Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	GLM-5 (Reasoning)OpenZ AI	49.6	$1.6	—	—
2	—	Kimi K2.5 (Reasoning)OpenKimi	46.7	$1.2	—	—
3	—	Qwen3.5 397B A17B (Reasoning)OpenAlibaba	45.0	$1.4	—	—
4	—	GLM-4.7 (Reasoning)OpenZ AI	42.1	$0.95	—	—
5	—	MiniMax-M2.5OpenMiniMax	42.0	$0.52	—	—
6	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek	41.6	$0.32	—	—
7	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi	41.4	$0.15	—	—
8	—	Kimi K2 ThinkingOpenKimi	40.7	$1.1	—	—
9	—	GLM-5 (Non-reasoning)OpenZ AI	40.5	$1.6	—	—
10	—	Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba	39.9	$1.4	—	—
11	—	MiniMax-M2.1OpenMiniMax	39.6	$0.52	—	—
12	—	MiMo-V2-Flash (Reasoning)OpenXiaomi	39.2	$0.15	—	—
13	—	Kimi K2.5 (Non-reasoning)OpenKimi	37.2	$1.2	—	—
14	—	MiniMax-M2OpenMiniMax	36.0	$0.52	—	—
15	—	GLM-4.7 (Non-reasoning)OpenZ AI	34.1	$0.95	—	—
16	—	DeepSeek V3.2 SpecialeOpenDeepSeek	34.1	$0.43	—	—
17	—	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek	33.8	$0.80	—	—
18	—	gpt-oss-120B (high)OpenOpenAI	33.3	$0.26	—	—
19	—	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek	32.9	$0.32	—	—
20	—	GLM-4.6 (Reasoning)OpenZ AI	32.5	$0.96	—	—
21	—	K-EXAONE (Reasoning)OpenLG AI Research	32.1	$0.000	—	—
22	—	DeepSeek V3.2 (Non-reasoning)OpenDeepSeek	32.1	$0.32	—	—
23	—	Kimi K2 0905OpenKimi	30.8	$1.4	—	—
24	—	MiMo-V2-Flash (Non-reasoning)OpenXiaomi	30.6	$0.15	—	—
25	—	GLM-4.6 (Non-reasoning)OpenZ AI	30.2	$1.0	—	—
26	—	GLM-4.7-Flash (Reasoning)OpenZ AI	30.1	$0.15	—	—
27	—	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba	29.5	$2.6	—	—
28	—	DeepSeek V3.1 Terminus (Non-reasoning)OpenDeepSeek	28.4	$0.72	—	—
29	—	Apriel-v1.5-15B-ThinkerOpenServiceNow	28.3	$0.000	—	—
30	—	DeepSeek V3.2 Exp (Non-reasoning)OpenDeepSeek	28.3	$0.32	—	—
31	—	Qwen3 Coder NextOpenAlibaba	28.1	$0.45	—	—
32	—	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek	28.0	$0.84	—	—
33	—	DeepSeek V3.1 (Reasoning)OpenDeepSeek	27.6	$0.87	—	—
34	—	Apriel-v1.6-15B-ThinkerOpenServiceNow	27.5	$0.000	—	—
34	—	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.5	$2.6	—	—
36	—	DeepSeek R1 0528 (May '25)OpenDeepSeek	27.0	$2.1	—	—
37	—	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.5	$1.9	—	—
38	—	GLM-4.5 (Reasoning)OpenZ AI	26.2	$1.0	—	—
39	—	Kimi K2OpenKimi	26.2	$1.1	—	—
40	—	Seed-OSS-36B-InstructOpenByteDance Seed	25.0	$0.30	—	—
41	—	Qwen3 235B A22B 2507 InstructOpenAlibaba	24.7	$1.2	—	—
42	—	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.7	$3.0	—	—
43	—	K2 Think V2OpenMBZUAI Institute of Foundation Models	24.5	$0.000	—	—
43	—	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.5	$2.6	—	—
45	—	gpt-oss-20B (high)OpenOpenAI	24.5	$0.10	—	—
46	—	MiniMax M1 80kOpenMiniMax	24.3	$0.96	—	—
46	—	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA	24.3	$0.11	—	—
48	—	gpt-oss-120B (low)OpenOpenAI	23.9	$0.26	—	—
