/s	0 ms	$1.35 in $3.00 out
94	NVIDIA: Nemotron 3.5 Lightning nvidia/nemotron-3.5-lightning	NVIDIA	12,9	296,5 t/s	393 ms	$0.06 in $0.20 out
95	NVIDIA: Nemotron 3 Super nvidia/nemotron-3-super-120b-a12b	NVIDIA	12,8	143,1 t/s	830 ms	$0.30 in $0.90 out
96	OpenAI: GPT-4.1 openai/gpt-4.1	OpenAI	12,7	0 t/s	0 ms	$2.00 in $8.00 out
97	OpenAI: GPT-5 Nano openai/gpt-5-nano	OpenAI	12,5	0 t/s	0 ms	$0.05 in $0.40 out
98	OpenAI: o1-pro openai/o1-pro	OpenAI	12,4	0 t/s	0 ms	$150.00 in $600.00 out
99	Inception: Mercury 2.5 inception/mercury-2.5	Inception	12,3	731,3 t/s	2,74 s	$0.25 in $0.75 out
100	Perplexity: Sonar Reasoning Pro perplexity/sonar-reasoning-pro	Perplexity	11,8	0 t/s	0 ms	$0 in $0 out
101	OpenAI: GPT-5.4 Nano openai/gpt-5.4-nano	OpenAI	11,7	0 t/s	0 ms	$0.20 in $1.25 out
102	xAI: Grok 4.1 Fast x-ai/grok-4.1-fast	xAI	11,3	0 t/s	0 ms	$0 in $0 out
103	xAI: Grok 4 Fast x-ai/grok-4-fast	xAI	11,1	0 t/s	0 ms	$0.20 in $0.50 out
104	OpenAI: GPT-5.4 Mini openai/gpt-5.4-mini	OpenAI	11,1	0 t/s	0 ms	$0.75 in $4.50 out
105	OpenAI: o3 Mini openai/o3-mini	OpenAI	11	0 t/s	0 ms	$1.10 in $4.40 out
106	Inception: Mercury 2 inception/mercury-2	Inception	10,8	0 t/s	0 ms	$0.25 in $0.75 out
107	Prime Intellect: INTELLECT-3 prime-intellect/intellect-3	Prime-intellect	10,6	0 t/s	0 ms	$0 in $0 out
108	xAI: Grok 3 x-ai/grok-3	xAI	10,4	0 t/s	0 ms	$0 in $0 out
109	OpenAI: GPT-4.1 Mini openai/gpt-4.1-mini	OpenAI	10,2	0 t/s	0 ms	$0.40 in $1.60 out
110	OpenAI: gpt-oss-120b openai/gpt-oss-120b	OpenAI	10,2	228,2 t/s	493 ms	$0.15 in $0.50 out
111	Google: Gemini 2.5 Flash google/gemini-2.5-flash	Google	9,9	0 t/s	0 ms	$0.30 in $2.50 out
112	inclusionAI: Ling-2.6-flash inclusionai/ling-2.6-flash	Inclusionai	9,7	0 t/s	0 ms	$0 in $0 out
113	OpenAI: GPT-5.4 openai/gpt-5.4	OpenAI	9,6	0 t/s	0 ms	$0 in $0 out
114	Google: Gemini 2.5 Flash Lite Preview 09-2025 google/gemini-2.5-flash-lite-preview-09-2025	Google	9,3	0 t/s	0 ms	$0.10 in $0.40 out
115	Meta: Llama 4 Maverick meta-llama/llama-4-maverick	Meta	9,3	56,5 t/s	646 ms	$0.25 in $0.87 out
116	Mistral: Mistral Medium 3.1 mistralai/mistral-medium-3.1	Mistral	9,2	0 t/s	0 ms	$0 in $0 out
117	Mistral: Mistral Medium 3 mistralai/mistral-medium-3	Mistral	9	0 t/s	0 ms	$0.40 in $2.00 out
118	OpenAI: gpt-oss-20b openai/gpt-oss-20b	OpenAI	9	224,8 t/s	401 ms	$0.07 in $0.18 out
119	Anthropic: Claude 3.5 Haiku anthropic/claude-3.5-haiku	Anthropic	8,9	0 t/s	0 ms	$0 in $0 out
120	DeepSeek: R1 Distill Qwen 32B deepseek/deepseek-r1-distill-qwen-32b	DeepSeek	8,4	0 t/s	0 ms	$0 in $0 out
