Modell	Anbieter	Intelligenz	Coding	Input $/M	Output $/M	Mischpreis $/M	Geschw. t/s	TTFT s	Kontext	Wert ↓
Qwen3.5 0.8B (Reasoning)	Alibaba	10.5	0.0	$0.01	$0.05	$0.02	0.0	0.00	—	525.0
Qwen3.5 0.8B (Non-reasoning)	Alibaba	9.9	1.0	$0.01	$0.05	$0.02	88.5	0.26	—	495.0
Qwen3.5 4B (Reasoning)	Alibaba	27.1	17.5	$0.03	$0.15	$0.06	189.8	0.24	—	451.7
Qwen3.5 2B (Reasoning)	Alibaba	16.3	3.5	$0.02	$0.10	$0.04	0.0	0.00	—	407.5
Qwen3.5 4B (Non-reasoning)	Alibaba	22.6	13.7	$0.03	$0.15	$0.06	171.1	0.24	—	376.7
Qwen3.5 2B (Non-reasoning)	Alibaba	14.7	4.9	$0.02	$0.10	$0.04	319.3	0.24	—	367.5
Qwen3.5 9B (Reasoning)	Alibaba	32.4	25.3	$0.10	$0.15	$0.11	47.8	0.34	—	286.7
gpt-oss-20B (high)	OpenAI	24.5	18.5	$0.05	$0.20	$0.09	269.1	0.42	—	278.4
MiMo-V2-Flash (Feb 2026)	Xiaomi	41.5	33.5	$0.10	$0.30	$0.15	125.7	1.45	—	276.7
DeepSeek V4 Flash (Reasoning, Max Effort)	DeepSeek	46.5	38.7	$0.14	$0.28	$0.17	105.2	0.75	—	265.7
DeepSeek V4 Flash (Reasoning, High Effort)	DeepSeek	46.0	39.8	$0.14	$0.28	$0.17	0.0	0.00	—	262.9
MiMo-V2-Flash (Reasoning)	Xiaomi	39.2	31.8	$0.10	$0.30	$0.15	128.3	1.56	—	261.3
Gemma 3n E4B Instruct	Google	6.4	4.2	$0.02	$0.04	$0.03	55.3	0.44	—	256.0
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)	NVIDIA	24.3	19.0	$0.06	$0.22	$0.10	137.8	1.18	—	253.1
Step 3.5 Flash	StepFun	37.8	31.6	$0.10	$0.30	$0.15	152.4	0.95	—	252.0
gpt-oss-20B (low)	OpenAI	20.8	14.4	$0.06	$0.20	$0.10	273.4	0.48	—	218.9
NVIDIA Nemotron Nano 9B V2 (Reasoning)	NVIDIA	14.8	8.3	$0.04	$0.16	$0.07	123.3	0.22	—	211.4
Hy3-preview (Reasoning)	Tencent	41.9	36.5	$0.12	$0.43	$0.20	101.9	2.44	—	209.5
DeepSeek V4 Flash (Non-reasoning)	DeepSeek	36.5	35.2	$0.14	$0.28	$0.17	97.8	0.86	—	208.6
MiMo-V2-Flash (Non-reasoning)	Xiaomi	30.3	25.8	$0.10	$0.30	$0.15	128.3	1.20	—	202.0
LFM2 24B A2B	Liquid AI	10.5	3.6	$0.03	$0.12	$0.05	151.2	0.27	—	201.9
Granite 4.1 8B	IBM	12.4	7.3	$0.05	$0.10	$0.06	134.2	0.41	—	196.8
GLM-4.7-Flash (Reasoning)	Z AI	30.1	25.9	$0.07	$0.40	$0.15	71.9	0.84	—	196.7
GPT-5 nano (high)	OpenAI	26.8	20.3	$0.05	$0.40	$0.14	159.1	83.05	—	194.2
GPT-5 nano (medium)	OpenAI	25.9	22.9	$0.05	$0.40	$0.14	161.3	32.98	—	187.7
Ling 2.6 Flash	InclusionAI	26.2	23.2	$0.10	$0.30	$0.15	0.0	0.00	—	174.7
Nova Micro	Amazon	10.3	4.1	$0.04	$0.14	$0.06	307.1	0.62	—	168.9
Hy3-preview (Non-reasoning)	Tencent	33.7	34.3	$0.12	$0.43	$0.20	87.8	2.69	—	168.5
Nemotron 3 Nano Omni 30B A3B Reasoning	NVIDIA	21.4	14.8	$0.07	$0.30	$0.13	301.0	0.62	—	163.4
Gemma 4 26B A4B (Reasoning)	Google	31.2	22.4	$0.13	$0.40	$0.20	0.0	0.00	—	157.6
Gemma 4 31B (Non-reasoning)	Google	32.3	33.9	$0.14	$0.40	$0.20	30.8	0.75	—	157.6
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)	NVIDIA	13.2	7.5	$0.05	$0.20	$0.09	125.4	0.34	—	153.5
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)	NVIDIA	13.2	15.8	$0.05	$0.20	$0.09	90.4	0.28	—	150.0
GLM-4.7-Flash (Non-reasoning)	Z AI	22.1	11.0	$0.07	$0.40	$0.15	195.1	1.24	—	144.4
Gemma 4 26B A4B (Non-reasoning)	Google	27.1	29.1	$0.13	$0.40	$0.20	83.7	0.77	—	136.9
Qwen2.5 Turbo	Alibaba	12.0	—	$0.05	$0.20	$0.09	70.5	1.26	—	136.4
Grok 4 Fast (Reasoning)	xAI	35.1	27.4	$0.20	$0.50	$0.28	0.0	0.00	—	127.6
gpt-oss-120b (high)	OpenAI	33.3	28.6	$0.15	$0.60	$0.26	315.4	0.48	—	127.1
Llama 3.2 Instruct 1B	Meta	6.3	0.6	$0.05	$0.05	$0.05	90.1	0.57	—	126.0
Gemma 3 4B Instruct	Google	6.3	2.9	$0.04	$0.08	$0.05	0.0	0.00	—	126.0
DeepSeek V3.2 (Reasoning)	DeepSeek	41.7	36.7	$0.30	$0.45	$0.34	0.0	0.00	—	123.7
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)	Google	21.6	18.2	$0.10	$0.40	$0.17	0.0	0.00	—	123.4
Mistral Small 3	Mistral	12.7	—	$0.07	$0.19	$0.10	157.0	0.51	—	122.1
Nova Lite	Amazon	12.7	5.1	$0.06	$0.24	$0.10	84.6	0.64	—	121.0
Llama 3.1 Instruct 8B	Meta	11.8	4.9	$0.10	$0.10	$0.10	218.4	0.45	—	118.0
Mistral Small 3.2	Mistral	15.1	13.3	$0.09	$0.25	$0.13	140.7	0.36	—	118.0
Ministral 3 3B	Mistral	11.2	4.8	$0.10	$0.10	$0.10	203.0	0.34	—	112.0
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)	Google	19.4	14.5	$0.10	$0.40	$0.17	0.0	0.00	—	110.9
Llama Nemotron Super 49B v1.5 (Reasoning)	NVIDIA	18.7	15.1	$0.10	$0.40	$0.17	49.7	0.30	—	106.9
DeepSeek V3.2 Exp (Reasoning)	DeepSeek	32.9	33.3	$0.28	$0.41	$0.31	0.0	0.00	—	106.1
Mistral Small 4 (Reasoning)	Mistral	27.8	24.3	$0.15	$0.60	$0.26	160.9	0.54	—	106.1
Mistral Small 3.1	Mistral	14.5	13.9	$0.10	$0.23	$0.14	152.3	0.51	—	105.1
Devstral Small (Jul '25)	Mistral	15.2	12.1	$0.10	$0.30	$0.15	203.1	0.40	—	101.3
Granite 4.0 H Small	IBM	10.8	8.5	$0.06	$0.25	$0.11	420.0	8.80	—	100.9
Gemini 2.5 Flash-Lite (Reasoning)	Google	17.6	9.5	$0.10	$0.40	$0.17	242.2	15.10	—	100.6
GPT-5 nano (minimal)	OpenAI	13.8	14.2	$0.05	$0.40	$0.14	151.7	0.68	—	100.0
Ministral 3 8B	Mistral	14.8	10.0	$0.15	$0.15	$0.15	112.9	0.36	—	98.7
Llama 2 Chat 7B	Meta	9.7	—	$0.05	$0.25	$0.10	94.1	8.42	—	97.0
GPT-5.4 nano (xhigh)	OpenAI	44.0	43.9	$0.20	$1.25	$0.46	159.3	1.92	—	95.0
DeepSeek V4 Pro (Reasoning, Max Effort)	DeepSeek	51.5	47.5	$0.43	$0.87	$0.54	44.2	1.24	—	94.7
MiniMax-M2.7	MiniMax	49.6	41.9	$0.30	$1.20	$0.53	51.2	1.14	—	94.5
Qwen3.5 Omni Flash	Alibaba	25.9	14.0	$0.10	$0.80	$0.28	231.6	0.95	—	94.2
Qwen3 30B A3B (Non-reasoning)	Alibaba	12.5	13.3	$0.08	$0.29	$0.13	68.0	1.09	—	94.0
gpt-oss-120b (low)	OpenAI	24.5	15.5	$0.15	$0.60	$0.26	363.6	0.47	—	93.5
Grok 3 mini Reasoning (high)	xAI	32.1	25.2	$0.30	$0.50	$0.35	51.7	0.46	—	91.7
DeepSeek V3.2 Exp (Non-reasoning)	DeepSeek	28.4	30.0	$0.28	$0.41	$0.31	0.0	0.00	—	91.6
DeepSeek V4 Pro (Reasoning, High Effort)	DeepSeek	49.8	43.2	$0.43	$0.87	$0.54	41.7	1.10	—	91.5
