Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	New	Kimi K2.6OpenKimi	53.9	$1.7	100	1.1 s
2	▼ 1	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	51.4	$2.2	49	1.5 s
3	▼ 1	GLM-5 (Reasoning)OpenZ AI · 1 more variant	49.8	$1.6	70	1.7 s
4	▼ 1	MiniMax-M2.7OpenMiniMax	49.6	$0.52	50	2.3 s
5	▼ 1	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	46.8	$1.2	38	2.8 s
6	New	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek · 1 more variant	46.5	$0.18	85	1.0 s
7	New	Qwen3.6 27B (Reasoning)OpenAlibaba	45.8	$1.4	64	3.9 s
8	▼ 3	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	45.1	$1.4	53	2.4 s
9	New	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	43.5	$0.84	209	2.5 s
10	▼ 4	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	42.1	$1.0	103	1.2 s
11	▼ 4	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	42.1	$0.83	80	5.7 s
12	▼ 4	MiniMax-M2.5OpenMiniMax	41.9	$0.52	98	1.9 s
13	▼ 4	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	41.7	$0.32	31	2.1 s
14	▼ 4	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	41.6	$1.1	143	2.5 s
15	▼ 4	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	41.5	$0.15	122	2.3 s
16	▼ 4	Kimi K2 ThinkingOpenKimi	40.9	$1.1	79	2.0 s
17	▼ 4	MiniMax-M2.1OpenMiniMax	39.4	$0.52	86	2.1 s
18	▼ 4	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	39.2	$0.000	35	1.8 s
19	▼ 4	Step 3.5 FlashOpenStepFun	37.8	$0.15	140	1.1 s
20	▼ 4	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	37.1	$0.69	169	2.3 s
21	▼ 4	MiniMax-M2OpenMiniMax	36.1	$0.52	91	1.9 s
22	▼ 4	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	154	1.3 s
23	▼ 4	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	33.9	$1.9	—	—
24	New	Ling-2.6-1TOpenInclusionAI	33.6	$0.85	68	3.1 s
25	▼ 5	gpt-oss-120B (high)OpenOpenAI · 1 more variant	33.3	$0.26	211	0.9 s
26	▼ 5	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	32.9	$0.32	31	2.0 s
27	▼ 5	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	32.5	$0.96	31	1.6 s
28	▼ 5	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	32.4	$0.11	45	1.0 s
29	▼ 5	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	32.1	—	—	—
30	▼ 5	Trinity Large ThinkingOpenArcee AI	31.9	$0.40	116	1.1 s
31	▼ 5	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	31.2	$0.20	—	—
32	▼ 5	Kimi K2 0905OpenKimi · 1 more variant	30.9	$1.1	18	3.2 s
33	▼ 5	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	30.2	$0.15	87	1.2 s
34	▼ 5	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	29.5	$2.6	44	3.1 s
35	▼ 5	DeepSeek V3.2 SpecialeOpenDeepSeek	29.4	—	—	—
36	▼ 5	Nemotron Cascade 2 30B A3BOpenNVIDIA	28.4	—	—	—
37	▼ 5	Qwen3 Coder NextOpenAlibaba	28.3	$0.56	149	1.1 s
38	▼ 5	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	28.1	$0.83	—	—
39	▼ 5	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	27.8	$0.26	147	0.8 s
40	▼ 5	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.6	$2.6	42	3.1 s
41	▼ 5	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	27.1	$0.060	174	0.9 s
42	▼ 5	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	27.1	$2.1	—	—
43	▼ 5	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.7	$1.9	148	2.2 s
44	▼ 5	GLM-4.5 (Reasoning)OpenZ AI	26.4	$1.0	45	3.2 s
45	New	Ling 2.6 FlashOpenInclusionAI	26.2	$0.15	207	1.1 s
46	▼ 6	Seed-OSS-36B-InstructOpenByteDance Seed	25.2	$0.30	36	3.1 s
47	▼ 6	Qwen3 235B A22B 2507 InstructOpenAlibaba	25.0	$1.2	54	2.5 s
