Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	MiMo-V2.6-ProOpenXiaomi	46.3	$0.54	57	3.1 s
2	New	DeepSeek V4.1 Flash 1017 (Max)OpenDeepSeek	45.1	$0.52	169	1.2 s
3	▼ 1	GLM-5.3 (Max)OpenZ AI	44.8	$2.2	98	2.4 s
4	▼ 1	Step 5 PreviewOpenStepFun	43.7	$1.4	229	1.2 s
5	—	GLM-5.3-FlashOpenZ AI	41.8	$0.24	70	2.8 s
6	—	Ling 3.1 FlashOpenInclusionAI	41.1	$0.45	213	1.8 s
7	—	Qwen3.8 2.4T A95BOpenAlibaba	39.9	$3.0	41	2.9 s
8	—	Qwen3.8-Flash-NextOpenAlibaba	39.8	$0.23	52	2.1 s
9	▲ 1	Muse Spark Open (Xhigh)OpenMeta	38.9	$2.0	151	0.8 s
10	▲ 1	MiMo-V2.6-FlashOpenXiaomi	37.9	$0.18	56	3.8 s
11	▲ 1	DeepSeek V4 Pro 0813 (Max)OpenDeepSeek	36.0	$2.0	105	1.8 s
12	▲ 1	GLM-5.3 (Low)OpenZ AI	34.3	$2.2	91	3.0 s
13	▲ 1	Qwen3.8 27B (Xhigh)OpenAlibaba	33.7	$1.1	45	3.9 s
14	▲ 1	Motif 3OpenMotif Technologies	33.6	—	—	—
15	▲ 1	K2 Horizon 375B A23BOpenInstitute of Foundation Models	30.5	$0.000	879	2.2 s
16	▲ 1	Beam 1.0OpenReflection	30.3	$0.60	363	0.7 s
17	▲ 2	MiniMax-M3OpenMiniMax	29.2	$0.52	103	1.3 s
18	▲ 2	Nex-N2-Pro (Based on Qwen3.5-397B-A17B)OpenNex AGI	28.2	—	—	—
19	▲ 2	Qwen3.8 27B (Medium)OpenAlibaba	27.6	$1.1	48	4.0 s
20	▲ 2	Nemotron 3.5 Super VLOpenNVIDIA	26.5	$0.31	446	0.7 s
21	▲ 2	Qwen3.8 27B (Low)OpenAlibaba	26.2	$1.1	49	3.9 s
22	▲ 2	Kimi K2.7 CodeOpenKimi	25.8	$1.7	64	2.8 s
23	▲ 2	Inkling SmallOpenThinking Machines	25.7	$0.52	223	1.6 s
24	▲ 2	K2 Horizon MoVA 36B A4BOpenInstitute of Foundation Models	25.3	—	—	—
25	▲ 2	Hy3OpenTencent	25.3	$0.24	81	2.8 s
26	▲ 2	Inkling (Xhigh)OpenThinking Machines	25.0	$1.8	195	1.8 s
27	▲ 2	Solar Open2 250BOpenUpstage	24.7	—	—	—
28	▲ 3	Ling-3.0-flash-VLOpenInclusionAI	24.6	—	—	—
29	▲ 3	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	22.9	$1.1	158	1.2 s
30	▲ 3	Ling-3.0-flash-FinOpenInclusionAI	22.6	—	—	—
31	▲ 3	G9v3-39A5BOpenAI9Stars	21.8	—	—	—
32	▲ 3	A.X-K2OpenSK Telecom	21.5	—	—	—
33	▲ 3	Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba	21.4	$1.4	60	2.1 s
34	▲ 3	Nemotron 3.5 Bolt 74B-A9BOpenNVIDIA	21.4	—	—	—
35	▲ 3	K2 Horizon 7BOpenInstitute of Foundation Models	20.6	—	—	—
36	▲ 3	DeepSeek V4 Pro 0813 (Non-reasoning)OpenDeepSeek	20.4	$2.0	100	1.8 s
37	▲ 3	Qwen3.8 27B (Non-reasoning)OpenAlibaba	20.2	$1.1	50	4.0 s
38	▲ 3	K-EXAONE 2.0 0803OpenLG AI Research	19.7	—	—	—
39	▲ 3	LongCat 2.0OpenLongCat	19.1	$1.3	76	2.6 s
40	▲ 3	Qwen3.5 397B A17B (Reasoning)OpenAlibaba	18.4	$1.4	59	2.2 s
41	▲ 3	Qwen3.6 35B A3B (Reasoning)OpenAlibaba	18.2	$0.84	131	2.0 s
42	▲ 3	Qwen3.5 122B A10B (Non-reasoning)OpenAlibaba	17.7	$1.1	143	2.3 s
43	▲ 3	Muse Glimmer (High)OpenMeta	17.5	$0.52	105	1.1 s
44	▲ 3	Gemma 4 26B A4B (Reasoning)OpenGoogle	16.7	$0.16	91	0.9 s