Llama 3 Instruct 8B	Meta	6.4	4.0	$0.04	$0.14	$0.07	82.3	0.50	—	91.4
Mercury 2	Inception	32.8	30.6	$0.25	$0.75	$0.38	718.8	3.42	—	87.5
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)	NVIDIA	36.0	31.2	$0.30	$0.75	$0.41	155.4	0.87	—	87.4
Qwen3 30B A3B (Reasoning)	Alibaba	15.3	11.0	$0.09	$0.45	$0.18	67.9	1.32	—	85.0
Grok 4 Fast (Non-reasoning)	xAI	23.1	19.0	$0.20	$0.50	$0.28	0.0	0.00	—	84.0
Seed-OSS-36B-Instruct	ByteDance Seed	25.2	16.7	$0.21	$0.57	$0.30	41.7	1.82	—	84.0
Llama Nemotron Super 49B v1.5 (Non-reasoning)	NVIDIA	14.6	10.5	$0.10	$0.40	$0.17	48.9	0.29	—	83.4
KAT Coder Pro V2	KwaiKAT	43.8	45.6	$0.30	$1.20	$0.53	106.6	1.94	—	83.4
Granite 3.3 8B (Non-reasoning)	IBM	7.0	3.4	$0.03	$0.25	$0.09	340.3	21.78	—	82.4
GPT-5.4 nano (medium)	OpenAI	38.1	35.0	$0.20	$1.25	$0.46	162.8	2.83	—	82.3
Hermes 4 - Llama-3.1 70B (Reasoning)	Nous Research	16.0	14.4	$0.13	$0.40	$0.20	73.8	0.62	—	80.8
Trinity Large Thinking	Arcee AI	31.9	27.2	$0.23	$0.88	$0.40	136.8	0.61	—	80.8
Ministral 3 14B	Mistral	16.0	10.9	$0.20	$0.20	$0.20	77.4	0.42	—	80.0
MiniMax-M2.5	MiniMax	41.9	37.4	$0.30	$1.20	$0.53	95.4	1.07	—	79.8
Solar Mini	Upstage	11.9	—	$0.15	$0.15	$0.15	72.3	0.77	—	79.3
Qwen3.6 35B A3B (Reasoning)	Alibaba	43.5	35.2	$0.25	$1.49	$0.56	169.5	1.19	—	78.1
MiniMax-M2.1	MiniMax	39.4	32.8	$0.30	$1.20	$0.53	86.2	1.08	—	75.0
GPT-4.1 nano	OpenAI	13.0	11.2	$0.10	$0.40	$0.17	193.2	0.37	—	74.3
Gemini 2.5 Flash-Lite (Non-reasoning)	Google	12.7	7.4	$0.10	$0.40	$0.17	260.6	5.95	—	72.6
DeepSeek V4 Pro (Non-reasoning)	DeepSeek	39.3	38.4	$0.43	$0.87	$0.54	42.9	1.22	—	72.2
Gemma 3 27B Instruct	Google	10.3	9.6	$0.11	$0.25	$0.14	0.0	0.00	—	71.0
Mistral Small 4 (Non-reasoning)	Mistral	18.6	16.4	$0.15	$0.60	$0.26	158.7	0.52	—	71.0
Gemini 2.0 Flash (Feb '25)	Google	18.5	13.6	$0.15	$0.60	$0.26	0.0	0.00	—	70.6
Qwen3 30B A3B 2507 Instruct	Alibaba	15.0	14.2	$0.15	$0.40	$0.21	106.0	1.21	—	70.4
Qwen3 235B A22B 2507 Instruct	Alibaba	25.0	22.1	$0.20	$0.82	$0.36	65.5	1.29	—	70.2
MiniMax-M2	MiniMax	36.1	29.2	$0.30	$1.20	$0.53	97.0	1.10	—	68.8
KAT-Coder-Pro V1	KwaiKAT	36.0	18.3	$0.30	$1.20	$0.53	95.8	2.62	—	68.6
MiMo-V2.5	Xiaomi	49.0	42.1	$0.36	$1.80	$0.72	93.2	1.98	—	68.1
Qwen3 4B (Non-reasoning)	Alibaba	12.5	—	$0.11	$0.42	$0.19	105.0	1.02	—	66.5
Olmo 3 7B Instruct	Allen Institute for AI	8.1	3.4	$0.10	$0.20	$0.13	0.0	0.00	—	64.8
Llama 3.2 Instruct 3B	Meta	9.7	—	$0.15	$0.15	$0.15	52.4	0.69	—	64.7
Hermes 4 - Llama-3.1 70B (Non-reasoning)	Nous Research	12.6	9.2	$0.13	$0.40	$0.20	70.0	0.60	—	63.6
Ling-flash-2.0	InclusionAI	15.7	16.7	$0.14	$0.57	$0.25	81.3	1.64	—	63.6
DeepSeek V3.1 Terminus (Non-reasoning)	DeepSeek	28.5	31.9	$0.27	$1.00	$0.45	0.0	0.00	—	62.9
Gemma 3 12B Instruct	Google	8.8	6.3	$0.09	$0.29	$0.14	0.0	0.00	—	62.9
GLM-4.5-Air	Z AI	23.2	23.8	$0.17	$0.98	$0.37	55.6	1.69	—	62.4
GPT-5 mini (high)	OpenAI	41.2	35.3	$0.25	$2.00	$0.69	94.0	76.28	—	59.9
Qwen3 32B (Reasoning)	Alibaba	16.5	13.8	$0.20	$0.52	$0.28	98.1	1.05	—	59.8
Gemini 3.1 Flash-Lite Preview	Google	33.5	30.1	$0.25	$1.50	$0.56	274.1	5.33	—	59.5
Qwen3 VL 30B A3B (Reasoning)	Alibaba	19.7	13.1	$0.20	$0.75	$0.34	126.0	1.11	—	58.3
Qwen3 8B (Non-reasoning)	Alibaba	10.6	7.1	$0.18	$0.20	$0.18	65.6	1.32	—	57.3
Qwen3 Coder 30B A3B Instruct	Alibaba	20.0	19.4	$0.19	$0.84	$0.35	99.3	1.55	—	56.8
Ring-flash-2.0	InclusionAI	14.0	10.6	$0.14	$0.57	$0.25	0.0	0.00	—	56.7
GPT-5 mini (medium)	OpenAI	38.9	32.8	$0.25	$2.00	$0.69	93.6	17.40	—	56.5
MiMo-V2-Omni-0327	Xiaomi	44.9	36.9	$0.40	$2.00	$0.80	93.7	1.53	—	56.1
GPT-5.1 Codex mini (high)	OpenAI	38.6	36.4	$0.25	$2.00	$0.69	209.7	2.31	—	56.1
Qwen3 32B (Non-reasoning)	Alibaba	14.5	—	$0.15	$0.59	$0.26	101.3	1.15	—	55.8
Qwen3.5 35B A3B (Reasoning)	Alibaba	37.1	30.3	$0.25	$2.00	$0.69	147.3	1.05	—	53.9
Qwen3 VL 30B A3B Instruct	Alibaba	16.0	14.3	$0.20	$0.60	$0.30	124.5	0.98	—	53.3
GPT-5.4 nano (Non-Reasoning)	OpenAI	24.4	27.9	$0.20	$1.25	$0.46	146.6	0.57	—	52.7
GLM-4.6V (Reasoning)	Z AI	23.4	19.7	$0.30	$0.90	$0.45	42.4	1.34	—	52.0
Qwen3.5 27B (Reasoning)	Alibaba	42.1	34.9	$0.30	$2.40	$0.82	83.3	1.55	—	51.0
Qwen3 Coder Next	Alibaba	28.3	22.9	$0.35	$1.20	$0.56	171.7	0.87	—	50.3
NVIDIA Nemotron Nano 12B v2 VL (Reasoning)	NVIDIA	14.9	11.7	$0.20	$0.60	$0.30	0.0	0.00	—	49.7
GPT-4o mini	OpenAI	12.6	—	$0.15	$0.60	$0.26	62.5	0.77	—	48.1
Phi-4	Microsoft	10.4	11.2	$0.13	$0.50	$0.22	22.6	0.56	—	47.5
Apertus 8B Instruct	Swiss AI Initiative	5.9	1.4	$0.10	$0.20	$0.13	0.0	0.00	—	47.2
Llama 4 Scout	Meta	13.5	6.7	$0.17	$0.66	$0.29	112.2	0.57	—	46.2
Qwen3 VL 8B Instruct	Alibaba	14.3	7.3	$0.18	$0.70	$0.31	146.2	1.08	—	46.1
Ring-2.6-1T	InclusionAI	38.5	33.3	$0.30	$2.50	$0.85	121.2	1.91	—	45.3
Qwen3.5 35B A3B (Non-reasoning)	Alibaba	30.7	16.8	$0.25	$2.00	$0.69	146.2	1.14	—	44.6
Qwen3.5 27B (Non-reasoning)	Alibaba	37.2	33.4	$0.28	$2.50	$0.83	89.0	1.38	—	44.6
Qwen3.6 Plus	Alibaba	50.0	42.9	$0.50	$3.00	$1.13	53.1	1.69	—	44.4
Qwen2.5 Instruct 72B	Alibaba	15.6	11.9	$0.36	$0.40	$0.37	54.9	1.22	—	42.2
GLM-4.7 (Reasoning)	Z AI	42.1	36.3	$0.60	$2.20	$1.00	90.9	0.81	—	42.1
DeepSeek V3.2 (Non-reasoning)	DeepSeek	32.1	34.6	$0.50	$1.60	$0.78	0.0	0.00	—	41.4
Gemini 3 Flash Preview (Reasoning)	Google	46.4	42.6	$0.50	$3.00	$1.13	195.4	5.01	—	41.2
Nova 2.0 Lite (high)	Amazon	34.5	23.4	$0.30	$2.50	$0.85	148.0	14.81	—	40.6
Ling-2.6-1T	InclusionAI	33.6	33.1	$0.30	$2.50	$0.85	0.0	0.00	—	39.5
Kimi K2.5 (Reasoning)	Kimi	46.8	39.6	$0.58	$3.00	$1.19	53.8	1.24	—	39.5
Llama 4 Maverick	Meta	18.4	15.6	$0.35	$0.85	$0.47	116.6	0.68	—	38.7
Kimi K2 Thinking	Kimi	40.9	34.8	$0.60	$2.50	$1.07	94.7	0.81	—	38.0
