📊 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: 07. September 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	OpenAI: GPT-6 Astra openai/gpt-6-astra	OpenAI	54,3	57,5 t/s	61,93 s	$10.00 in $50.00 out
2	Anthropic: Claude Fable 5.1 anthropic/claude-fable-5.1	Anthropic	53,8	51,7 t/s	34,81 s	$10.00 in $50.00 out
3	Anthropic: Claude Fable 5 anthropic/claude-fable-5	Anthropic	53,2	59,4 t/s	53,36 s	$10.00 in $50.00 out
4	Meta: Muse Spark 1.3 meta/muse-spark-1.3	Meta	51,6	107,9 t/s	45,19 s	$1.25 in $4.25 out
5	Claude Opus 5 anthropic/claude-opus-5	Anthropic	49,5	49,1 t/s	9,07 s	$5.00 in $25.00 out
6	SpaceXAI: Grok 4.6 x-ai/grok-4.6	xAI	48,4	55,4 t/s	35,79 s	$2.00 in $6.00 out
7	OpenAI: GPT-5.6 Sol openai/gpt-5.6-sol	OpenAI	48,3	73,5 t/s	6,91 s	$4.00 in $20.00 out
8	Google: Gemini 3.8 Flash google/gemini-3.8-flash	Google	46,8	392 t/s	5,04 s	$0.75 in $3.75 out
9	Meta: Muse Spark 1.2 meta/muse-spark-1.2	Meta	46,8	223,6 t/s	7,37 s	$1.25 in $4.25 out
10	Anthropic: Claude Opus 4.8 anthropic/claude-opus-4.8	Anthropic	46,4	0 t/s	0 ms	$5.00 in $25.00 out
11	SpaceXAI: Grok 4.5 x-ai/grok-4.5	xAI	45,5	48,4 t/s	11,13 s	$2.00 in $6.00 out
12	OpenAI: GPT-5.5 openai/gpt-5.5	OpenAI	44,1	0 t/s	0 ms	$5.00 in $30.00 out
13	Google: Gemini 3.7 Flash google/gemini-3.7-flash	Google	43,4	294,3 t/s	4,37 s	$0.75 in $3.75 out
14	Meta: Muse Spark 1.1 meta/muse-spark-1.1	Meta	43,3	0 t/s	0 ms	$1.25 in $4.25 out
15	DeepSeek: DeepSeek V4 Pro 0423 deepseek/deepseek-v4-pro	DeepSeek	42,1	59,5 t/s	1,11 s	$1.32 in $3.96 out
16	OpenAI: GPT-5.6 Terra openai/gpt-5.6-terra	OpenAI	41,3	87,0 t/s	2,71 s	$2.00 in $12.00 out
17	Google: Gemini 3.6 Flash google/gemini-3.6-flash	Google	40,3	185,7 t/s	11,51 s	$0.75 in $3.75 out
18	Google: Gemini 3.5 Flash google/gemini-3.5-flash	Google	39,7	0 t/s	0 ms	$1.50 in $9.00 out
19	OpenAI: GPT-5.3-Codex openai/gpt-5.3-codex	OpenAI	36,9	120,1 t/s	31,50 s	$1.75 in $14.00 out
20	Google: Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview	Google	36,7	117,4 t/s	20,28 s	$2.00 in $12.00 out
21	MiniMax: MiniMax M3 minimax/minimax-m3	MiniMax	35,7	84,6 t/s	1,12 s	$0.30 in $1.20 out
22	Anthropic: Claude Opus 4.7 anthropic/claude-opus-4.7	Anthropic	35,4	0 t/s	0 ms	$5.00 in $25.00 out
23	Anthropic: Claude Sonnet 5 anthropic/claude-sonnet-5	Anthropic	33,5	60,0 t/s	1,25 s	$2.00 in $10.00 out