45	▲ 3	Ring-2.6-1TOpenInclusionAI	16.6	$0.85	124	3.7 s
46	▲ 3	K2 Horizon 3.7BOpenInstitute of Foundation Models	15.6	—	—	—
47	▲ 3	Qwen3.5 122B A10B (Reasoning)OpenAlibaba	15.6	$1.1	128	2.3 s
48	▲ 3	Qwen3.6 35B A3B (Non-reasoning)OpenAlibaba	15.2	$0.84	147	2.0 s
49	▲ 3	Gemma 4 31B (Reasoning)OpenGoogle	14.7	$0.000	35	1.1 s
50	▲ 3	Mistral Medium 3.5OpenMistral	14.2	$3.0	162	2.3 s
51	▲ 3	Gemma 4 12B (Reasoning)OpenGoogle	14.2	$0.15	114	2.2 s
52	▲ 3	Gemma 4 31B (Non-reasoning)OpenGoogle	13.9	$0.22	55	1.8 s
53	▲ 3	Apriel-v1.6-15B-ThinkerOpenServiceNow	13.4	—	—	—
54	▲ 3	Qwen3.5 9B (Non-reasoning)OpenAlibaba	13.3	$0.19	80	0.9 s
55	▲ 3	EXAONE 4.5 33B (Reasoning)OpenLG AI Research	13.2	—	—	—
56	▲ 3	Command A+OpenCohere	13.1	$0.000	166	0.5 s
57	▲ 3	Gemma 4 26B A4B (Non-reasoning)OpenGoogle	13.1	$0.19	108	0.9 s
58	▲ 3	Qwen3.5 4B (Reasoning)OpenAlibaba	13.1	$0.060	19	0.9 s
59	▲ 3	Nemotron 3.5 LightningOpenNVIDIA	12.9	$0.095	295	0.6 s
60	▲ 3	Granite 4.2 30BOpenIBM	12.7	$0.28	47	0.8 s
61	▲ 3	MiniCPM5-2BOpenOpenBMB	12.5	—	—	—
62	▲ 3	HyperNova 60B 2605 (High, Based on gpt-oss-120b)OpenMultiverse Computing	11.7	—	—	—
63	▲ 3	Nemotron Cascade 2 30B A3BOpenNVIDIA	11.7	—	—	—
64	▲ 3	gpt-oss-120b (High)OpenOpenAI	11.6	$0.26	233	0.8 s
65	▲ 3	K2 Think V2OpenInstitute of Foundation Models	11.5	—	—	—
66	▲ 3	LongCat Flash LiteOpenLongCat	11.5	—	—	—
67	▲ 3	HyperCLOVA X SEED Think (32B)OpenNaver	11.4	—	—	—
68	▲ 3	Mistral Small 4 (Reasoning)OpenMistral	11.3	$0.26	178	0.9 s
69	▲ 3	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	11.2	—	—	—
70	▲ 3	Qwen3.5 9B (Reasoning)OpenAlibaba	11.2	$0.15	61	1.9 s
71	▲ 3	Granite 4.2 8BOpenIBM	11.1	$0.11	54	0.8 s
72	▲ 3	Ling 3.0 TinyOpenInclusionAI	11.1	$0.000	58	2.6 s
73	▲ 3	G9v3-3BOpenAI9Stars	10.8	—	—	—
74	▲ 3	Trinity Large ThinkingOpenArcee AI	10.8	$0.39	353	1.3 s
75	▲ 3	Qwen3.5 4B (Non-reasoning)OpenAlibaba	10.8	$0.060	14	0.9 s
76	▲ 3	INTELLECT-3 (Based on GLM-4.5-Air)OpenPrime Intellect	10.6	—	—	—
77	▲ 3	Solar Open 100B (Reasoning)OpenUpstage	10.4	—	—	—
78	▲ 3	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	10.3	$0.64	231	0.8 s
79	▲ 3	gpt-oss-120b (Low)OpenOpenAI	10.2	$0.24	265	0.8 s
80	▲ 3	gpt-oss-20b (Low)OpenOpenAI	10.0	$0.13	186	1.0 s
81	▲ 3	North Mini CodeOpenCohere	9.9	$0.000	66	0.5 s
82	▲ 3	K2-V2 (High)OpenInstitute of Foundation Models	9.9	—	—	—
83	▲ 3	Qwen3 Next 80B A3B InstructOpenAlibaba	9.6	$0.35	133	0.8 s
84	▲ 3	DiffusionGemma 26B A4BOpenGoogle	9.5	—	—	—
85	▲ 3	Gemma 4 12B (Non-reasoning)OpenGoogle	9.4	$0.15	118	2.3 s
86	▲ 3	Llama 4 MaverickOpenMeta	9.3	$0.42	52	1.0 s