GLM-4.6V (Non-reasoning)	Z AI	17.1	11.1	$0.30	$0.90	$0.45	42.7	1.19	—	38.0
Qwen3.5 122B A10B (Reasoning)	Alibaba	41.6	34.7	$0.40	$3.20	$1.10	145.6	1.07	—	37.8
Qwen3.6 35B A3B (Non-reasoning)	Alibaba	31.5	17.6	$0.38	$2.25	$0.84	167.3	1.34	—	37.3
Qwen3 Coder 480B A35B Instruct	Alibaba	24.8	24.6	$0.30	$1.80	$0.68	65.6	1.61	—	36.7
Qwen3 Omni 30B A3B (Reasoning)	Alibaba	15.6	12.7	$0.25	$0.97	$0.43	86.3	1.02	—	36.3
Qwen3 1.7B (Non-reasoning)	Alibaba	6.8	2.3	$0.11	$0.42	$0.19	139.4	0.93	—	36.2
Mistral 7B Instruct	Mistral	7.4	—	$0.20	$0.23	$0.21	105.5	0.37	—	35.9
MiMo-V2.5-Pro	Xiaomi	53.8	45.5	$1.00	$3.00	$1.50	52.6	2.56	—	35.9
Qwen3 4B (Reasoning)	Alibaba	14.2	—	$0.11	$1.26	$0.40	102.9	1.03	—	35.7
Qwen3 8B (Reasoning)	Alibaba	13.2	9.0	$0.11	$1.15	$0.37	61.4	1.43	—	35.7
Llama 3.2 Instruct 11B (Vision)	Meta	8.7	4.2	$0.24	$0.24	$0.24	86.7	0.42	—	35.5
Hermes 3 - Llama-3.1 70B	Nous Research	10.6	—	$0.30	$0.30	$0.30	33.5	0.41	—	35.3
Qwen3 235B A22B 2507 (Reasoning)	Alibaba	29.5	23.2	$0.40	$2.15	$0.84	71.6	1.17	—	35.2
Nova 2.0 Lite (medium)	Amazon	29.7	23.9	$0.30	$2.50	$0.85	160.7	16.58	—	34.9
Reka Flash (Sep '24)	Reka AI	12.0	—	$0.20	$0.80	$0.35	85.5	1.74	—	34.3
GLM-4.7 (Non-reasoning)	Z AI	34.2	32.0	$0.60	$2.20	$1.00	103.8	0.86	—	34.2
Grok 4.3 (high)	xAI	53.2	41.0	$1.25	$2.50	$1.56	147.3	19.23	—	34.0
Mistral Small (Sep '24)	Mistral	10.2	—	$0.20	$0.60	$0.30	149.6	0.49	—	34.0
Qwen3.6 27B (Reasoning)	Alibaba	45.8	36.5	$0.60	$3.60	$1.35	61.2	1.36	—	33.9
GLM-4.6 (Reasoning)	Z AI	32.5	29.5	$0.55	$2.20	$0.96	46.3	0.81	—	33.7
DeepSeek V3.1 (Non-reasoning)	DeepSeek	28.1	28.4	$0.56	$1.67	$0.83	0.0	0.00	—	33.7
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)	NVIDIA	10.1	5.9	$0.20	$0.60	$0.30	222.9	0.72	—	33.7
Qwen3 14B (Non-reasoning)	Alibaba	12.8	12.4	$0.23	$0.82	$0.38	64.0	1.03	—	33.6
Qwen3.5 397B A17B (Reasoning)	Alibaba	45.0	41.3	$0.60	$3.60	$1.35	52.2	1.73	—	33.3
Qwen3 30B A3B 2507 (Reasoning)	Alibaba	22.4	14.6	$0.28	$1.85	$0.67	146.2	1.06	—	33.3
Nova 2.0 Omni (medium)	Amazon	28.0	15.1	$0.30	$2.50	$0.85	0.0	0.00	—	32.9
MiMo-V2-Pro	Xiaomi	49.2	41.4	$1.00	$3.00	$1.50	61.4	1.51	—	32.8
GPT-4.1 mini	OpenAI	22.9	18.5	$0.40	$1.60	$0.70	95.8	0.42	—	32.7
Qwen3.5 122B A10B (Non-reasoning)	Alibaba	35.9	31.6	$0.40	$3.20	$1.10	158.6	1.08	—	32.6
GLM-5 (Reasoning)	Z AI	49.8	44.2	$1.00	$3.20	$1.55	72.9	0.66	—	32.1
DeepSeek V3.1 (Reasoning)	DeepSeek	27.7	29.7	$0.59	$1.69	$0.86	0.0	0.00	—	32.0
Jamba 1.5 Mini	AI21 Labs	8.0	—	$0.20	$0.40	$0.25	0.0	0.00	—	32.0
Gemini 2.5 Flash (Reasoning)	Google	27.0	22.2	$0.30	$2.50	$0.85	218.2	11.34	—	31.8
Jamba 1.6 Mini	AI21 Labs	7.9	—	$0.20	$0.40	$0.25	183.2	0.67	—	31.6
DeepSeek V3 (Dec '24)	DeepSeek	16.5	16.4	$0.40	$0.89	$0.52	0.0	0.00	—	31.5
Kimi K2.6	Kimi	53.9	47.1	$0.95	$4.00	$1.71	67.5	1.11	—	31.5
Grok 4.3 (medium)	xAI	48.8	35.1	$1.25	$2.50	$1.56	143.1	14.47	—	31.2
Gemini 3 Flash Preview (Non-reasoning)	Google	35.0	37.8	$0.50	$3.00	$1.13	190.4	0.77	—	31.1
Kimi K2.5 (Non-reasoning)	Kimi	37.3	25.8	$0.60	$3.00	$1.20	42.7	1.16	—	31.1
ERNIE 4.5 300B A47B	Baidu	15.0	14.5	$0.28	$1.10	$0.48	23.3	1.44	—	30.9
Mistral Large 3	Mistral	22.8	22.7	$0.50	$1.50	$0.75	60.2	0.55	—	30.4
Qwen3 0.6B (Non-reasoning)	Alibaba	5.7	1.4	$0.11	$0.42	$0.19	222.9	1.06	—	30.3
GLM-4.6 (Non-reasoning)	Z AI	30.2	30.2	$0.60	$2.20	$1.00	58.2	1.74	—	30.2
GPT-5 mini (minimal)	OpenAI	20.7	21.9	$0.25	$2.00	$0.69	90.3	0.80	—	30.1
Qwen3 VL 235B A22B Instruct	Alibaba	20.8	16.5	$0.30	$1.90	$0.70	52.6	1.15	—	29.7
Qwen3.5 397B A17B (Non-reasoning)	Alibaba	40.1	37.4	$0.60	$3.60	$1.35	53.4	1.64	—	29.7
GPT-5.4 mini (xhigh)	OpenAI	48.9	51.5	$0.75	$4.50	$1.69	161.3	4.28	—	29.0
Nova 2.0 Lite (low)	Amazon	24.6	13.6	$0.30	$2.50	$0.85	163.6	5.46	—	28.9
Kimi K2 0905	Kimi	30.9	25.9	$0.60	$2.50	$1.07	21.6	3.42	—	28.7
Grok 4.3 (low)	xAI	43.9	31.6	$1.25	$2.50	$1.56	127.3	5.47	—	28.1
Qwen3.6 27B (Non-reasoning)	Alibaba	37.1	26.6	$0.60	$3.60	$1.35	61.1	1.52	—	27.5
Nova 2.0 Omni (low)	Amazon	23.2	13.9	$0.30	$2.50	$0.85	0.0	0.00	—	27.3
Reka Flash 3	Reka AI	9.5	8.9	$0.20	$0.80	$0.35	92.3	19.08	—	27.1
Mistral Medium 3.1	Mistral	21.3	18.3	$0.40	$2.00	$0.80	67.4	0.52	—	26.6
QwQ 32B	Alibaba	19.7	—	$0.66	$1.00	$0.74	30.5	0.46	—	26.4
GLM-4.5 (Reasoning)	Z AI	26.4	26.3	$0.60	$2.20	$1.00	50.6	1.05	—	26.4
GLM-5 (Non-reasoning)	Z AI	40.6	39.0	$1.00	$3.20	$1.55	65.2	1.04	—	26.2
Qwen3.5 Omni Plus	Alibaba	38.6	27.6	$0.40	$4.80	$1.50	55.5	1.23	—	25.7
MiniMax M1 80k	MiniMax	24.4	14.5	$0.55	$2.20	$0.96	0.0	0.00	—	25.3
Kimi K2	Kimi	26.3	22.1	$0.58	$2.40	$1.04	25.4	1.48	—	25.3
Qwen3 VL 8B (Reasoning)	Alibaba	16.7	9.8	$0.18	$2.10	$0.66	133.3	1.03	—	25.3
Kimi K2.6 (Non-reasoning)	Kimi	42.9	38.4	$0.95	$4.00	$1.71	26.0	1.57	—	25.1
Qwen3 Omni 30B A3B Instruct	Alibaba	10.7	7.2	$0.25	$0.97	$0.43	109.0	0.93	—	24.9
Claude 3 Haiku	Anthropic	12.3	6.7	$0.25	$1.25	$0.50	0.0	0.00	—	24.6
Magistral Small 1.2	Mistral	18.2	14.8	$0.50	$1.50	$0.75	109.0	0.38	—	24.3
Gemini 2.5 Flash (Non-reasoning)	Google	20.6	17.8	$0.30	$2.50	$0.85	204.4	0.49	—	24.2
GLM-5.1 (Reasoning)	Z AI	51.4	43.4	$1.40	$4.40	$2.15	64.8	0.79	—	23.9
MiMo-V2.5-Pro (Non-reasoning)	Xiaomi	35.6	36.8	$1.00	$3.00	$1.50	56.2	2.21	—	23.7
Llama 3.3 Instruct 70B	Meta	14.5	10.7	$0.58	$0.71	$0.62	93.7	0.63	—	23.5
Mistral Medium 3	Mistral	18.8	13.6	$0.40	$2.00	$0.80	45.2	0.52	—	23.5
Devstral Medium	Mistral	18.7	15.9	$0.40	$2.00	$0.80	69.4	0.51	—	23.4
Qwen3 Next 80B A3B Instruct	Alibaba	20.1	15.3	$0.50	$2.00	$0.88	144.8	1.19	—	23.0
GPT-5.4 mini (medium)	OpenAI	37.7	37.5	$0.75	$4.50	$1.69	166.9	6.94	—	22.3