49	—	HyperCLOVA X SEED Think (32B)OpenNaver	23.7	$0.000	—	—
50	—	GLM-4.6V (Reasoning)OpenZ AI	23.5	$0.45	—	—
51	—	GLM-4.5-AirOpenZ AI	23.2	$0.43	—	—
52	—	K-EXAONE (Non-reasoning)OpenLG AI Research	23.0	$0.000	—	—
52	—	Mi:dm K 2.5 ProOpenKorea Telecom	23.0	$0.000	—	—
54	—	Mistral Large 3OpenMistral	22.7	$0.75	—	—
55	—	Ring-1TOpenInclusionAI	22.5	$0.000	—	—
56	—	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba	22.4	$0.75	—	—
57	—	INTELLECT-3OpenPrime Intellect	22.1	$0.43	—	—
58	—	Devstral 2OpenMistral	22.0	$0.000	—	—
59	—	DeepSeek V3 0324OpenDeepSeek	21.8	$1.2	—	—
60	—	Solar Open 100B (Reasoning)OpenUpstage	21.6	$0.000	—	—
61	—	GLM-4.7-Flash (Non-reasoning)OpenZ AI	21.5	$0.15	—	—
62	—	MiniMax M1 40kOpenMiniMax	20.9	$0.000	—	—
63	—	gpt-oss-20B (low)OpenOpenAI	20.8	$0.10	—	—
64	—	K2-V2 (high)OpenMBZUAI Institute of Foundation Models	20.7	$0.000	—	—
65	—	Qwen3 VL 235B A22B InstructOpenAlibaba	20.6	$1.2	—	—
66	—	Tri-21B-think PreviewOpenTrillion Labs	20.5	$0.000	—	—
67	—	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	—	—
68	—	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.90	—	—
69	—	Qwen3 235B A22B (Reasoning)OpenAlibaba	19.8	$2.6	—	—
70	—	QwQ 32BOpenAlibaba	19.7	$0.47	—	—
71	—	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.6	$0.75	—	—
72	—	Devstral Small 2OpenMistral	19.3	$0.000	—	—
73	—	Ling-1TOpenInclusionAI	19.0	$0.000	—	—
74	—	DeepSeek R1 (Jan '25)OpenDeepSeek	18.8	$2.0	—	—
75	—	K2-V2 (medium)OpenMBZUAI Institute of Foundation Models	18.7	$0.000	—	—
76	—	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA	18.6	$0.18	—	—
76	—	Tri-21B-ThinkOpenTrillion Labs	18.6	$0.000	—	—
78	—	Qwen3 4B 2507 (Reasoning)OpenAlibaba	18.6	$0.000	—	—
79	—	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research	18.6	$1.5	—	—
80	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA	18.5	$0.000	—	—
81	—	Llama 4 MaverickOpenMeta	18.3	$0.44	—	—
82	—	Magistral Small 1.2OpenMistral	18.1	$0.75	—	—
83	—	Devstral Small (May '25)OpenMistral	18.0	$0.15	—	—
84	—	Hermes 4 - Llama-3.1 405B (Non-reasoning)OpenNous Research	17.6	$1.5	—	—
85	—	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	—	—
86	—	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	$0.27	—	—
87	—	GLM-4.6V (Non-reasoning)OpenZ AI	17.1	$0.45	—	—
88	—	Qwen3 235B A22B (Non-reasoning)OpenAlibaba	16.9	$1.2	—	—
89	—	Magistral Small 1OpenMistral	16.8	$0.000	—	—
90	—	EXAONE 4.0 32B (Reasoning)OpenLG AI Research	16.7	$0.70	—	—
91	—	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.6	$0.66	—	—
92	—	Qwen3 32B (Reasoning)OpenAlibaba	16.5	$2.6	—	—
93	—	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	$0.000	—	—
94	—	DeepSeek V3 (Dec '24)OpenDeepSeek	16.4	$0.52	—	—
95	—	Qwen3 14B (Reasoning)OpenAlibaba	16.2	$1.3	—	—
96	—	Qwen3 VL 30B A3B InstructOpenAlibaba	16.0	$0.35	—	—
97	—	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research	16.0	$0.20	—	—