121	OpenAI: GPT-4o openai/gpt-4o	OpenAI	8,4	0 t/s	0 ms	$2.50 in $10.00 out
122	DeepSeek: R1 Distill Llama 70B deepseek/deepseek-r1-distill-llama-70b	DeepSeek	7,9	0 t/s	0 ms	$0.70 in $1.10 out
123	OpenAI: GPT-4.1 Nano openai/gpt-4.1-nano	OpenAI	7,8	0 t/s	0 ms	$0.10 in $0.40 out
124	Upstage: Solar Pro 3 upstage/solar-pro-3	Upstage	7,8	0 t/s	0 ms	$0.15 in $0.60 out
125	Perplexity: Sonar perplexity/sonar	Perplexity	7,7	0 t/s	0 ms	$0 in $0 out
126	Meta: Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct	Meta	7,7	95,3 t/s	645 ms	$0.71 in $0.72 out
127	OpenAI: GPT-4o (2024-08-06) openai/gpt-4o-2024-08-06	OpenAI	7,7	0 t/s	0 ms	$2.50 in $10.00 out
128	Mistral: Devstral Small 1.1 mistralai/devstral-small	Mistral	7,6	0 t/s	0 ms	$0 in $0 out
129	Perplexity: Sonar Pro perplexity/sonar-pro	Perplexity	7,6	0 t/s	0 ms	$0 in $0 out
130	NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 nvidia/llama-3.1-nemotron-ultra-253b-v1	NVIDIA	7,5	0 t/s	0 ms	$0 in $0 out
131	Baidu: ERNIE 4.5 300B A47B baidu/ernie-4.5-300b-a47b	Baidu	7,5	0 t/s	0 ms	$0.28 in $1.10 out
132	Google: Gemini 2.0 Flash Lite google/gemini-2.0-flash-lite-001	Google	7,4	0 t/s	0 ms	$0 in $0 out
133	OpenAI: GPT-4o (2024-05-13) openai/gpt-4o-2024-05-13	OpenAI	7,3	0 t/s	0 ms	$5.00 in $15.00 out
134	Mistral: Pixtral Large 2411 mistralai/pixtral-large-2411	Mistral	7,1	0 t/s	0 ms	$0 in $0 out
135	OpenAI: GPT-4 Turbo openai/gpt-4-turbo	OpenAI	7	0 t/s	0 ms	$10.00 in $30.00 out
136	Cohere: Command A cohere/command-a	Cohere	7	64,8 t/s	337 ms	$2.50 in $10.00 out
137	Meta: Llama 3.1 8B Instruct meta-llama/llama-3.1-8b-instruct	Meta	6,9	0 t/s	0 ms	$0.035 in $0.065 out
138	NVIDIA: Llama 3.1 Nemotron 70B Instruct nvidia/llama-3.1-nemotron-70b-instruct	NVIDIA	6,9	0 t/s	0 ms	$0 in $0 out
139	NVIDIA: Nemotron 3 Nano 30B A3B nvidia/nemotron-3-nano-30b-a3b	NVIDIA	6,8	250,3 t/s	365 ms	$0.05 in $0.20 out
140	Mistral Large 2407 mistralai/mistral-large-2407	Mistral	6,8	0 t/s	0 ms	$2.00 in $6.00 out
141	NVIDIA: Nemotron Nano 9B V2 nvidia/nemotron-nano-9b-v2	NVIDIA	6,8	171,1 t/s	716 ms	$0.05 in $0.195 out
142	Google: Gemini 2.5 Flash Lite google/gemini-2.5-flash-lite	Google	6,7	0 t/s	0 ms	$0.10 in $0.40 out
143	OpenAI: GPT-4o-mini openai/gpt-4o-mini	OpenAI	6,7	0 t/s	0 ms	$0.15 in $0.60 out
144	OpenAI: GPT-4 openai/gpt-4	OpenAI	6,7	0 t/s	0 ms	$30.00 in $60.00 out
145	Meta: Llama 3.1 70B Instruct meta-llama/llama-3.1-70b-instruct	Meta	6,6	0 t/s	0 ms	$0.56 in $0.56 out