Llama 3.1 Instruct 70B	Meta	12.5	10.9	$0.56	$0.56	$0.56	31.0	0.77	—	22.3
Qwen3 14B (Reasoning)	Alibaba	16.2	13.1	$0.23	$2.22	$0.73	61.0	1.02	—	22.2
Qwen3 235B A22B (Non-reasoning)	Alibaba	17.0	14.0	$0.45	$1.80	$0.79	59.5	1.24	—	21.6
Nova 2.0 Lite (Non-reasoning)	Amazon	18.0	12.5	$0.30	$2.50	$0.85	222.4	0.80	—	21.2
GLM-5.1 (Non-reasoning)	Z AI	43.8	35.8	$1.40	$4.40	$2.15	44.3	0.82	—	20.4
DeepSeek R1 Distill Llama 70B	DeepSeek	16.0	11.4	$0.70	$1.05	$0.79	46.4	0.32	—	20.3
Qwen3 1.7B (Reasoning)	Alibaba	8.0	1.4	$0.11	$1.26	$0.40	140.4	0.95	—	20.1
Grok 4.3 (Non-reasoning)	xAI	31.0	25.1	$1.25	$2.50	$1.56	130.8	0.45	—	19.8
Nova 2.0 Omni (Non-reasoning)	Amazon	16.6	13.8	$0.30	$2.50	$0.85	0.0	0.00	—	19.5
DeepSeek V3 0324	DeepSeek	22.3	22.0	$1.20	$1.25	$1.21	0.0	0.00	—	18.4
DeepSeek V3.1 Terminus (Reasoning)	DeepSeek	33.9	33.7	$1.64	$2.75	$1.91	0.0	0.00	—	17.7
Qwen3.6 Max Preview	Alibaba	51.8	44.9	$1.30	$7.80	$2.92	34.7	2.06	—	17.7
o4-mini (high)	OpenAI	33.1	25.6	$1.10	$4.40	$1.93	178.3	15.68	—	17.2
Claude 4.5 Haiku (Reasoning)	Anthropic	37.1	32.6	$1.25	$5.00	$2.19	102.0	9.91	—	17.0
GLM-4.5V (Reasoning)	Z AI	15.1	10.9	$0.60	$1.80	$0.90	35.2	1.10	—	16.8
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)	NVIDIA	15.0	13.1	$0.60	$1.80	$0.90	52.9	0.69	—	16.7
Qwen3 Max Thinking	Alibaba	39.8	30.5	$1.20	$6.00	$2.40	48.6	1.40	—	16.6
Grok 4.20 0309 v2 (Reasoning)	xAI	49.3	40.5	$2.00	$6.00	$3.00	152.8	16.35	—	16.4
Gemini 3.5 Flash (high)	Google	55.3	45.0	$1.50	$9.00	$3.38	220.6	14.31	—	16.4
Qwen3 0.6B (Reasoning)	Alibaba	6.5	0.9	$0.11	$1.26	$0.40	222.4	0.90	—	16.3
Grok 4.20 0309 (Reasoning)	xAI	48.5	42.2	$2.00	$6.00	$3.00	159.0	17.91	—	16.2
Qwen3.7 Max	Alibaba	56.6	50.1	$2.50	$7.50	$3.75	197.9	1.59	—	15.1
Mixtral 8x7B Instruct	Mistral	7.7	—	$0.45	$0.70	$0.51	0.0	0.00	—	15.0
Qwen3 Next 80B A3B (Reasoning)	Alibaba	26.7	19.5	$0.50	$6.00	$1.88	166.3	1.19	—	14.2
Claude 4.5 Haiku (Non-reasoning)	Anthropic	31.0	29.6	$1.25	$5.00	$2.19	98.0	0.63	—	14.2
GLM-4.5V (Non-reasoning)	Z AI	12.7	10.8	$0.60	$1.80	$0.90	42.9	34.34	—	14.1
Qwen3 VL 32B Instruct	Alibaba	17.2	15.6	$0.70	$2.80	$1.23	78.5	1.24	—	14.0
GPT-5.1 (high)	OpenAI	47.7	44.7	$1.25	$10.00	$3.44	154.3	17.46	—	13.9
GPT-5.4 mini (Non-Reasoning)	OpenAI	23.3	25.3	$0.75	$4.50	$1.69	158.3	0.53	—	13.8
Qwen3 Max Thinking (Preview)	Alibaba	32.5	24.5	$1.20	$6.00	$2.40	48.9	1.80	—	13.5
o3-mini	OpenAI	25.9	17.9	$1.10	$4.40	$1.93	182.7	6.68	—	13.5
DeepSeek R1 0528 (May '25)	DeepSeek	27.1	24.0	$1.35	$4.20	$2.06	0.0	0.00	—	13.1
o3-mini (high)	OpenAI	25.2	17.3	$1.10	$4.40	$1.93	167.8	19.34	—	13.1
Mistral Medium 3.5	Mistral	39.2	35.4	$1.50	$7.50	$3.00	146.6	0.65	—	13.1
GPT-5 (high)	OpenAI	44.6	36.0	$1.25	$10.00	$3.44	80.9	83.02	—	13.0
GPT-5 Codex (high)	OpenAI	44.6	38.9	$1.25	$10.00	$3.44	177.2	8.84	—	13.0
Gemini 3.5 Flash (minimal)	Google	43.3	47.1	$1.50	$9.00	$3.38	212.7	0.79	—	12.8
Gemini 3.1 Pro Preview	Google	57.2	55.5	$2.00	$12.00	$4.50	124.6	24.85	—	12.7
Qwen3 VL 235B A22B (Reasoning)	Alibaba	27.6	20.9	$0.84	$6.17	$2.17	39.5	1.99	—	12.7
GPT-5.1 Codex (high)	OpenAI	43.1	36.6	$1.25	$10.00	$3.44	175.5	3.14	—	12.5
Hermes 4 - Llama-3.1 405B (Reasoning)	Nous Research	18.6	16.0	$1.00	$3.00	$1.50	28.8	0.79	—	12.4
GPT-5 (medium)	OpenAI	42.0	38.9	$1.25	$10.00	$3.44	85.4	33.96	—	12.2
GPT-3.5 Turbo	OpenAI	9.0	10.7	$0.50	$1.50	$0.75	118.6	0.45	—	12.0
Hermes 4 - Llama-3.1 405B (Non-reasoning)	Nous Research	17.6	18.1	$1.00	$3.00	$1.50	32.0	0.76	—	11.7
GPT-5 (low)	OpenAI	39.2	30.7	$1.25	$10.00	$3.44	85.5	8.41	—	11.4
Llama 3.1 Nemotron Instruct 70B	NVIDIA	13.4	10.8	$1.20	$1.20	$1.20	299.0	0.26	—	11.2
GPT-5.3 Codex (xhigh)	OpenAI	53.6	53.1	$1.75	$14.00	$4.81	76.2	56.81	—	11.1
o3	OpenAI	38.4	38.4	$2.00	$8.00	$3.50	149.6	5.20	—	11.0
Qwen3 Max (Preview)	Alibaba	26.1	25.5	$1.20	$6.00	$2.40	52.8	1.98	—	10.9
Gemini 3 Pro Preview (high)	Google	48.4	46.5	$2.00	$12.00	$4.50	125.3	28.70	—	10.8
Claude 3.5 Haiku	Anthropic	18.7	10.7	$1.00	$4.00	$1.75	0.0	0.00	—	10.7
GPT-5.2 (xhigh)	OpenAI	51.3	48.7	$1.75	$14.00	$4.81	80.0	99.59	—	10.7
Nova 2.0 Pro Preview (medium)	Amazon	35.7	30.4	$1.25	$10.00	$3.44	124.9	16.55	—	10.4
Qwen3 Max	Alibaba	31.4	26.4	$1.66	$7.22	$3.05	32.7	1.94	—	10.3
GPT-5.2 Codex (xhigh)	OpenAI	49.0	43.0	$1.75	$14.00	$4.81	98.5	1.82	—	10.2
GPT-5.4 (xhigh)	OpenAI	56.8	57.2	$2.50	$15.00	$5.63	79.4	173.52	—	10.1
Gemini 2.5 Pro	Google	34.6	32.0	$1.25	$10.00	$3.44	133.2	20.78	—	10.1
Grok 4.20 0309 (Non-reasoning)	xAI	29.7	25.4	$2.00	$6.00	$3.00	139.1	0.53	—	9.9
Command-R (Mar '24)	Cohere	7.4	—	$0.50	$1.50	$0.75	0.0	0.00	—	9.9
Magistral Medium 1.2	Mistral	27.1	21.7	$2.00	$5.00	$2.75	40.0	0.51	—	9.9
GPT-5.2 (medium)	OpenAI	46.6	44.2	$1.75	$14.00	$4.81	0.0	0.00	—	9.7
Grok 4.20 0309 v2 (Non-reasoning)	xAI	29.0	22.0	$2.00	$6.00	$3.00	137.0	0.62	—	9.7
Nova Pro	Amazon	13.5	11.0	$0.80	$3.20	$1.40	0.0	0.00	—	9.6
Qwen3 VL 32B (Reasoning)	Alibaba	24.7	14.5	$0.70	$8.40	$2.63	96.8	1.32	—	9.4
Nova 2.0 Pro Preview (low)	Amazon	31.9	24.5	$1.25	$10.00	$3.44	134.4	5.27	—	9.3
Gemini 3 Pro Preview (low)	Google	41.3	39.4	$2.00	$12.00	$4.50	0.0	0.00	—	9.2
Llama 3.2 Instruct 90B (Vision)	Meta	11.9	—	$1.38	$1.38	$1.38	42.5	0.49	—	8.6
Gemini 2.5 Pro Preview (May' 25)	Google	29.5	—	$1.25	$10.00	$3.44	0.0	0.00	—	8.6
GPT-5.4 (low)	OpenAI	47.9	45.6	$2.50	$15.00	$5.63	64.0	1.55	—	8.5
GPT-5.1 (Non-reasoning)	OpenAI	27.4	27.3	$1.25	$10.00	$3.44	135.0	0.66	—	8.0
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)	Anthropic	51.7	50.9	$3.75	$15.00	$6.56	57.3	58.27	—	7.9