87	▲ 3	Qwen3 Coder NextOpenAlibaba	9.2	$0.48	94	0.9 s
88	▲ 3	Granite 4.2 3BOpenIBM	9.1	$0.053	51	0.7 s
89	▲ 3	K2-V2 (Medium)OpenInstitute of Foundation Models	9.0	—	—	—
90	▲ 3	Mistral Small 4 (Non-reasoning)OpenMistral	9.0	$0.26	173	0.9 s
91	▲ 3	Tri-21B-ThinkOpenTrillion Labs	9.0	—	—	—
92	▲ 3	gpt-oss-20b (High)OpenOpenAI	9.0	$0.093	173	0.8 s
93	▲ 3	Gemma 4 E4B (Reasoning)OpenGoogle	8.9	$0.040	45	0.9 s
94	▲ 3	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA	8.9	$0.088	241	0.9 s
95	▲ 3	MiniCPM5-1B (Reasoning)OpenOpenBMB	8.8	—	—	—
96	▲ 3	Sarvam 105B (High)OpenSarvam	8.8	$0.074	189	1.6 s
97	▲ 3	MiniCPM5-1B (Non-reasoning)OpenOpenBMB	8.7	—	—	—
98	▲ 3	Magistral Small 1.2OpenMistral	8.6	$0.75	77	1.5 s
99	▲ 3	Nanbeige4.1-3BOpenNanbeige	8.4	—	—	—
100	▲ 3	LFM2.5-2.6BOpenLiquid AI	8.4	—	—	—
101	▲ 3	EXAONE 4.0 32B (Reasoning)OpenLG AI Research	8.2	—	—	—
102	▲ 3	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research	7.9	—	—	—
103	▲ 3	Falcon-H1R-7BOpenTII UAE	7.8	—	—	—
104	▲ 3	Gemma 4 E2B (Reasoning)OpenGoogle	7.8	—	—	—
105	▲ 3	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	7.8	$0.43	103	1.9 s
106	▲ 3	Step3 VL 10BOpenStepFun	7.7	—	—	—
107	▲ 3	Llama 3.3 Instruct 70BOpenMeta	7.7	$0.67	89	1.8 s
108	▲ 3	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	7.5	—	—	—
109	▲ 3	ERNIE 4.5 300B A47BOpenBaidu	7.5	—	—	—
110	▲ 3	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research	7.5	$1.5	43	2.3 s
111	▲ 3	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA	7.5	—	—	—
112	▲ 3	Gemma 4 E4B (Non-reasoning)OpenGoogle	7.5	$0.040	45	0.8 s
113	▲ 3	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA	7.4	$0.070	122	0.6 s
114	▲ 3	Hermes 4 - Llama-3.1 405B (Non-reasoning)OpenNous Research	7.4	$1.5	43	2.3 s
115	▲ 3	K2-V2 (Low)OpenInstitute of Foundation Models	7.3	—	—	—
116	▲ 3	Kimi Linear 48B A3B InstructOpenKimi	7.3	—	—	—
117	▲ 3	Llama 3.1 Instruct 405BOpenMeta	7.3	—	—	—
118	▲ 3	LFM2.5-8B-A1BOpenLiquid AI	7.2	—	—	—
119	▲ 3	Ring-flash-2.0OpenInclusionAI	7.2	—	—	—
120	▲ 3	Olmo 3.1 32B ThinkOpenAllen Institute for AI	7.1	—	—	—
121	▲ 3	Command AOpenCohere	7.0	$4.4	33	1.8 s
122	▲ 3	Qwen3.5 2B (Reasoning)OpenAlibaba	6.9	—	—	—
123	▲ 3	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)OpenNVIDIA	6.8	$0.088	277	0.8 s
124	▲ 3	NVIDIA Nemotron Nano 9B V2 (Non-reasoning)OpenNVIDIA	6.8	$0.086	168	1.0 s
125	▲ 3	Hermes 4 - Llama-3.1 70B (Non-reasoning)OpenNous Research	6.7	—	—	—
126	▲ 3	Sarvam 30B (High)OpenSarvam	6.6	—	—	—
127	▲ 3	Olmo 3.1 32B InstructOpenAllen Institute for AI	6.5	—	—	—
128	▲ 3	Gemma 4 E2B (Non-reasoning)OpenGoogle	6.5	—	—	—
129	▲ 3	Llama 4 ScoutOpenMeta	6.5	$0.30	118	0.8 s