48	▼ 6	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.8	$3.0	53	3.2 s
49	▼ 6	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.7	$2.6	89	2.6 s
50	▼ 6	gpt-oss-20B (high)OpenOpenAI · 1 more variant	24.5	$0.10	229	0.7 s
51	▼ 6	MiniMax M1 80kOpenMiniMax	24.4	$0.96	—	—
52	▼ 6	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	24.3	$0.096	128	2.4 s
53	▼ 6	LongCat Flash LiteOpenLongCat	23.9	$0.000	113	7.2 s
54	▼ 6	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	23.4	$0.45	25	2.6 s
55	▼ 6	GLM-4.5-AirOpenZ AI	23.2	$0.37	82	3.0 s
56	▼ 6	Mistral Large 3OpenMistral	22.8	$0.75	50	48 s
57	▼ 6	Ring-1TOpenInclusionAI	22.8	—	—	—
58	▼ 6	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	22.4	$0.75	144	2.5 s
59	▼ 6	DeepSeek V3 0324OpenDeepSeek · 1 more variant	22.3	$1.2	—	—
60	▼ 6	INTELLECT-3OpenPrime Intellect	22.2	—	—	—
61	▼ 6	Devstral 2OpenMistral	22.0	$0.000	72	1.1 s
62	▼ 6	Solar Open 100B (Reasoning)OpenUpstage	21.7	—	—	—
63	▼ 6	MiniMax M1 40kOpenMiniMax	20.9	—	—	—
64	▼ 6	Qwen3 VL 235B A22B InstructOpenAlibaba	20.8	$1.2	51	2.7 s
65	▼ 6	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	149	2.3 s
66	▼ 6	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.90	107	2.6 s
67	▼ 6	QwQ 32BOpenAlibaba	19.7	$0.75	29	2.1 s
68	▼ 6	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.7	$0.75	111	2.3 s
69	▼ 6	Devstral Small 2OpenMistral	19.5	$0.000	62	1.2 s
70	▼ 6	Ling-1TOpenInclusionAI	19.0	—	—	—
71	▼ 6	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	18.8	—	—	—
72	▼ 6	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	18.7	$0.18	49	1.7 s
73	▼ 6	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	18.5	—	—	—
74	▼ 6	Llama 4 MaverickOpenMeta	18.4	$0.48	113	1.0 s
75	▼ 6	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	18.2	—	—	—
76	▼ 6	Magistral Small 1.2OpenMistral	18.2	$0.75	143	0.8 s
76	▼ 6	Sarvam 105B (high)OpenSarvam	18.2	$0.000	121	2.4 s
78	▼ 6	Devstral Small (May '25)OpenMistral · 1 more variant	18.0	—	—	—
79	▼ 6	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	29	2.4 s
80	▼ 6	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	75	2.6 s
81	▼ 6	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	—	—	—
82	▼ 6	Magistral Small 1OpenMistral	16.8	—	—	—
83	▼ 6	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	16.7	—	—	—
84	▼ 6	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.7	$0.66	110	2.5 s
85	▼ 6	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	16.5	$2.6	89	2.5 s
86	▼ 6	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	—	—	—
87	▼ 6	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	16.3	$0.040	—	—
88	▼ 6	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	16.2	$1.3	62	2.8 s
89	▼ 6	Nanbeige4.1-3BOpenNanbeige	16.1	—	—	—
90	▼ 6	Qwen3 VL 30B A3B InstructOpenAlibaba	16.1	$0.35	111	2.2 s
91	▼ 6	Ministral 3 14BOpenMistral	16.0	$0.20	99	0.6 s
92	▼ 6	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	44	1.8 s
93	▼ 6	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	—	—	—
94	▼ 6	Falcon-H1R-7BOpenTII UAE	15.8	—	—	—
95	▼ 6	Ling-flash-2.0OpenInclusionAI	15.7	$0.25	92	2.3 s
96	▼ 6	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	80	2.0 s
97	▼ 6	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.000	28	3.7 s
98	▼ 6	Step3 VL 10BOpenStepFun	15.5	—	—	—
99	▼ 6	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	15.2	—	—	—
100	▼ 6	QwQ 32B-PreviewOpenAlibaba	15.2	—	—	—