DeepSeek R1 (Jan '25)	DeepSeek	18.8	15.9	$1.68	$4.70	$2.43	0.0	0.00	—	7.7
Llama 3 Instruct 70B	Meta	8.9	6.8	$0.65	$2.75	$1.18	46.2	0.63	—	7.6
Qwen3 235B A22B (Reasoning)	Alibaba	19.8	17.4	$0.70	$8.40	$2.63	63.0	1.18	—	7.5
GPT-4.1	OpenAI	26.3	21.8	$2.00	$8.00	$3.50	139.7	0.74	—	7.5
GPT-5.2 (Non-reasoning)	OpenAI	33.6	34.7	$1.75	$14.00	$4.81	69.7	0.58	—	7.0
GPT-5 (minimal)	OpenAI	23.9	25.0	$1.25	$10.00	$3.44	81.1	0.75	—	7.0
Claude Sonnet 4.6 (Non-reasoning, High Effort)	Anthropic	44.4	46.4	$3.75	$15.00	$6.56	45.4	1.07	—	6.8
Nova 2.0 Pro Preview (Non-reasoning)	Amazon	23.1	20.5	$1.25	$10.00	$3.44	130.7	0.76	—	6.7
Claude 4.5 Sonnet (Reasoning)	Anthropic	43.0	38.6	$3.75	$15.00	$6.56	49.5	7.95	—	6.6
Claude Sonnet 4.6 (Non-reasoning, Low Effort)	Anthropic	42.6	43.0	$3.75	$15.00	$6.56	45.2	1.01	—	6.5
GPT-5 (ChatGPT)	OpenAI	21.8	21.2	$1.25	$10.00	$3.44	178.9	0.45	—	6.3
GPT-5.4 (Non-reasoning)	OpenAI	35.4	41.0	$2.50	$15.00	$5.63	66.6	0.73	—	6.3
Mistral Small (Feb '24)	Mistral	9.0	—	$1.00	$3.00	$1.50	150.2	0.52	—	6.0
Claude 4 Sonnet (Reasoning)	Anthropic	38.7	34.1	$3.75	$15.00	$6.56	45.1	7.78	—	5.9
Qwen2.5 Max	Alibaba	16.3	—	$1.60	$6.40	$2.80	48.5	1.12	—	5.8
Apertus 70B Instruct	Swiss AI Initiative	7.7	1.9	$0.82	$2.92	$1.34	0.0	0.00	—	5.7
Claude 4.5 Sonnet (Non-reasoning)	Anthropic	37.1	33.5	$3.75	$15.00	$6.56	46.4	1.43	—	5.7
GPT-5.5 (xhigh)	OpenAI	60.2	59.1	$5.00	$30.00	$11.25	66.6	40.67	—	5.4
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)	Anthropic	57.3	52.5	$6.25	$25.00	$10.94	46.7	13.93	—	5.2
GPT-5.5 (high)	OpenAI	58.9	58.5	$5.00	$30.00	$11.25	66.2	11.32	—	5.2
GPT-5.5 (medium)	OpenAI	56.7	56.2	$5.00	$30.00	$11.25	65.8	6.14	—	5.0
Mistral Large 2 (Nov '24)	Mistral	15.1	13.8	$2.00	$6.00	$3.00	31.9	0.60	—	5.0
Claude 4 Sonnet (Non-reasoning)	Anthropic	33.0	30.6	$3.75	$15.00	$6.56	46.4	1.12	—	5.0
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)	Anthropic	52.9	48.1	$6.25	$25.00	$10.94	44.5	7.14	—	4.8
Claude Opus 4.7 (Non-reasoning, High Effort)	Anthropic	51.8	53.1	$6.25	$25.00	$10.94	43.1	1.43	—	4.7
Llama 3.1 Instruct 405B	Meta	17.4	14.5	$2.75	$6.50	$3.69	59.3	0.64	—	4.7
Claude 3.7 Sonnet (Non-reasoning)	Anthropic	30.8	26.7	$3.75	$15.00	$6.56	0.0	0.00	—	4.7
Pixtral Large	Mistral	14.0	—	$2.00	$6.00	$3.00	54.8	0.51	—	4.7
Claude Opus 4.5 (Reasoning)	Anthropic	49.7	47.8	$6.25	$25.00	$10.94	50.0	10.45	—	4.5
GPT-5.5 (low)	OpenAI	50.8	52.1	$5.00	$30.00	$11.25	62.1	1.60	—	4.5
Mistral Large 2 (Jul '24)	Mistral	13.0	—	$2.00	$6.00	$3.00	0.0	0.00	—	4.3
GPT-4o (Aug '24)	OpenAI	18.6	16.6	$2.50	$10.00	$4.38	133.1	0.55	—	4.3
Claude Opus 4.6 (Non-reasoning, High Effort)	Anthropic	46.5	47.6	$6.25	$25.00	$10.94	45.9	1.43	—	4.3
GPT-4o (Nov '24)	OpenAI	17.3	16.7	$2.50	$10.00	$4.38	203.8	0.45	—	4.0
Claude Opus 4.5 (Non-reasoning)	Anthropic	43.1	42.9	$6.25	$25.00	$10.94	52.4	1.45	—	3.9
Nova Premier	Amazon	19.0	13.8	$2.50	$12.50	$5.00	69.9	1.07	—	3.8
Grok 4	xAI	41.5	40.5	$5.50	$27.50	$11.00	0.0	0.00	—	3.8
GPT-5.5 (Non-reasoning)	OpenAI	40.9	48.6	$5.00	$30.00	$11.25	61.1	0.88	—	3.6
Grok 3	xAI	25.2	19.8	$4.00	$20.00	$8.00	0.0	0.00	—	3.1
Jamba 1.7 Large	AI21 Labs	10.9	7.8	$2.00	$8.00	$3.50	60.6	0.87	—	3.1
Command A	Cohere	13.5	9.9	$2.50	$10.00	$4.38	61.1	0.40	—	3.1
Jamba 1.5 Large	AI21 Labs	10.7	—	$2.00	$8.00	$3.50	0.0	0.00	—	3.1
Jamba 1.6 Large	AI21 Labs	10.6	—	$2.00	$8.00	$3.50	60.3	0.92	—	3.0
Claude 3.5 Sonnet (Oct '24)	Anthropic	15.9	30.2	$3.75	$15.00	$6.56	0.0	0.00	—	2.4
Mistral Medium	Mistral	9.0	—	$2.75	$8.10	$4.09	55.7	0.76	—	2.2
Claude 3.5 Sonnet (June '24)	Anthropic	14.2	26.0	$3.75	$15.00	$6.56	0.0	0.00	—	2.2
GPT-4o (May '24)	OpenAI	14.5	24.2	$5.00	$15.00	$7.50	134.8	0.49	—	1.9
Claude 3 Sonnet	Anthropic	10.3	—	$3.00	$15.00	$6.00	0.0	0.00	—	1.7
Mistral Large (Feb '24)	Mistral	9.9	—	$4.00	$12.00	$6.00	0.0	0.00	—	1.7
Command-R+ (Apr '24)	Cohere	8.3	—	$3.00	$15.00	$6.00	0.0	0.00	—	1.4
Claude 4.1 Opus (Reasoning)	Anthropic	42.0	36.5	$18.75	$75.00	$32.81	34.9	8.13	—	1.3
Claude 4 Opus (Reasoning)	Anthropic	39.0	34.0	$18.75	$75.00	$32.81	33.6	7.33	—	1.2
o1	OpenAI	30.7	20.5	$15.00	$60.00	$26.25	101.8	19.19	—	1.2
o3-pro	OpenAI	40.7	—	$20.00	$80.00	$35.00	23.1	63.04	—	1.2
Claude 4.1 Opus (Non-reasoning)	Anthropic	36.0	—	$18.75	$75.00	$32.81	34.3	1.71	—	1.1
Claude 4 Opus (Non-reasoning)	Anthropic	33.0	—	$18.75	$75.00	$32.81	33.9	1.60	—	1.0
GPT-4 Turbo	OpenAI	13.7	21.5	$10.00	$30.00	$15.00	35.9	1.11	—	0.9
o1-preview	OpenAI	23.7	34.0	$16.50	$66.00	$28.88	0.0	0.00	—	0.8
Claude 3 Opus	Anthropic	18.0	19.5	$18.75	$75.00	$32.81	0.0	0.00	—	0.5
GPT-4	OpenAI	12.8	13.1	$30.00	$60.00	$37.50	41.6	0.96	—	0.3
o1-pro	OpenAI	25.8	—	$150.00	$600.00	$262.50	0.0	0.00	—	0.1
Grok-1	xAI	11.7	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Muse Spark	Meta	52.2	47.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemma 4 E4B (Non-reasoning)	Google	14.8	6.4	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemma 4 31B (Reasoning)	Google	39.2	38.7	$0.00	$0.00	$0.00	35.7	0.99	—	0.0
Gemma 4 E4B (Reasoning)	Google	18.8	13.7	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemma 4 E2B (Non-reasoning)	Google	12.1	8.3	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemma 3 270M	Google	7.7	0.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemma 4 E2B (Reasoning)	Google	15.2	9.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Devstral Small 2	Mistral	19.5	20.7	$0.00	$0.00	$0.00	56.9	0.51	—	0.0
Devstral 2	Mistral	22.0	23.7	$0.00	$0.00	$0.00	59.2	0.61	—	0.0
