Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Kimi K2.6OpenKimi · 1 more variant	53.9	$1.7	48	2.9 s
2	—	MiMo-V2.5-ProOpenXiaomi · 1 more variant	53.8	$1.5	56	2.9 s
3	—	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	51.5	$2.2	33	2.0 s
4	—	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	51.4	$2.2	45	1.6 s
5	—	GLM-5 (Reasoning)OpenZ AI · 1 more variant	49.8	$1.6	91	1.5 s
6	—	MiniMax-M2.7OpenMiniMax	49.6	$0.52	52	2.0 s
7	—	MiMo-V2.5OpenXiaomi	49.0	$0.72	91	3.2 s
8	—	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	46.8	$1.1	54	3.1 s
9	—	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	46.5	$0.18	110	1.2 s
10	—	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	45.8	$1.4	66	3.8 s
11	—	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	45.0	$1.4	52	2.5 s
12	—	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	43.5	$0.56	203	2.5 s
13	—	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	42.1	$1.0	106	1.3 s
14	—	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	42.1	$0.83	87	5.8 s
15	—	MiniMax-M2.5OpenMiniMax	41.9	$0.52	97	1.8 s
16	—	Hy3-preview (Reasoning)OpenTencent · 1 more variant	41.9	$0.20	116	4.0 s
17	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	41.7	$0.34	—	—
18	—	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	41.6	$1.1	160	2.5 s
19	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	41.5	$0.15	153	2.7 s
20	—	Kimi K2 ThinkingOpenKimi	40.9	$1.1	110	2.4 s
21	—	MiniMax-M2.1OpenMiniMax	39.4	$0.52	96	1.6 s
22	—	Mistral Medium 3.5OpenMistral	39.2	$3.0	149	1.7 s
23	—	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	39.2	$0.000	35	1.6 s
24	—	Step 3.5 FlashOpenStepFun	37.8	$0.15	164	1.1 s
25	—	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	37.1	$0.69	176	2.2 s
26	—	MiniMax-M2OpenMiniMax	36.1	$0.52	91	1.7 s
27	—	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	212	1.2 s
28	—	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	33.9	$1.9	—	—
29	—	Ling-2.6-1TOpenInclusionAI	33.6	$0.85	—	—
30	—	gpt-oss-120B (high)OpenOpenAI · 1 more variant	33.3	$0.26	260	1.0 s
31	—	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	32.9	$0.31	—	—
32	—	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	32.5	$0.96	45	1.3 s
33	—	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	32.4	$0.11	64	0.8 s
34	—	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	32.1	—	—	—
35	—	Trinity Large ThinkingOpenArcee AI	31.9	$0.40	109	1.0 s
36	—	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	31.2	$0.20	—	—
37	—	Kimi K2 0905OpenKimi · 1 more variant	30.9	$1.1	16	3.1 s
38	—	EXAONE 4.5 33BOpenLG AI Research	30.2	—	—	—
39	—	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	30.1	$0.15	83	1.2 s
40	—	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	29.5	$0.84	52	2.8 s
41	—	DeepSeek V3.2 SpecialeOpenDeepSeek	29.4	—	—	—
42	—	Nemotron Cascade 2 30B A3BOpenNVIDIA	28.4	—	—	—
43	—	Qwen3 Coder NextOpenAlibaba	28.3	$0.56	145	1.4 s
44	—	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	28.1	$0.83	—	—
45	—	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	27.8	$0.26	153	0.7 s
46	—	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.6	$2.2	33	3.1 s
47	—	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	27.1	$0.060	197	0.5 s
48	—	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	27.1	$2.1	—	—
49	—	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.7	$1.9	167	2.2 s
50	—	GLM-4.5 (Reasoning)OpenZ AI	26.4	$1.0	48	3.2 s