101	▼ 6	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	15.1	$0.90	34	1.8 s
101	▼ 6	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	15.1	$3.0	39	1.7 s
103	▼ 6	Mistral Small 3.2OpenMistral	15.1	$0.15	118	0.6 s
104	▼ 6	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	42	2.6 s
105	▼ 6	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.35	55	2.2 s
106	▼ 6	ERNIE 4.5 300B A47BOpenBaidu	15.0	$0.49	26	3.7 s
107	▼ 6	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	14.9	$0.30	125	0.7 s
108	▼ 6	Ministral 3 8BOpenMistral	14.8	$0.15	176	0.6 s
109	▼ 6	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	14.8	$0.070	118	0.7 s
110	▼ 6	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
111	▼ 6	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.62	91	1.4 s
112	▼ 6	Mistral Small 3.1OpenMistral	14.5	$0.15	128	0.7 s
113	▼ 6	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
114	▼ 6	Kimi Linear 48B A3B InstructOpenKimi	14.4	—	—	—
115	▼ 6	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	120	2.4 s
116	▼ 6	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	86	2.3 s
117	▼ 6	Pixtral LargeOpenMistral	14.0	$3.0	50	1.6 s
118	▼ 6	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
119	▼ 6	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	—	—	—
120	▼ 6	Llama 4 ScoutOpenMeta	13.5	$0.29	139	0.8 s
121	▼ 6	Command AOpenCohere	13.5	$4.4	37	2.4 s
122	▼ 6	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	39	1.7 s
123	▼ 6	Qwen2.5 Instruct 32BOpenAlibaba	13.2	—	—	—
124	▼ 6	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	13.2	$0.66	84	2.3 s
125	▼ 6	Qwen3 4B 2507 InstructOpenAlibaba	12.9	—	—	—
126	▼ 6	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	—	—	—
127	▼ 6	Mistral Small 3OpenMistral	12.7	$0.15	132	0.8 s
128	▼ 6	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	12.5	—	—	—
129	▼ 6	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	15	2.1 s
130	▼ 6	Sarvam 30B (high)OpenSarvam	12.3	$0.000	186	2.0 s
131	▼ 6	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	—	—	—
132	▼ 6	R1 1776OpenPerplexity	12.0	—	—	—
133	▼ 6	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$1.4	55	1.2 s
133	▼ 6	Solar MiniOpenUpstage	11.9	$0.15	—	—
135	▼ 6	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	142	0.9 s
136	▼ 6	Grok-1OpenxAI	11.7	—	—	—
137	▼ 6	Qwen2 Instruct 72BOpenAlibaba	11.7	—	—	—
138	▼ 6	Ministral 3 3BOpenMistral	11.2	$0.10	279	0.4 s
139	▼ 6	Jamba 1.7 LargeOpenAI21 Labs	10.9	$3.5	62	1.5 s
140	▼ 6	Granite 4.0 H SmallOpenIBM	10.8	$0.11	430	10 s
141	▼ 6	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
142	▼ 6	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	95	1.9 s
143	▼ 6	DeepSeek-Coder-V2OpenDeepSeek	10.6	—	—	—
144	▼ 6	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	62	1.4 s
145	▼ 6	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	10.5	$0.020	—	—
146	▼ 6	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	122	0.5 s
147	▼ 6	Phi-4OpenMicrosoft Azure	10.4	$0.22	27	2.2 s
148	▼ 6	Gemma 3 27B InstructOpenGoogle	10.3	$0.000	28	2.0 s
149	▼ 6	Mistral Small (Sep '24)OpenMistral	10.2	$0.30	132	0.7 s
150	▼ 6	Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure	10.1	—	—	—
151	▼ 6	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
152	▼ 6	Phi-4 Multimodal InstructOpenMicrosoft Azure	10.0	$0.000	17	0.8 s