R1 1776	Perplexity	12.0	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Falcon-H1R-7B	TII UAE	15.8	9.8	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Phi-4 Multimodal Instruct	Microsoft	10.0	—	$0.00	$0.00	$0.00	17.0	0.37	—	0.0
Phi-4 Mini Instruct	Microsoft	8.4	3.6	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
LFM2.5-1.2B-Thinking	Liquid AI	8.1	1.4	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
LFM2.5-VL-1.6B	Liquid AI	6.2	1.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
LFM2.5-1.2B-Instruct	Liquid AI	8.0	0.8	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
LFM2 8B A1B	Liquid AI	7.0	2.3	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
LFM2 2.6B	Liquid AI	8.0	1.4	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Solar Pro 2 (Non-reasoning)	Upstage	13.6	11.3	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Solar Open 100B (Reasoning)	Upstage	21.7	10.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Solar Pro 3	Upstage	25.9	13.3	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Solar Pro 2 (Reasoning)	Upstage	14.9	12.1	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)	NVIDIA	14.4	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
NVIDIA Nemotron 3 Nano 4B	NVIDIA	14.7	10.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)	NVIDIA	14.3	7.6	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Nemotron Cascade 2 30B A3B	NVIDIA	28.4	25.8	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Llama 3.3 Nemotron Super 49B v1 (Reasoning)	NVIDIA	18.5	9.4	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Kimi Linear 48B A3B Instruct	Kimi	14.4	14.2	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Step3 VL 10B	StepFun	15.5	13.9	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Step 3.5 Flash 2603	StepFun	38.5	34.6	$0.00	$0.00	$0.00	149.5	0.78	—	0.0
Molmo2-8B	Allen Institute for AI	7.3	4.4	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Olmo 3 7B Think	Allen Institute for AI	9.4	7.6	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Molmo 7B-D	Allen Institute for AI	9.2	1.2	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Olmo 3.1 32B Instruct	Allen Institute for AI	12.2	5.6	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Olmo 3.1 32B Think	Allen Institute for AI	13.9	9.8	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Llama 65B	Meta	7.4	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Granite 4.0 1B	IBM	7.3	2.9	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Granite 4.0 Micro	IBM	7.7	5.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Granite 4.1 3B	IBM	8.5	5.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Granite 4.0 350M	IBM	6.1	0.3	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Granite 4.0 H 350M	IBM	5.4	0.6	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Granite 4.1 30B	IBM	14.7	10.1	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Granite 4.0 H 1B	IBM	8.0	2.7	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)	Nous Research	10.9	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)	Nous Research	7.6	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Exaone 4.0 1.2B (Non-reasoning)	LG AI Research	8.1	2.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
K-EXAONE (Reasoning)	LG AI Research	32.1	27.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
K-EXAONE (Non-reasoning)	LG AI Research	23.4	13.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
EXAONE 4.0 32B (Non-reasoning)	LG AI Research	11.7	9.4	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Exaone 4.0 1.2B (Reasoning)	LG AI Research	8.3	3.1	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
EXAONE 4.0 32B (Reasoning)	LG AI Research	16.7	14.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
EXAONE 4.5 33B	LG AI Research	30.2	23.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
MiMo-V2-Omni	Xiaomi	43.4	35.5	$0.00	$0.00	$0.00	96.3	1.36	—	0.0
ERNIE 5.0 Thinking Preview	Baidu	29.1	29.2	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Sarvam 30B (high)	Sarvam	12.3	7.9	$0.00	$0.00	$0.00	75.2	1.27	—	0.0
Sarvam 105B (high)	Sarvam	18.2	9.8	$0.00	$0.00	$0.00	116.4	1.23	—	0.0
Qwen Chat 14B	Alibaba	7.4	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
INTELLECT-3	Prime Intellect	22.2	19.1	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Motif-2-12.7B-Reasoning	Motif Technologies	19.1	11.9	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
K2-V2 (medium)	MBZUAI Institute of Foundation Models	18.7	14.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
K2 Think V2	MBZUAI Institute of Foundation Models	24.1	15.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
K2-V2 (high)	MBZUAI Institute of Foundation Models	20.6	16.1	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
K2-V2 (low)	MBZUAI Institute of Foundation Models	14.4	10.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Mi:dm K 2.5 Pro	Korea Telecom	23.1	12.6	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
HyperCLOVA X SEED Think (32B)	Naver	23.7	17.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
LongCat Flash Lite	LongCat	23.9	16.5	$0.00	$0.00	$0.00	103.2	4.28	—	0.0
Tri-21B-think Preview	Trillion Labs	20.0	7.4	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Tri-21B-Think	Trillion Labs	18.6	6.3	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Nanbeige4.1-3B	Nanbeige	16.1	8.9	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
MiniCPM-V 4.6 1.3B	OpenBMB	12.7	0.7	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