98	—	Ministral 3 14BOpenMistral	16.0	$0.20	—	—
99	—	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	—	—
100	—	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	$0.000	—	—
101	—	Falcon-H1R-7BOpenTII UAE	15.8	$0.000	—	—
102	—	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	—	—
103	—	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.000	—	—
104	—	Ling-flash-2.0OpenInclusionAI	15.5	$0.25	—	—
105	—	Step3 VL 10BOpenStepFun	15.4	$0.000	—	—
106	—	Qwen3 30B A3B (Reasoning)OpenAlibaba	15.3	$0.75	—	—
107	—	Devstral Small (Jul '25)OpenMistral	15.2	$0.15	—	—
108	—	QwQ 32B-PreviewOpenAlibaba	15.2	$0.14	—	—
109	—	Mistral Large 2 (Nov '24)OpenMistral	15.1	$3.0	—	—
110	—	Mistral Small 3.2OpenMistral	15.0	$0.15	—	—
111	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	—	—
112	—	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.35	—	—
113	—	ERNIE 4.5 300B A47BOpenBaidu	14.9	$0.49	—	—
114	—	GLM-4.5V (Reasoning)OpenZ AI	14.9	$0.90	—	—
115	—	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA	14.8	$0.30	—	—
116	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA	14.8	$0.070	—	—
117	—	Ministral 3 8BOpenMistral	14.6	$0.15	—	—
118	—	Qwen3 32B (Non-reasoning)OpenAlibaba	14.5	$1.2	—	—
119	—	Llama Nemotron Super 49B v1.5 (Non-reasoning)OpenNVIDIA	14.5	$0.18	—	—
120	—	K2-V2 (low)OpenMBZUAI Institute of Foundation Models	14.4	$0.000	—	—
121	—	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	$0.000	—	—
122	—	Kimi Linear 48B A3B InstructOpenKimi	14.4	$0.000	—	—
123	—	Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)OpenNVIDIA	14.3	$0.000	—	—
124	—	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	—	—
125	—	Olmo 3.1 32B ThinkOpenAllen Institute for AI	14.2	$0.000	—	—
126	—	Llama 3.3 Instruct 70BOpenMeta	14.2	$0.62	—	—
127	—	Qwen3 4B (Reasoning)OpenAlibaba	14.2	$0.40	—	—
128	—	Llama 3.1 Instruct 405BOpenMeta	14.2	$4.5	—	—
129	—	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	14.1	$0.000	—	—
130	—	Pixtral LargeOpenMistral	14.0	$3.0	—	—
131	—	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	—	—
132	—	Mistral Small 3.1OpenMistral	14.0	$0.15	—	—
133	—	Grok 2 (Dec '24)OpenxAI	13.9	$0.000	—	—
134	—	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	$0.000	—	—
135	—	Hermes 4 - Llama-3.1 70B (Non-reasoning)OpenNous Research	13.6	$0.20	—	—
136	—	Llama 4 ScoutOpenMeta	13.5	$0.29	—	—
137	—	Command AOpenCohere	13.4	$4.4	—	—
138	—	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	—	—
139	—	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)OpenNVIDIA	13.3	$0.096	—	—
140	—	Qwen2.5 Instruct 32BOpenAlibaba	13.2	$0.000	—	—
141	—	Qwen3 4B 2507 InstructOpenAlibaba	13.2	$0.000	—	—
142	—	NVIDIA Nemotron Nano 9B V2 (Non-reasoning)OpenNVIDIA	13.1	$0.10	—	—
142	—	Qwen3 8B (Reasoning)OpenAlibaba	13.1	$0.66	—	—
144	—	Mistral Large 2 (Jul '24)OpenMistral	13.0	$3.0	—	—