24	Xiaomi: MiMo-V2-Pro xiaomi/mimo-v2-pro	Xiaomi	33,1	0 t/s	0 ms	$0 in $0 out
25	DeepSeek: DeepSeek V4 Flash 0423 deepseek/deepseek-v4-flash	DeepSeek	33,1	0 t/s	0 ms	$0.13 in $0.28 out
26	OpenAI: GPT-5.2-Codex openai/gpt-5.2-codex	OpenAI	33	0 t/s	0 ms	$1.75 in $14.00 out
27	Upstage: Solar Pro 4 upstage/solar-pro4	Upstage	32,7	59,1 t/s	1,22 s	$0.30 in $1.20 out
28	Xiaomi: MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro	Xiaomi	32,6	34,3 t/s	4,02 s	$0.435 in $0.87 out
29	OpenAI: GPT-5.2 openai/gpt-5.2	OpenAI	30,9	0 t/s	0 ms	$1.75 in $14.00 out
30	Anthropic: Claude Opus 4.6 anthropic/claude-opus-4.6	Anthropic	30,8	0 t/s	0 ms	$5.00 in $25.00 out
31	OpenAI: GPT-5.6 Luna openai/gpt-5.6-luna	OpenAI	30,2	102,4 t/s	2,18 s	$0.20 in $1.20 out
32	MiniMax: MiniMax M2.7 minimax/minimax-m2.7	MiniMax	30,1	0 t/s	0 ms	$0.30 in $1.20 out
33	NVIDIA: Nemotron 3 Ultra nvidia/nemotron-3-ultra-550b-a55b	NVIDIA	29,6	156,4 t/s	1,21 s	$0.60 in $2.60 out
34	SpaceXAI: Grok 4.3 x-ai/grok-4.3	xAI	29,3	0 t/s	0 ms	$1.25 in $2.50 out
35	OpenAI: GPT-5 Codex openai/gpt-5-codex	OpenAI	29,2	0 t/s	0 ms	$1.25 in $10.00 out
36	Anthropic: Claude Sonnet 4.6 anthropic/claude-sonnet-4.6	Anthropic	29	0 t/s	0 ms	$3.00 in $15.00 out
37	Xiaomi: MiMo-V2-Omni xiaomi/mimo-v2-omni	Xiaomi	28,1	0 t/s	0 ms	$0 in $0 out
38	OpenAI: GPT-5.1-Codex openai/gpt-5.1-codex	OpenAI	27,9	0 t/s	0 ms	$1.25 in $10.00 out
39	Anthropic: Claude Opus 4.5 anthropic/claude-opus-4.5	Anthropic	27,8	0 t/s	0 ms	$5.00 in $25.00 out
40	Google: Gemini 3.5 Flash Lite google/gemini-3.5-flash-lite	Google	27,6	315,5 t/s	6,75 s	$0.30 in $2.50 out
41	inclusionAI: Ling 3.0 Flash inclusionai/ling-3.0-flash	Inclusionai	27,4	347,2 t/s	1,60 s	$0.075 in $0.22 out
42	MiniMax: MiniMax M2.5 minimax/minimax-m2.5	MiniMax	26,8	0 t/s	0 ms	$0.30 in $1.20 out
43	Tencent: Hy3 preview tencent/hy3-preview	Tencent	26,8	0 t/s	0 ms	$0.063 in $0.21 out
44	xAI: Grok 4 x-ai/grok-4	xAI	26,5	0 t/s	0 ms	$3.00 in $15.00 out
45	OpenAI: o3 Pro openai/o3-pro	OpenAI	25,7	0 t/s	0 ms	$20.00 in $80.00 out
46	MiniMax: MiniMax M2.1 minimax/minimax-m2.1	MiniMax	24,6	0 t/s	0 ms	$0.30 in $1.20 out
47	Xiaomi: MiMo-V2-Flash xiaomi/mimo-v2-flash	Xiaomi	24,5	0 t/s	0 ms	$0.10 in $0.30 out
48	OpenAI: GPT-5 openai/gpt-5	OpenAI	24,4	0 t/s	0 ms	$1.25 in $10.00 out
49	OpenAI: GPT-5 Mini openai/gpt-5-mini	OpenAI	24,2	0 t/s	0 ms	$0.25 in $2.00 out