MiniCPM5-1B (Non-reasoning)	OpenBMB	17.9	0.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
JT-35B-Flash	China Mobile	36.1	28.9	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
JT-MINI	China Mobile	25.4	21.2	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
GLM-5-Turbo	Z AI	46.8	36.8	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
GLM 5V Turbo (Reasoning)	Z AI	42.9	36.2	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Command A+	Cohere	37.2	29.3	$0.00	$0.00	$0.00	198.2	0.18	—	0.0
Tiny Aya Global	Cohere	4.7	1.2	$0.00	$0.00	$0.00	124.2	0.30	—	0.0
Apriel-v1.6-15B-Thinker	ServiceNow	27.6	22.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Jamba Reasoning 3B	AI21 Labs	9.6	2.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Jamba 1.7 Mini	AI21 Labs	8.1	3.1	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Qwen3.5 9B (Non-reasoning)	Alibaba	27.3	21.3	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Ling-mini-2.0	InclusionAI	9.2	5.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Doubao Seed Code	ByteDance Seed	33.5	31.3	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
o1-mini	OpenAI	20.4	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
GPT-4o (March 2025, chatgpt-4o-latest)	OpenAI	18.6	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
GPT-4o (ChatGPT)	OpenAI	14.1	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
GPT-4.5 (Preview)	OpenAI	20.0	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Llama 2 Chat 70B	Meta	8.4	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Llama 2 Chat 13B	Meta	8.4	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 2.0 Pro Experimental (Feb '25)	Google	18.1	25.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 2.0 Flash (experimental)	Google	16.8	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 1.5 Pro (Sep '24)	Google	16.0	23.6	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 2.0 Flash-Lite (Preview)	Google	14.5	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 1.5 Flash (Sep '24)	Google	13.8	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 1.5 Flash-8B	Google	11.1	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 1.5 Pro (May '24)	Google	12.0	19.8	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 2.0 Flash Thinking Experimental (Jan '25)	Google	19.6	24.1	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 2.5 Pro Preview (Mar' 25)	Google	30.3	46.7	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 2.5 Flash Preview (Non-reasoning)	Google	17.8	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
PALM-2	Google	8.6	4.6	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)	Google	25.7	22.1	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 2.0 Flash Thinking Experimental (Dec '24)	Google	12.3	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 2.0 Flash-Lite (Feb '25)	Google	14.7	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 2.5 Flash Preview (Reasoning)	Google	24.3	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 1.0 Ultra	Google	10.1	17.6	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 1.0 Pro	Google	8.5	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemma 3n E4B Instruct Preview (May '25)	Google	10.1	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemma 3 1B Instruct	Google	5.6	0.2	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemma 3n E2B Instruct	Google	4.8	2.2	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)	Google	31.1	24.6	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Gemini 1.5 Flash (May '24)	Google	10.5	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Claude Instant	Anthropic	7.4	7.8	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Claude 2.1	Anthropic	9.3	14.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Claude 2.0	Anthropic	9.1	12.9	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Claude 3.7 Sonnet (Reasoning)	Anthropic	34.7	27.6	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Mixtral 8x22B Instruct	Mistral	9.8	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Mistral Saba	Mistral	12.1	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Magistral Medium 1	Mistral	18.8	16.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Magistral Small 1	Mistral	16.8	11.1	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Devstral Small (May '25)	Mistral	18.0	12.2	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepSeek R1 Distill Qwen 32B	DeepSeek	17.2	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepSeek R1 Distill Qwen 14B	DeepSeek	15.8	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepSeek-V2.5 (Dec '24)	DeepSeek	12.5	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepSeek-Coder-V2	DeepSeek	10.6	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepSeek R1 Distill Llama 8B	DeepSeek	12.1	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepSeek LLM 67B Chat (V1)	DeepSeek	8.4	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepSeek R1 Distill Qwen 1.5B	DeepSeek	9.1	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepSeek-V2.5	DeepSeek	12.3	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepSeek R1 0528 Qwen3 8B	DeepSeek	16.4	7.8	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepSeek V3.2 Speciale	DeepSeek	29.4	37.9	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepSeek-V2-Chat	DeepSeek	9.1	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DeepSeek Coder V2 Lite Instruct	DeepSeek	8.5	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Sonar Pro	Perplexity	15.2	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Sonar Reasoning	Perplexity	17.9	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Sonar	Perplexity	15.5	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Sonar Reasoning Pro	Perplexity	24.6	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Grok Beta	xAI	13.3	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Grok Code Fast 1	xAI	28.7	23.7	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Grok 4.1 Fast (Reasoning)	xAI	38.6	30.9	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Grok 4.1 Fast (Non-reasoning)	xAI	23.6	19.