51	—	Ling 2.6 FlashOpenInclusionAI	26.2	$0.15	—	—
52	—	Seed-OSS-36B-InstructOpenByteDance Seed	25.2	$0.30	34	3.5 s
53	—	Qwen3 235B A22B 2507 InstructOpenAlibaba	25.0	$0.36	58	2.3 s
54	—	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.8	$0.68	62	3.0 s
55	—	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.7	$2.6	85	2.8 s
56	—	gpt-oss-20B (high)OpenOpenAI · 1 more variant	24.5	$0.088	241	0.8 s
57	—	MiniMax M1 80kOpenMiniMax	24.4	$0.96	—	—
58	—	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	24.3	$0.096	109	2.5 s
59	—	LongCat Flash LiteOpenLongCat	23.9	$0.000	113	7.0 s
60	—	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	23.4	$0.45	35	3.5 s
61	—	GLM-4.5-AirOpenZ AI	23.2	$0.37	62	3.2 s
62	—	Mistral Large 3OpenMistral	22.8	$0.75	50	1.1 s
63	—	Ring-1TOpenInclusionAI	22.8	—	—	—
64	—	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	22.4	$0.67	139	2.5 s
65	—	DeepSeek V3 0324OpenDeepSeek · 1 more variant	22.3	$1.2	—	—
66	—	INTELLECT-3OpenPrime Intellect	22.2	—	—	—
67	—	Devstral 2OpenMistral	22.0	$0.000	56	1.1 s
68	—	Solar Open 100B (Reasoning)OpenUpstage	21.7	—	—	—
69	—	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	21.4	$0.13	300	1.0 s
70	—	MiniMax M1 40kOpenMiniMax	20.9	—	—	—
71	—	Qwen3 VL 235B A22B InstructOpenAlibaba	20.8	$0.70	48	2.9 s
72	—	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	163	2.2 s
73	—	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.35	95	2.7 s
74	—	QwQ 32BOpenAlibaba	19.7	$0.75	28	2.1 s
75	—	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.7	$0.34	106	2.3 s
76	—	Devstral Small 2OpenMistral	19.5	$0.000	52	1.2 s
77	—	Ling-1TOpenInclusionAI	19.0	—	—	—
78	—	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	18.8	—	—	—
79	—	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	18.7	$0.18	50	1.3 s
80	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	18.5	—	—	—
81	—	Llama 4 MaverickOpenMeta	18.4	$0.48	109	1.1 s
82	—	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	18.2	—	—	—
83	—	Magistral Small 1.2OpenMistral	18.2	$0.75	104	0.8 s
84	▼ 1	Sarvam 105B (high)OpenSarvam	18.2	$0.000	116	2.3 s
85	—	Devstral Small (May '25)OpenMistral · 1 more variant	18.0	—	—	—
86	—	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	38	2.4 s
87	—	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	56	3.0 s
88	—	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	—	—	—
89	—	Magistral Small 1OpenMistral	16.8	—	—	—
90	—	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	16.7	—	—	—
91	—	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.7	$0.66	110	2.5 s
92	—	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	16.5	$0.28	96	2.5 s
93	—	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	—	—	—
94	—	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	16.3	$0.040	—	—
95	—	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	16.2	$0.73	59	2.8 s
96	—	Nanbeige4.1-3BOpenNanbeige	16.1	—	—	—
97	—	Qwen3 VL 30B A3B InstructOpenAlibaba	16.0	$0.30	106	2.2 s
98	—	Ministral 3 14BOpenMistral	16.0	$0.20	93	0.7 s
99	—	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	42	1.7 s
100	—	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	—	—	—
101	—	Falcon-H1R-7BOpenTII UAE	15.8	—	—	—
102	—	Ling-flash-2.0OpenInclusionAI	15.7	$0.25	80	2.5 s
103	—	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	79	2.0 s
104	—	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.37	27	3.7 s
105	—	Step3 VL 10BOpenStepFun	15.5	—	—	—