50	OpenAI: GPT-5.1-Codex-Mini openai/gpt-5.1-codex-mini	OpenAI	24	0 t/s	0 ms	$0.25 in $2.00 out
51	OpenAI: o3 openai/o3	OpenAI	23,7	122,5 t/s	4,41 s	$2.00 in $8.00 out
52	inclusionAI: Ring-2.6-1T inclusionai/ring-2.6-1t	Inclusionai	23,7	121,8 t/s	2,06 s	$0.30 in $2.50 out
53	OpenAI: GPT-5.4 Nano openai/gpt-5.4-nano	OpenAI	23,5	0 t/s	0 ms	$0.20 in $1.25 out
54	DeepSeek: DeepSeek V3.1 Terminus deepseek/deepseek-v3.1-terminus	DeepSeek	23,5	0 t/s	0 ms	$1.635 in $2.75 out
55	StepFun: Step 3.7 Flash stepfun/step-3.7-flash	Stepfun	22,9	77,6 t/s	2,23 s	$0.20 in $1.15 out
56	Anthropic: Claude Sonnet 4.5 anthropic/claude-sonnet-4.5	Anthropic	22,7	0 t/s	0 ms	$3.00 in $15.00 out
57	Mistral: Mistral Medium 3.5 mistralai/mistral-medium-3-5	Mistral	22,7	139,3 t/s	710 ms	$1.50 in $7.50 out
58	MiniMax: MiniMax M2 minimax/minimax-m2	MiniMax	21,7	0 t/s	0 ms	$0.30 in $1.20 out
59	Anthropic: Claude Opus 4.1 anthropic/claude-opus-4.1	Anthropic	21,7	0 t/s	0 ms	$15.00 in $75.00 out
60	OpenAI: GPT-5.4 openai/gpt-5.4	OpenAI	21,1	0 t/s	0 ms	$2.50 in $15.00 out
61	xAI: Grok 4 Fast x-ai/grok-4-fast	xAI	20,8	0 t/s	0 ms	$0.20 in $0.50 out
62	inclusionAI: Ling-2.6-1T inclusionai/ling-2.6-1t	Inclusionai	19,6	0 t/s	0 ms	$0.30 in $2.50 out
63	Tencent: Hy3 tencent/hy3	Tencent	19,6	0 t/s	0 ms	$0.063 in $0.21 out
64	StepFun: Step 3.5 Flash stepfun/step-3.5-flash	Stepfun	19,5	0 t/s	0 ms	$0.10 in $0.30 out
65	Anthropic: Claude Opus 4 anthropic/claude-opus-4	Anthropic	19,1	0 t/s	0 ms	$15.00 in $75.00 out
66	OpenAI: o4 Mini openai/o4-mini	OpenAI	19,1	0 t/s	0 ms	$1.10 in $4.40 out
67	Anthropic: Claude Sonnet 4 anthropic/claude-sonnet-4	Anthropic	19,1	0 t/s	0 ms	$3.00 in $15.00 out
68	Google: Gemini 2.5 Pro google/gemini-2.5-pro	Google	19	0 t/s	0 ms	$1.25 in $10.00 out
69	Google: Gemini 3.1 Flash Lite Preview google/gemini-3.1-flash-lite-preview	Google	18,7	0 t/s	0 ms	$0.25 in $1.50 out
70	NVIDIA: Nemotron 3 Super nvidia/nemotron-3-super-120b-a12b	NVIDIA	18,6	141,9 t/s	1,12 s	$0.20 in $0.80 out
71	DeepSeek: DeepSeek V3.2 deepseek/deepseek-v3.2	DeepSeek	18,3	0 t/s	0 ms	$0.28 in $0.42 out
72	Anthropic: Claude Haiku 4.5 anthropic/claude-haiku-4.5	Anthropic	17,4	82,1 t/s	598 ms	$1.00 in $5.00 out
73	Anthropic: Claude 3.7 Sonnet anthropic/claude-3.7-sonnet	Anthropic	17,2	0 t/s	0 ms	$3.00 in $15.00 out
74	OpenAI: o1 openai/o1	OpenAI	17,1	0 t/s	0 ms	$15.00 in $60.00 out