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Grok 3 Reasoning Beta	xAI	21.6	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Grok 2 (Dec '24)	xAI	13.9	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
OpenChat 3.5 (1210)	OpenChat	8.3	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Phi-3 Mini Instruct 3.8B	Microsoft	10.1	3.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
LFM 40B	Liquid AI	8.8	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
LFM2 1.2B	Liquid AI	6.3	0.8	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Solar Pro 2 (Preview) (Reasoning)	Upstage	18.8	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Solar Pro 2 (Preview) (Non-reasoning)	Upstage	16.0	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
DBRX Instruct	Databricks	8.3	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
MiniMax M1 40k	MiniMax	20.9	14.1	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Llama 3.1 Tulu3 405B	Allen Institute for AI	14.1	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
OLMo 2 32B	Allen Institute for AI	10.6	2.7	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Olmo 3 32B Think	Allen Institute for AI	12.1	10.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
OLMo 2 7B	Allen Institute for AI	9.3	1.2	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Sarvam M (Reasoning)	Sarvam	8.4	7.5	$0.00	$0.00	$0.00	138.6	1.17	—	0.0
Apriel-v1.5-15B-Thinker	ServiceNow	28.3	18.7	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Arctic Instruct	Snowflake	8.8	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Qwen2.5 Coder Instruct 32B	Alibaba	12.9	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Qwen2 Instruct 72B	Alibaba	11.7	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Qwen2.5 Instruct 32B	Alibaba	13.2	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Qwen3 VL 4B (Reasoning)	Alibaba	13.7	6.7	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Qwen2.5 Coder Instruct 7B	Alibaba	10.0	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Qwen3 VL 4B Instruct	Alibaba	9.6	4.6	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Qwen3 4B 2507 (Reasoning)	Alibaba	18.2	9.5	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Qwen1.5 Chat 110B	Alibaba	9.5	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
QwQ 32B-Preview	Alibaba	15.2	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Qwen Chat 72B	Alibaba	8.8	—	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Qwen3 4B 2507 Instruct	Alibaba	12.9	9.0	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Ring-1T	InclusionAI	22.8	16.8	$0.00	$0.00	$0.00	0.0	0.00	—	0.0
Ling-1T	InclusionAI	19.0	18.8	$0.00	$0.00	$0.00	0.0	0.00	—	0.0

Das teuerste Modell ist selten die beste Wahl

In der Branche hält sich hartnäckig die Annahme, dass ein höherer Preis höhere Qualität bedeutet. Die Daten erzählen eine andere Geschichte. Sortiere die Tabelle oben nach Wertung und du wirst sehen, dass viele der bestplatzierten Modelle nur einen Bruchteil der Flaggschiff-Angebote kosten und dabei in Intelligenz- und Coding-Benchmarks gleichziehen oder sie übertreffen.

Das macht im großen Maßstab einen Unterschied. Wenn deine Anwendung eine Million Anfragen pro Tag verarbeitet, ist der Unterschied zwischen einem $2/M-Modell und einem $0,20/M-Modell kein Rundungsfehler — es sind tausende Dollar pro Monat. Und das günstigere Modell ist möglicherweise sogar schneller, weil kleinere oder besser optimierte Modelle oft einen höheren Durchsatz erreichen.

Die Flaggschiff-Modelle der größten Anbieter führen bei den schwierigsten Benchmarks — Spitzenmathematik, Wissenschaft auf Promotionsniveau, komplexes mehrstufiges Reasoning. Aber die meisten Produktions-Workloads sind keine Promotions-Wissenschaft. Es geht um Klassifikation, Extraktion, Zusammenfassung, Code-Generierung und Konversation. Dafür ist ein Mittelklasse-Modell kein Kompromiss — es ist das richtige Werkzeug.

Reasoning-Modelle fügen eine weitere Dimension hinzu. Sie verwenden zusätzliche Rechenleistung zum „Denken“ vor der Antwort, was die Genauigkeit bei schwierigen Problemen steigert, aber auch Latenz und Kosten erhöht. Wenn dein Anwendungsfall kein mehrstufiges logisches Schließen erfordert, liefert ein Standardmodell die gleiche Antwort in einem Zehntel der Zeit.

Die Wertung in dieser Tabelle — Intelligenz geteilt durch Mischpreis — macht diesen Kompromiss auf einen Blick sichtbar. Das beste Modell für dein Projekt ist nicht das intelligenteste verfügbare. Es ist das intelligenteste, das du brauchst, zum niedrigsten Preis, der es liefert.

Wenn du auf europäischer Infrastruktur aufbaust und Anbieter finden willst, die Datensouveränität respektieren, schau dir Voie.fi an — ein offenes Verzeichnis von über 1.400 europäischen Anbietern digitaler Infrastruktur in den Bereichen Compute, Speicher, Zahlungen, Sicherheit, KI und mehr.