146	Meta: Llama 4 Scout meta-llama/llama-4-scout	Meta	6,5	99,5 t/s	833 ms	$0.18 in $0.66 out
147	Mistral: Saba mistralai/mistral-saba	Mistral	6,5	0 t/s	0 ms	$0 in $0 out
148	NVIDIA: Nemotron Nano 12B 2 VL nvidia/nemotron-nano-12b-v2-vl	NVIDIA	5,8	207,7 t/s	783 ms	$0.20 in $0.60 out
149	Mistral Large mistralai/mistral-large	Mistral	5,8	0 t/s	0 ms	$4.00 in $12.00 out
150	Meta: Llama 3.2 3B Instruct meta-llama/llama-3.2-3b-instruct	Meta	5,7	0 t/s	0 ms	$0 in $0 out
151	Anthropic: Claude 3 Haiku anthropic/claude-3-haiku	Anthropic	5,6	0 t/s	0 ms	$0.25 in $1.25 out
152	Meta: Llama 3 70B Instruct meta-llama/llama-3-70b-instruct	Meta	5,5	0 t/s	0 ms	$0.65 in $2.75 out
153	Meta: Llama 3.2 11B Vision Instruct meta-llama/llama-3.2-11b-vision-instruct	Meta	5,4	22,8 t/s	849 ms	$0.345 in $0.345 out
154	Mistral: Mixtral 8x7B Instruct mistralai/mixtral-8x7b-instruct	Mistral	5,1	0 t/s	0 ms	$0.45 in $0.70 out
155	Meta: Llama 3 8B Instruct meta-llama/llama-3-8b-instruct	Meta	4,8	0 t/s	0 ms	$0.045 in $0.145 out
156	Meta: Llama 3.2 1B Instruct meta-llama/llama-3.2-1b-instruct	Meta	4,8	0 t/s	0 ms	$0 in $0 out
157	Union Alpha stealth/union-alpha	Stealth	—	— t/s	—	— in — out
158	Pareto Latest ~unbiased/pareto-latest	~unbiased	—	— t/s	—	— in — out
159	Elephant openrouter/elephant-alpha	Openrouter	—	— t/s	—	— in — out
160	Pareto 26.9 unbiased/pareto-26.9	Unbiased	—	— t/s	—	— in — out
161	LiquidAI: LFM2.5-24B-A2B liquid/lfm-2.5-24b-a2b	Liquid	—	— t/s	—	— in — out
162	inclusionAI: Ring-2.6-1T (free) inclusionai/ring-2.6-1t:free	Inclusionai	—	— t/s	—	— in — out
163	Nex AGI: Nex-N2-Pro (free) nex-agi/nex-n2-pro:free	Nex-agi	—	— t/s	—	— in — out
164	Ox Alpha stealth/ox-alpha	Stealth	—	— t/s	—	— in — out
165	Baidu Qianfan: CoBuddy (free) baidu/cobuddy:free	Baidu	—	— t/s	—	— in — out
166	DeepSeek: DeepSeek V4 Flash (free) deepseek/deepseek-v4-flash:free	DeepSeek	—	— t/s	—	— in — out
167	Apodex: Apodex 1.1 Mini (free) apodex/apodex-1.1-mini:free	Apodex	—	— t/s	—	— in — out
168	Anthropic: Claude Haiku 5.5 (batch) anthropic/claude-haiku-5.5:batch	Anthropic	—	— t/s	—	— in — out
169	Inception: Mercury 2.5 Preview inception/mercury-2.5-preview	Inception	—	— t/s	—	— in — out
170	inclusionAI: Ling 3.0 Tiny (free) inclusionai/ling-3.0-tiny:free	Inclusionai	—	— t/s	—	— in — out
171	Google: Nano Banana 2.1 google/gemini-nano-banana-2.1	Google	—	— t/s	—	— in — out
172	Google: Gemini 4 Argon (batch) google/gemini-4-argon:batch	Google	—	— t/s	—	— in — out