75	NVIDIA: Nemotron 3.5 Lightning nvidia/nemotron-3.5-lightning	NVIDIA	16,4	295,6 t/s	461 ms	$0.06 in $0.20 out
76	xAI: Grok 3 Mini x-ai/grok-3-mini	xAI	16,2	0 t/s	0 ms	$0.30 in $0.50 out
77	DeepSeek: DeepSeek V3.2 Speciale deepseek/deepseek-v3.2-speciale	DeepSeek	16	0 t/s	0 ms	$0 in $0 out
78	SpaceXAI: Grok 4.20 x-ai/grok-4.20	xAI	15,6	0 t/s	0 ms	$1.25 in $2.50 out
79	xAI: Grok Code Fast 1 x-ai/grok-code-fast-1	xAI	15,4	0 t/s	0 ms	$0 in $0 out
80	Inception: Mercury 2 inception/mercury-2	Inception	14,9	794,9 t/s	3,93 s	$0.25 in $0.75 out
81	OpenAI: GPT-5.1 openai/gpt-5.1	OpenAI	14,2	0 t/s	0 ms	$1.25 in $10.00 out
82	Google: Gemini 2.5 Flash google/gemini-2.5-flash	Google	13,9	0 t/s	0 ms	$0.30 in $2.50 out
83	DeepSeek: R1 deepseek/deepseek-r1	DeepSeek	13,9	0 t/s	0 ms	$1.35 in $3.00 out
84	OpenAI: GPT-4.1 openai/gpt-4.1	OpenAI	13,2	0 t/s	0 ms	$2.00 in $8.00 out
85	OpenAI: GPT-5 Nano openai/gpt-5-nano	OpenAI	12,9	0 t/s	0 ms	$0.05 in $0.40 out
86	OpenAI: o1-pro openai/o1-pro	OpenAI	12,8	0 t/s	0 ms	$150.00 in $600.00 out
87	Perplexity: Sonar Reasoning Pro perplexity/sonar-reasoning-pro	Perplexity	11,8	0 t/s	0 ms	$0 in $0 out
88	xAI: Grok 4.1 Fast x-ai/grok-4.1-fast	xAI	10,9	0 t/s	0 ms	$0 in $0 out
89	OpenAI: GPT-5.4 Mini openai/gpt-5.4-mini	OpenAI	10,6	0 t/s	0 ms	$0.75 in $4.50 out
90	Prime Intellect: INTELLECT-3 prime-intellect/intellect-3	Prime-intellect	9,6	0 t/s	0 ms	$0 in $0 out
91	OpenAI: o3 Mini openai/o3-mini	OpenAI	9,6	0 t/s	0 ms	$1.10 in $4.40 out
92	xAI: Grok 3 x-ai/grok-3	xAI	9,2	0 t/s	0 ms	$0 in $0 out
93	OpenAI: gpt-oss-120b openai/gpt-oss-120b	OpenAI	8,9	211,8 t/s	456 ms	$0.15 in $0.545 out
94	OpenAI: GPT-4.1 Mini openai/gpt-4.1-mini	OpenAI	8,8	0 t/s	0 ms	$0.40 in $1.60 out
95	Meta: Llama 4 Maverick meta-llama/llama-4-maverick	Meta	8,5	84,5 t/s	582 ms	$0.26 in $0.91 out
96	Upstage: Solar Pro 3 upstage/solar-pro-3	Upstage	8,5	139,4 t/s	1,17 s	$0.15 in $0.60 out
97	Mistral: Mistral Medium 3.1 mistralai/mistral-medium-3.1	Mistral	8,4	0 t/s	0 ms	$0.40 in $2.00 out
98	OpenAI: gpt-oss-20b openai/gpt-oss-20b	OpenAI	8,4	232,4 t/s	553 ms	$0.07 in $0.20 out
99	inclusionAI: Ling-2.6-flash inclusionai/ling-2.6-flash	Inclusionai	7,9	0 t/s	0 ms	$0 in $0 out
100	Google: Gemini 2.5 Flash Lite Preview 09-2025 google/gemini-2.5-flash-lite-preview-09-2025	Google	7,3	0 t/s	0 ms	$0.10 in $0.40 out