106	—	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	15.2	—	—	—
107	—	QwQ 32B-PreviewOpenAlibaba	15.2	—	—	—
108	—	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	15.1	$0.90	46	1.9 s
109	▼ 1	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	15.1	$3.0	31	1.8 s
110	—	Mistral Small 3.2OpenMistral	15.1	$0.13	116	0.7 s
111	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	41	2.6 s
112	—	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.21	105	2.1 s
113	—	ERNIE 4.5 300B A47BOpenBaidu	15.0	$0.49	23	3.6 s
114	—	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	14.9	$0.30	—	—
115	—	Ministral 3 8BOpenMistral	14.8	$0.15	93	0.7 s
116	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	14.8	$0.070	122	0.6 s
117	—	Granite 4.1 30BOpenIBM	14.7	—	—	—
118	—	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
119	—	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.62	75	1.7 s
120	—	Mistral Small 3.1OpenMistral	14.5	$0.14	142	0.7 s
121	—	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
122	—	Kimi Linear 48B A3B InstructOpenKimi	14.4	—	—	—
123	—	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	116	2.3 s
124	—	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	86	2.6 s
125	—	Pixtral LargeOpenMistral	14.0	$3.0	52	1.7 s
126	—	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
127	—	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	—	—	—
128	—	Llama 4 ScoutOpenMeta	13.5	$0.29	132	0.9 s
129	—	Command AOpenCohere	13.5	$4.4	38	2.1 s
130	—	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	284	0.5 s
131	—	Qwen2.5 Instruct 32BOpenAlibaba	13.2	—	—	—
132	—	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	13.2	$0.37	82	2.3 s
133	—	Qwen3 4B 2507 InstructOpenAlibaba	12.9	—	—	—
134	—	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	—	—	—
135	—	Mistral Small 3OpenMistral	12.7	$0.10	137	0.7 s
136	New	MiniCPM-V 4.6 1.3BOpenOpenBMB	12.7	—	—	—
137	▼ 1	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	12.5	—	—	—
138	▼ 1	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	32	1.9 s
139	▼ 1	Granite 4.1 8BOpenIBM	12.4	$0.063	120	0.8 s
140	▼ 1	Sarvam 30B (high)OpenSarvam	12.3	$0.000	262	1.9 s
141	▼ 1	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	—	—	—
142	▼ 1	R1 1776OpenPerplexity	12.0	—	—	—
143	▼ 1	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$1.4	57	1.2 s
143	▼ 1	Solar MiniOpenUpstage	11.9	$0.15	—	—
145	▼ 1	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	146	0.9 s
146	▼ 1	Grok-1OpenxAI	11.7	—	—	—
147	▼ 1	Qwen2 Instruct 72BOpenAlibaba	11.7	—	—	—
148	▼ 1	Ministral 3 3BOpenMistral	11.2	$0.10	247	0.5 s
149	▼ 1	Jamba 1.7 LargeOpenAI21 Labs	10.9	$3.5	60	1.6 s
150	▼ 1	Granite 4.0 H SmallOpenIBM	10.8	$0.11	232	10 s
151	▼ 1	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
152	▼ 1	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	94	2.0 s
153	▼ 1	DeepSeek-Coder-V2OpenDeepSeek	10.6	—	—	—
154	▼ 1	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	59	1.6 s
155	▼ 1	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	10.5	$0.020	—	—
156	▼ 1	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	225	0.5 s
157	▼ 1	Phi-4OpenMicrosoft	10.4	$0.22	32	2.1 s
158	▼ 1	Gemma 3 27B InstructOpenGoogle	10.3	$0.14	—	—
159	▼ 1	Mistral Small (Sep '24)OpenMistral	10.2	$0.30	138	0.8 s
160	▼ 1	Phi-3 Mini Instruct 3.8BOpenMicrosoft	10.1	—	—	—
161	▼ 1	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
162	▼ 1	Phi-4 Multimodal InstructOpenMicrosoft	10.0	$0.000	13	3.8 s