145	—	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	$0.14	—	—
146	—	Qwen3 14B (Non-reasoning)OpenAlibaba	12.7	$0.61	—	—
147	—	Mistral Small 3OpenMistral	12.7	$0.15	—	—
148	—	GLM-4.5V (Non-reasoning)OpenZ AI	12.5	$0.90	—	—
149	—	DeepSeek-V2.5 (Dec '24)OpenDeepSeek	12.5	$0.000	—	—
150	—	Qwen3 4B (Non-reasoning)OpenAlibaba	12.5	$0.19	—	—
151	—	Qwen3 30B A3B (Non-reasoning)OpenAlibaba	12.4	$0.35	—	—
152	—	DeepSeek-V2.5OpenDeepSeek	12.3	$0.000	—	—
153	—	Llama 3.1 Instruct 70BOpenMeta	12.2	$0.56	—	—
154	—	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	$0.000	—	—
155	—	Olmo 3.1 32B InstructOpenAllen Institute for AI	12.0	$0.30	—	—
156	—	Olmo 3 32B ThinkOpenAllen Institute for AI	12.0	$0.000	—	—
157	—	R1 1776OpenPerplexity	12.0	$0.000	—	—
158	—	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$0.72	—	—
159	—	Grok-1OpenxAI	11.7	$0.000	—	—
160	—	Llama 3.1 Instruct 8BOpenMeta	11.7	$0.10	—	—
161	—	Qwen2 Instruct 72BOpenAlibaba	11.7	$0.000	—	—
162	—	EXAONE 4.0 32B (Non-reasoning)OpenLG AI Research	11.5	$0.70	—	—
163	—	Ministral 3 3BOpenMistral	11.2	$0.10	—	—
164	—	Phi-4 Mini InstructOpenMicrosoft Azure	10.9	$0.000	—	—
165	—	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	10.9	$0.000	—	—
166	—	Granite 4.0 H SmallOpenIBM	10.8	$0.11	—	—
167	—	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
168	—	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	—	—
169	—	Hermes 3 - Llama-3.1 70BOpenNous Research	10.6	$0.30	—	—
170	—	DeepSeek-Coder-V2OpenDeepSeek	10.6	$0.000	—	—
171	—	OLMo 2 32BOpenAllen Institute for AI	10.6	$0.000	—	—
172	—	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	—	—
173	—	Qwen3 8B (Non-reasoning)OpenAlibaba	10.6	$0.31	—	—
174	—	Phi-4OpenMicrosoft Azure	10.5	$0.22	—	—
175	—	Jamba Reasoning 3BOpenAI21 Labs	10.3	$0.000	—	—
176	—	Llama 3 Instruct 70BOpenMeta	10.2	$0.87	—	—
177	—	Gemma 3 27B InstructOpenGoogle	10.2	$0.000	—	—
178	—	Mistral Small (Sep '24)OpenMistral	10.2	$0.30	—	—
179	—	NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)OpenNVIDIA	10.1	$0.30	—	—
180	—	Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure	10.1	$0.23	—	—
181	—	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	$0.000	—	—
182	—	Phi-4 Multimodal InstructOpenMicrosoft Azure	10.0	$0.000	—	—
183	—	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	$0.000	—	—
184	—	Mixtral 8x22B InstructOpenMistral	9.8	$0.000	—	—
185	—	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.080	—	—
186	—	Qwen1.5 Chat 110BOpenAlibaba	9.5	$0.000	—	—
187	—	Qwen3 VL 4B InstructOpenAlibaba	9.5	$0.000	—	—
187	—	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
189	—	Olmo 3 7B ThinkOpenAllen Institute for AI	9.5	$0.14	—	—
190	—	OLMo 2 7BOpenAllen Institute for AI	9.3	$0.000	—	—
191	—	Jamba 1.7 LargeOpenAI21 Labs	9.3	$3.5	—	—
192	—	Molmo 7B-DOpenAllen Institute for AI	9.2	$0.000	—	—