153	▼ 6	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	—	—	—
154	▼ 6	Mixtral 8x22B InstructOpenMistral	9.8	—	—	—
155	▼ 6	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
156	▼ 6	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.15	51	1.1 s
157	▼ 6	Jamba Reasoning 3BOpenAI21 Labs	9.6	—	—	—
158	▼ 6	Qwen3 VL 4B InstructOpenAlibaba	9.6	—	—	—
159	▼ 6	Qwen1.5 Chat 110BOpenAlibaba	9.5	—	—	—
160	▼ 6	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
161	▼ 6	Ling-mini-2.0OpenInclusionAI	9.2	—	—	—
162	▼ 6	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	—	—	—
163	▼ 6	DeepSeek-V2-ChatOpenDeepSeek	9.1	—	—	—
164	▼ 6	Llama 3 Instruct 70BOpenMeta	8.9	$1.2	—	—
165	▼ 6	Arctic InstructOpenSnowflake	8.8	—	—	—
165	▼ 6	Qwen Chat 72BOpenAlibaba	8.8	—	—	—
167	▼ 6	Gemma 3 12B InstructOpenGoogle	8.8	$0.000	27	3.3 s
168	▼ 6	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.25	50	0.7 s
169	▼ 6	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	—	—	—
170	▼ 6	Phi-4 Mini InstructOpenMicrosoft Azure	8.4	$0.000	44	0.8 s
170	▼ 6	Sarvam M (Reasoning)OpenSarvam	8.4	—	—	—
172	▼ 6	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	—	—	—
172	▼ 6	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
174	▼ 6	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
175	▼ 6	Command-R+ (Apr '24)OpenCohere · 1 more variant	8.3	$6.0	—	—
176	▼ 6	OpenChat 3.5 (1210)OpenOpenChat	8.3	—	—	—
177	▼ 6	DBRX InstructOpenDatabricks	8.3	—	—	—
178	▼ 6	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	8.3	—	—	—
179	▼ 6	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
180	▼ 6	Jamba 1.7 MiniOpenAI21 Labs	8.1	—	—	—
181	▼ 6	LFM2 2.6BOpenLiquid AI	8.0	$0.000	—	—
181	▼ 6	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
183	▼ 6	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
184	▼ 6	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
185	▼ 6	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	8.0	$0.40	128	1.8 s
186	▼ 6	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	181	0.9 s
187	▼ 6	Mixtral 8x7B InstructOpenMistral	7.7	$0.51	—	—
188	▼ 6	Gemma 3 270MOpenGoogle	7.7	—	—	—
189	▼ 6	Apertus 70B InstructOpenSwiss AI Initiative	7.7	$1.3	—	—
190	▼ 6	Granite 4.0 MicroOpenIBM	7.7	—	—	—
191	▼ 6	Llama 65BOpenMeta	7.4	—	—	—
191	▼ 6	Mistral 7B InstructOpenMistral	7.4	$0.25	165	0.6 s
191	▼ 6	Qwen Chat 14BOpenAlibaba	7.4	—	—	—
194	▼ 6	Granite 4.0 1BOpenIBM	7.3	—	—	—
195	▼ 6	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
196	▼ 6	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	356	26 s
197	▼ 6	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	6.5	$0.40	163	1.6 s
198	▼ 6	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	29	1.3 s
198	▼ 6	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
200	▼ 6	LFM2 1.2BOpenLiquid AI	6.3	$0.000	—	—
201	▼ 6	Gemma 3 4B InstructOpenGoogle	6.3	$0.000	29	1.6 s
202	▼ 6	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	90	0.9 s
203	▼ 6	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	—	—
204	▼ 6	Granite 4.0 350MOpenIBM	6.1	—	—	—
205	▼ 6	Apertus 8B InstructOpenSwiss AI Initiative	5.9	$0.13	—	—
206	▼ 6	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	49	0.9 s
207	▼ 6	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
208	▼ 6	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
209	▼ 6	Tiny Aya GlobalOpenCohere	4.7	—	—	—

159 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