163	▼ 1	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	—	—	—
164	▼ 1	Mixtral 8x22B InstructOpenMistral	9.8	—	—	—
165	▼ 1	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
166	▼ 1	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.15	50	1.2 s
167	▼ 1	Jamba Reasoning 3BOpenAI21 Labs	9.6	—	—	—
168	▼ 1	Qwen3 VL 4B InstructOpenAlibaba	9.6	—	—	—
169	▼ 1	Qwen1.5 Chat 110BOpenAlibaba	9.5	—	—	—
170	▼ 1	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
171	▼ 1	Ling-mini-2.0OpenInclusionAI	9.2	—	—	—
172	▼ 1	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	—	—	—
173	▼ 1	DeepSeek-V2-ChatOpenDeepSeek	9.1	—	—	—
174	▼ 1	Llama 3 Instruct 70BOpenMeta	8.9	$1.2	—	—
175	▼ 1	Arctic InstructOpenSnowflake	8.8	—	—	—
175	▼ 1	Qwen Chat 72BOpenAlibaba	8.8	—	—	—
177	▼ 1	Gemma 3 12B InstructOpenGoogle	8.8	$0.14	—	—
178	▼ 1	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.25	45	0.7 s
179	▼ 1	Granite 4.1 3BOpenIBM	8.5	—	—	—
180	▼ 1	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	—	—	—
181	▼ 1	Sarvam M (Reasoning)OpenSarvam	8.4	$0.000	—	—
182	▼ 2	Phi-4 Mini InstructOpenMicrosoft	8.4	$0.000	41	0.8 s
183	▼ 1	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	—	—	—
183	▼ 1	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
185	▼ 1	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
186	▼ 1	Command-R+ (Apr '24)OpenCohere · 1 more variant	8.3	$6.0	—	—
187	▼ 1	OpenChat 3.5 (1210)OpenOpenChat	8.3	—	—	—
188	▼ 1	DBRX InstructOpenDatabricks	8.3	—	—	—
189	▼ 1	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	8.3	—	—	—
190	▼ 1	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
191	▼ 1	Jamba 1.7 MiniOpenAI21 Labs	8.1	—	—	—
192	▼ 1	LFM2 2.6BOpenLiquid AI	8.0	$0.000	—	—
193	▼ 2	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
194	▼ 1	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
195	▼ 1	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
196	▼ 1	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	8.0	$0.40	124	1.8 s
197	▼ 1	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	182	1.0 s
198	▼ 1	Mixtral 8x7B InstructOpenMistral	7.7	$0.51	—	—
199	▼ 1	Gemma 3 270MOpenGoogle	7.7	—	—	—
200	▼ 1	Apertus 70B InstructOpenSwiss AI Initiative	7.7	$1.3	—	—
201	▼ 1	Granite 4.0 MicroOpenIBM	7.7	—	—	—
202	▼ 1	Llama 65BOpenMeta	7.4	—	—	—
202	▼ 1	Mistral 7B InstructOpenMistral	7.4	$0.21	115	0.7 s
202	▼ 1	Qwen Chat 14BOpenAlibaba	7.4	—	—	—
205	▼ 1	Granite 4.0 1BOpenIBM	7.3	—	—	—
206	▼ 1	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
207	▼ 1	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	319	24 s
208	▼ 1	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	6.5	$0.40	191	1.7 s
209	▼ 1	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
210	▼ 2	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	39	1.5 s
211	▼ 1	LFM2 1.2BOpenLiquid AI	6.3	$0.000	—	—
212	▼ 1	Gemma 3 4B InstructOpenGoogle	6.3	$0.050	—	—
213	▼ 1	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	89	0.9 s
214	▼ 1	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	—	—
215	▼ 1	Granite 4.0 350MOpenIBM	6.1	—	—	—
216	▼ 1	Apertus 8B InstructOpenSwiss AI Initiative	5.9	$0.13	—	—
217	▼ 1	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	—	—
218	▼ 1	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
219	▼ 1	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
220	▼ 1	Tiny Aya GlobalOpenCohere	4.7	$0.000	—	—

170 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