101	Mistral: Mistral Medium 3 mistralai/mistral-medium-3	Mistral	6,7	0 t/s	0 ms	$0.40 in $2.00 out
102	Anthropic: Claude 3.5 Haiku anthropic/claude-3.5-haiku	Anthropic	6,5	0 t/s	0 ms	$0 in $0 out
103	Perplexity: Sonar perplexity/sonar	Perplexity	5,9	0 t/s	0 ms	$0 in $0 out
104	OpenAI: GPT-4o openai/gpt-4o	OpenAI	5,4	0 t/s	0 ms	$2.50 in $10.00 out
105	DeepSeek: R1 Distill Qwen 32B deepseek/deepseek-r1-distill-qwen-32b	DeepSeek	5,3	0 t/s	0 ms	$0 in $0 out
106	Meta: Llama 4 Scout meta-llama/llama-4-scout	Meta	4,6	85,2 t/s	611 ms	$0.19 in $0.68 out
107	DeepSeek: R1 Distill Llama 70B deepseek/deepseek-r1-distill-llama-70b	DeepSeek	4,2	0 t/s	0 ms	$0.70 in $1.10 out
108	OpenAI: GPT-4.1 Nano openai/gpt-4.1-nano	OpenAI	4,1	0 t/s	0 ms	$0.10 in $0.40 out
109	OpenAI: GPT-4o (2024-08-06) openai/gpt-4o-2024-08-06	OpenAI	3,9	0 t/s	0 ms	$2.50 in $10.00 out
110	Meta: Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct	Meta	3,7	90,4 t/s	617 ms	$0.655 in $0.72 out
111	Mistral: Devstral Small 1.1 mistralai/devstral-small	Mistral	3,6	0 t/s	0 ms	$0 in $0 out
112	Perplexity: Sonar Pro perplexity/sonar-pro	Perplexity	3,6	0 t/s	0 ms	$0 in $0 out
113	NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 nvidia/llama-3.1-nemotron-ultra-253b-v1	NVIDIA	3,4	52,8 t/s	685 ms	$0.60 in $1.80 out
114	Baidu: ERNIE 4.5 300B A47B baidu/ernie-4.5-300b-a47b	Baidu	3,4	0 t/s	0 ms	$0.28 in $1.10 out
115	NVIDIA: Nemotron Nano 12B 2 VL nvidia/nemotron-nano-12b-v2-vl	NVIDIA	3,3	25,5 t/s	10,10 s	$0.20 in $0.60 out
116	Google: Gemini 2.0 Flash Lite google/gemini-2.0-flash-lite-001	Google	3,2	0 t/s	0 ms	$0 in $0 out
117	NVIDIA: Nemotron Nano 9B V2 nvidia/nemotron-nano-9b-v2	NVIDIA	3,2	94,5 t/s	4,37 s	$0.04 in $0.16 out
118	OpenAI: GPT-4o (2024-05-13) openai/gpt-4o-2024-05-13	OpenAI	3	0 t/s	0 ms	$5.00 in $15.00 out
119	Mistral: Pixtral Large 2411 mistralai/pixtral-large-2411	Mistral	2,5	0 t/s	0 ms	$0 in $0 out
120	OpenAI: GPT-4 Turbo openai/gpt-4-turbo	OpenAI	2,3	0 t/s	0 ms	$10.00 in $30.00 out
121	Cohere: Command A cohere/command-a	Cohere	2,1	58,8 t/s	323 ms	$2.50 in $10.00 out
122	NVIDIA: Llama 3.1 Nemotron 70B Instruct nvidia/llama-3.1-nemotron-70b-instruct	NVIDIA	2,1	19,3 t/s	17,25 s	$1.20 in $1.20 out
123	Meta: Llama 3.1 8B Instruct meta-llama/llama-3.1-8b-instruct	Meta	2	0 t/s	0 ms	$0.02 in $0.05 out