173	ScaleDown: Summarize scaledown/summarize	Scaledown	—	— t/s	—	— in — out
174	ScaleDown: Extract scaledown/extract	Scaledown	—	— t/s	—	— in — out
175	StepFun: Step 5 Preview stepfun/step-5-preview	Stepfun	—	— t/s	—	— in — out
176	Thinking Machines: Inkling Small (batch) thinkingmachines/inkling-small:batch	Thinkingmachines	—	— t/s	—	— in — out
177	Tencent: Hy3 (free) tencent/hy3:free	Tencent	—	— t/s	—	— in — out
178	inclusionAI: Ling-2.6-flash (free) inclusionai/ling-2.6-flash:free	Inclusionai	—	— t/s	—	— in — out
179	Owl Alpha openrouter/owl-alpha	Openrouter	—	— t/s	—	— in — out
180	Space Bunny Alpha stealth/space-bunny-alpha	Stealth	—	— t/s	—	— in — out
181	Mistral: Mistral Large 4 mistralai/mistral-large-4-0	Mistral	—	— t/s	—	— in — out
182	inclusionAI: Ling-2.6-1T (free) inclusionai/ling-2.6-1t:free	Inclusionai	—	— t/s	—	— in — out
183	Tencent: Hy3 preview (free) tencent/hy3-preview:free	Tencent	—	— t/s	—	— in — out
184	Ling-3.0-flash (free) inclusionai/ling-3.0-flash:free	Inclusionai	—	— t/s	—	— in — out
185	inclusionAI: Ling 3.0 Flash VL (free) inclusionai/ling-3.0-flash-vl:free	Inclusionai	—	— t/s	—	— in — out
186	Pareto 26.10 Preview unbiased/pareto-26.10-preview	Unbiased	—	— t/s	—	— in — out
187	OpenAI: GPT-6.1 Sol Pro openai/gpt-6.1-sol-pro	OpenAI	—	— t/s	—	— in — out
188	OpenAI: GPT-6.1 Sol Pro (batch) openai/gpt-6.1-sol-pro:batch	OpenAI	—	— t/s	—	— in — out
189	OpenAI: GPT-6.1 Sol (batch) openai/gpt-6.1-sol:batch	OpenAI	—	— t/s	—	— in — out
190	Anthropic: Claude Sonnet 5.5 (batch) anthropic/claude-sonnet-5.5:batch	Anthropic	—	— t/s	—	— in — out
191	Pareto unbiased/pareto	Unbiased	—	— t/s	—	— in — out
192	TypeSafe: Jev Router typesafe/jev-router	Typesafe	—	— t/s	—	— in — out
193	Baidu: Qianfan-OCR-Fast baidu/qianfan-ocr-fast	Baidu	—	— t/s	—	— in — out
194	Poolside: Laguna XS.2 (free) poolside/laguna-xs.2:free	Poolside	—	— t/s	—	— in — out
195	Poolside: Laguna XS.2 poolside/laguna-xs.2	Poolside	—	— t/s	—	— in — out
196	Perceptron: Perceptron Mk1.5 perceptron/perceptron-mk1.5	Perceptron	—	— t/s	—	— in — out
197	Baidu: Qianfan-OCR-Fast (free) baidu/qianfan-ocr-fast:free	Baidu	—	— t/s	—	— in — out
198	Z.ai: GLM 5.3 Prime z-ai/glm-5.3-prime	Z-ai	—	— t/s	—	— in — out
199	Qwen: Qwen3.8 Max Prime qwen/qwen3.8-max-prime	Alibaba / Qwen	—	— t/s	—	— in — out
200	Arcee AI: Trinity Large Thinking (free) arcee-ai/trinity-large-thinking:free	Arcee-ai	—	— 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.