193	—	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	$0.000	—	—
194	—	DeepSeek-V2-ChatOpenDeepSeek	9.1	$0.000	—	—
195	—	Ling-mini-2.0OpenInclusionAI	8.9	$0.12	—	—
196	—	Arctic InstructOpenSnowflake	8.8	$0.000	—	—
196	—	Qwen Chat 72BOpenAlibaba	8.8	$0.000	—	—
198	—	Gemma 3 12B InstructOpenGoogle	8.8	$0.000	—	—
199	—	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.8	$0.16	—	—
200	—	Llama 3 Instruct 8BOpenMeta	8.7	$0.070	—	—
201	—	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	$0.000	—	—
202	—	Gemma 3 270MOpenGoogle	8.4	$0.000	—	—
203	—	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	$0.000	—	—
204	—	Command-R+ (Apr '24)OpenCohere	8.3	$6.0	—	—
205	—	OpenChat 3.5 (1210)OpenOpenChat	8.3	$0.000	—	—
206	—	DBRX InstructOpenDatabricks	8.3	$0.000	—	—
207	—	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research	8.3	$0.000	—	—
208	—	Olmo 3 7B InstructOpenAllen Institute for AI	8.1	$0.13	—	—
209	—	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	$0.000	—	—
210	—	Exaone 4.0 1.2B (Non-reasoning)OpenLG AI Research	8.1	$0.000	—	—
211	—	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
212	—	Solar MiniOpenUpstage	8.0	$0.15	—	—
213	—	Granite 4.0 H 1BOpenIBM	8.0	$0.000	—	—
214	—	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
215	—	Qwen3 1.7B (Reasoning)OpenAlibaba	7.9	$0.40	—	—
216	—	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	—	—
217	—	LFM2 2.6BOpenLiquid AI	7.9	$0.000	—	—
218	—	Mixtral 8x7B InstructOpenMistral	7.7	$0.56	—	—
219	—	Granite 4.0 MicroOpenIBM	7.7	$0.000	—	—
220	—	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	7.6	$0.000	—	—
221	—	Command-R (Mar '24)OpenCohere	7.4	$0.75	—	—
221	—	Mistral 7B InstructOpenMistral	7.4	$0.25	—	—
221	—	Qwen Chat 14BOpenAlibaba	7.4	$0.000	—	—
224	—	Jamba 1.7 MiniOpenAI21 Labs	7.3	$0.25	—	—
225	—	Granite 4.0 1BOpenIBM	7.3	$0.000	—	—
226	—	Llama 2 Chat 70BOpenMeta	7.0	$0.000	—	—
227	—	Granite 3.3 8B (Non-reasoning)OpenIBM	6.9	$0.085	—	—
227	—	LFM2 8B A1BOpenLiquid AI	6.9	$0.000	—	—
229	—	Qwen3 1.7B (Non-reasoning)OpenAlibaba	6.8	$0.19	—	—
230	—	Granite 4.0 350MOpenIBM	6.6	$0.000	—	—
231	—	Qwen3 0.6B (Reasoning)OpenAlibaba	6.4	$0.40	—	—
232	—	LFM2 1.2BOpenLiquid AI	6.4	$0.000	—	—
233	—	Gemma 3 4B InstructOpenGoogle	6.3	$0.000	—	—
234	—	Gemma 3n E4B InstructOpenGoogle	6.3	$0.025	—	—
235	—	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.10	—	—
236	—	LFM2.5-VL-1.6BOpenLiquid AI	6.1	$0.000	—	—
237	—	Qwen3 0.6B (Non-reasoning)OpenAlibaba	5.6	$0.19	—	—
238	—	Gemma 3 1B InstructOpenGoogle	5.4	$0.000	—	—
239	—	Granite 4.0 H 350MOpenIBM	5.3	$0.000	—	—
240	—	Llama 2 Chat 13BOpenMeta	5.0	$0.000	—	—
241	—	Gemma 3n E2B InstructOpenGoogle	4.7	$0.000	—	—
242	—	Llama 2 Chat 7BOpenMeta	4.0	$0.10	—	—
242	—	Llama 65BOpenMeta	4.0	$0.000	—	—

193 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