124	NVIDIA: Nemotron 3 Nano 30B A3B nvidia/nemotron-3-nano-30b-a3b	NVIDIA	1,8	165,8 t/s	400 ms	$0.05 in $0.20 out
125	Mistral Large 2407 mistralai/mistral-large-2407	Mistral	1,7	0 t/s	0 ms	$2.00 in $6.00 out
126	OpenAI: GPT-4 openai/gpt-4	OpenAI	1,5	0 t/s	0 ms	$30.00 in $60.00 out
127	Google: Gemini 2.5 Flash Lite google/gemini-2.5-flash-lite	Google	1,4	0 t/s	0 ms	$0.10 in $0.40 out
128	OpenAI: GPT-4o-mini openai/gpt-4o-mini	OpenAI	1,4	0 t/s	0 ms	$0.15 in $0.60 out
129	Meta: Llama 3.1 70B Instruct meta-llama/llama-3.1-70b-instruct	Meta	1,2	0 t/s	0 ms	$0.56 in $0.56 out
130	Mistral: Mixtral 8x7B Instruct mistralai/mixtral-8x7b-instruct	Mistral	1	0 t/s	0 ms	$0.45 in $0.70 out
131	Meta: Llama 3 70B Instruct meta-llama/llama-3-70b-instruct	Meta	1	0 t/s	0 ms	$0.65 in $2.75 out
132	Mistral: Saba mistralai/mistral-saba	Mistral	1	0 t/s	0 ms	$0 in $0 out
133	Meta: Llama 3 8B Instruct meta-llama/llama-3-8b-instruct	Meta	1	0 t/s	0 ms	$0.045 in $0.145 out
134	Mistral Large mistralai/mistral-large	Mistral	1	0 t/s	0 ms	$4.00 in $12.00 out
135	Meta: Llama 3.2 11B Vision Instruct meta-llama/llama-3.2-11b-vision-instruct	Meta	1	26,8 t/s	583 ms	$0.345 in $0.345 out
136	Meta: Llama 3.2 1B Instruct meta-llama/llama-3.2-1b-instruct	Meta	1	0 t/s	0 ms	$0 in $0 out
137	Meta: Llama 3.2 3B Instruct meta-llama/llama-3.2-3b-instruct	Meta	1	0 t/s	0 ms	$0 in $0 out
138	Anthropic: Claude 3 Haiku anthropic/claude-3-haiku	Anthropic	1	0 t/s	0 ms	$0.25 in $1.25 out
139	Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-0902	Alibaba / Qwen	—	— t/s	—	— in — out
140	OpenAI: GPT-6 Astra (batch) openai/gpt-6-astra:batch	OpenAI	—	— t/s	—	— in — out
141	OpenAI: GPT-6 Astra Pro openai/gpt-6-astra-pro	OpenAI	—	— t/s	—	— in — out
142	Elephant openrouter/elephant-alpha	Openrouter	—	— t/s	—	— in — out
143	inclusionAI: Ring-2.6-1T (free) inclusionai/ring-2.6-1t:free	Inclusionai	—	— t/s	—	— in — out
144	OpenAI: GPT-6 Astra Pro (batch) openai/gpt-6-astra-pro:batch	OpenAI	—	— t/s	—	— in — out
145	inclusionAI: Ling 3.0 Flash Sante (free) inclusionai/ling-3.0-flash-sante:free	Inclusionai	—	— t/s	—	— in — out
146	Nex AGI: Nex-N2-Pro (free) nex-agi/nex-n2-pro:free	Nex-agi	—	— t/s	—	— in — out
147	Ox Alpha stealth/ox-alpha	Stealth	—	— t/s	—	— in — out
148	Baidu Qianfan: CoBuddy (free) baidu/cobuddy:free	Baidu	—	— t/s	—	— in — out
149	DeepSeek: DeepSeek V4 Flash (free) deepseek/deepseek-v4-flash:free	DeepSeek	—	— t/s	—	— in — out
150	MoonshotAI: Kimi K3 moonshotai/kimi-k3	Moonshot AI	—	— t/s	—	— in — out
151	Meta: Muse Spark 1.3 Contributor meta/muse-spark-1.3-contributor	Meta	—	— t/s	—	— in — out
152	Inception: Mercury 2.5 Preview inception/mercury-2.5-preview	Inception	—	— t/s	—	— in — out
153	inclusionAI: Ling 3.0 Tiny (free) inclusionai/ling-3.0-tiny:free	Inclusionai	—	— t/s	—	— in — out
154	IBM: Granite 4.2 8B ibm-granite/granite-4.2-8b	Ibm-granite	—	— t/s	—	— in — out
155	Google: Gemini 3.8 Flash (batch) google/gemini-3.8-flash:batch	Google	—	— t/s	—	— in — out
156	Tencent: Hy4 preview tencent/hy4-preview	Tencent	—	— t/s	—	— in — out
157	Anthropic: Claude Fable 5.1 (batch) anthropic/claude-fable-5.1:batch	Anthropic	—	— t/s	—	— in — out
158	Z.ai: GLM Flash Latest ~z-ai/glm-flash-latest	~z-ai	—	— t/s	—	— in — out
159	Tencent: Hy3 (free) tencent/hy3:free	Tencent	—	— t/s	—	— in — out
160	inclusionAI: Ling 3.0 Flash Fin inclusionai/ling-3.0-flash-fin	Inclusionai	—	— t/s	—	— in — out
161	inclusionAI: Ling-2.6-flash (free) inclusionai/ling-2.6-flash:free	Inclusionai	—	— t/s	—	— in — out
162	Owl Alpha openrouter/owl-alpha	Openrouter	—	— t/s	—	— in — out
163	DeepSeek: DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp	DeepSeek	—	— t/s	—	— in — out
164	Tencent: Hy-MT2-1.8B tencent/hy-mt2-1.8b	Tencent	—	— t/s	—	— in — out
165	inclusionAI: Ling-2.6-1T (free) inclusionai/ling-2.6-1t:free	Inclusionai	—	— t/s	—	— in — out
166	Tencent: Hy3 preview (free) tencent/hy3-preview:free	Tencent	—	— t/s	—	— in — out
167	Ling-3.0-flash (free) inclusionai/ling-3.0-flash:free	Inclusionai	—	— t/s	—	— in — out
168	Z.ai: GLM Latest ~z-ai/glm-latest	~z-ai	—	— t/s	—	— in — out
169	inclusionAI: Ling 3.0 Flash Fin (free) inclusionai/ling-3.0-flash-fin:free	Inclusionai	—	— t/s	—	— in — out
170	Qwen: Qwen3.8 Flash qwen/qwen3.8-flash	Alibaba / Qwen	—	— t/s	—	— in — out
171	Z.ai: GLM 5.3 Flash z-ai/glm-5.3-flash	Z-ai	—	— t/s	—	— in — out
172	Z.ai: GLM 5.3 Flash (batch) z-ai/glm-5.3-flash:batch	Z-ai	—	— t/s	—	— in — out
173	Meta: Muse Spark 1.2 Contributor meta/muse-spark-1.2-contributor	Meta	—	— t/s	—	— in — out
174	Baidu: Qianfan-OCR-Fast baidu/qianfan-ocr-fast	Baidu	—	— t/s	—	— in — out
175	Poolside: Laguna XS.2 (free) poolside/laguna-xs.2:free	Poolside	—	— t/s	—	— in — out
176	Poolside: Laguna XS.2 poolside/laguna-xs.2	Poolside	—	— t/s	—	— in — out
177	Baidu: Qianfan-OCR-Fast (free) baidu/qianfan-ocr-fast:free	Baidu	—	— t/s	—	— in — out
178	Google: Gemini 3.7 Flash (batch) google/gemini-3.7-flash:batch	Google	—	— t/s	—	— in — out
179	Arcee AI: Trinity Large Thinking (free) arcee-ai/trinity-large-thinking:free	Arcee-ai	—	— t/s	—	— in — out
180	Tencent: Hy-MT2-30B-A3B tencent/hy-mt2-30b-a3b	Tencent	—	— t/s	—	— in — out
181	Tencent: Hy-MT2-7B tencent/hy-mt2-7b	Tencent	—	— t/s	—	— in — out
182	Z.ai: GLM 5.3 z-ai/glm-5.3	Z-ai	—	— t/s	—	— in — out
183	Qwen: Qwen3.8 27B qwen/qwen3.8-27b	Alibaba / Qwen	—	— t/s	—	— in — out
184	Dots Studio: Dots3-Note Preview (free) dots-studio/dots-3-note-preview:free	Dots-studio	—	— t/s	—	— in — out
185	Qwen: Qwen3.6 Plus (free) qwen/qwen3.6-plus:free	Alibaba / Qwen	—	— t/s	—	— in — out
186	Anthropic: Claude Opus 4.6 (Fast) anthropic/claude-opus-4.6-fast	Anthropic	—	— t/s	—	— in — out
187	MoonshotAI: Kimi K2.6 (free) moonshotai/kimi-k2.6:free	Moonshot AI	—	— t/s	—	— in — out
188	Claude Opus 5 (Fast) anthropic/claude-opus-5-fast	Anthropic	—	— t/s	—	— in — out
189	LiquidAI: LFM2.5-2.6B (free) liquid/lfm-2.5-2.6b:free	Liquid	—	— t/s	—	— in — out
190	ByteDance Seed: Seed 2.1 Turbo bytedance-seed/seed-2-1-turbo	Bytedance-seed	—	— t/s	—	— in — out
191	Qwen: Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b	Alibaba / Qwen	—	— t/s	—	— in — out
192	Qwen: Qwen3.8 2.4T A95B (batch) qwen/qwen3.8-2.4t-a95b:batch	Alibaba / Qwen	—	— t/s	—	— in — out
193	ByteDance Seed: Seed-2.0-Code bytedance-seed/seed-2.0-code	Bytedance-seed	—	— t/s	—	— in — out
194	DeepSeek: DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813	DeepSeek	—	— t/s	—	— in — out
195	DeepSeek: DeepSeek V4 Pro 0813 (batch) deepseek/deepseek-v4-pro-0813:batch	DeepSeek	—	— t/s	—	— in — out
196	MiniMax: MiniMax M2.5 (free) minimax/minimax-m2.5:free	MiniMax	—	— t/s	—	— in — out
197	Arcee AI: Trinity Large Preview arcee-ai/trinity-large-preview	Arcee-ai	—	— t/s	—	— in — out
198	DeepSeek: DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731	DeepSeek	—	— t/s	—	— in — out
199	NVIDIA: Nemotron 3.5 Lightning (free) nvidia/nemotron-3.5-lightning:free	NVIDIA	—	— t/s	—	— in — out
200	AllenAI: Olmo 3.1 32B Instruct allenai/olmo-3.1-32b-instruct	Allenai	—	— 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.