130	▲ 3	R1 1776OpenPerplexity	6.4	—	—	—
131	▲ 3	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.4	—	—	—
132	▲ 3	Phi-4 Mini InstructOpenMicrosoft	6.3	$0.13	46	0.8 s
133	▲ 3	EXAONE 4.0 32B (Non-reasoning)OpenLG AI Research	6.3	—	—	—
134	▲ 3	Qwen3.5 2B (Non-reasoning)OpenAlibaba	6.2	—	—	—
135	▲ 3	Qwen3.5 0.8B (Reasoning)OpenAlibaba	6.1	—	—	—
136	▲ 3	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	6.1	—	—	—
137	▲ 3	Jamba 1.7 LargeOpenAI21 Labs	6.1	—	—	—
138	▲ 3	Granite 4.0 H SmallOpenIBM	6.0	—	—	—
139	▲ 3	Ministral 3 14BOpenMistral	6.0	$0.20	77	1.0 s
140	▲ 3	Qwen3 Omni 30B A3B InstructOpenAlibaba	6.0	$0.43	96	1.8 s
141	▲ 3	LFM2 24B A2BOpenLiquid AI	5.9	—	—	—
142	▲ 3	Phi-4OpenMicrosoft	5.9	$0.22	39	2.5 s
143	▲ 3	NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)OpenNVIDIA	5.8	$0.30	202	1.0 s
144	▲ 3	Phi-4 Multimodal InstructOpenMicrosoft	5.8	$0.14	—	—
145	▲ 3	MiniCPM-V 4.6 1.3BOpenOpenBMB	5.7	—	—	—
146	▲ 3	Jamba Reasoning 3BOpenAI21 Labs	5.7	—	—	—
147	▲ 3	Reka Flash 3OpenReka AI	5.6	$0.35	88	1.4 s
148	▲ 3	Olmo 3 7B ThinkOpenAllen Institute for AI	5.6	—	—	—
149	▲ 3	Molmo 7B-DOpenAllen Institute for AI	5.6	—	—	—
150	▲ 3	Ministral 3 8BOpenMistral	5.5	$0.15	119	0.9 s
151	▲ 3	Llama 3.2 Instruct 11B (Vision)OpenMeta	5.4	$0.35	26	1.3 s
152	▲ 3	Qwen3.5 0.8B (Non-reasoning)OpenAlibaba	5.4	—	—	—
153	▲ 3	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research	5.3	—	—	—
154	▲ 3	Olmo 3 7B InstructOpenAllen Institute for AI	5.2	—	—	—
155	▲ 3	Exaone 4.0 1.2B (Non-reasoning)OpenLG AI Research	5.2	—	—	—
156	▲ 3	LFM2.5-1.2B-ThinkingOpenLiquid AI	5.2	—	—	—
157	▲ 3	Jamba 1.7 MiniOpenAI21 Labs	5.2	—	—	—
158	▲ 3	LFM2.5-1.2B-InstructOpenLiquid AI	5.2	—	—	—
159	▲ 3	Granite 4.0 H 1BOpenIBM	5.2	—	—	—
160	▲ 3	Gemma 3 270MOpenGoogle	5.1	—	—	—
161	▲ 3	Apertus 70B InstructOpenSwiss AI Initiative	5.1	—	—	—
162	▲ 3	Granite 4.0 MicroOpenIBM	5.1	—	—	—
163	▲ 3	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	5.1	—	—	—
164	▲ 3	Molmo2-8BOpenAllen Institute for AI	5.0	—	—	—
165	▲ 3	Ministral 3 3BOpenMistral	4.8	$0.10	209	0.7 s
166	▲ 3	Apertus 8B InstructOpenSwiss AI Initiative	4.8	$0.13	136	3.5 s
166	▲ 3	Granite 4.0 350MOpenIBM	4.8	—	—	—
166	▲ 3	Granite 4.0 H 350MOpenIBM	4.8	—	—	—
166	▲ 3	LFM2.5-VL-1.6BOpenLiquid AI	4.8	—	—	—
166	▲ 3	Tiny Aya GlobalOpenCohere	4.8	$0.000	—	—
171	▲ 3	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	4.8	—	—	—
172	▲ 3	K2 Horizon 0.9BOpenInstitute of Foundation Models	3.0	—	—	—

122 more models

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026

64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi