Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	New	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	51.4	$2.2	66	1.7 s
2	▼ 1	GLM-5 (Reasoning)OpenZ AI · 1 more variant	49.8	$1.6	73	1.7 s
3	▼ 1	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	46.8	$1.2	37	2.1 s
4	▼ 1	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	45.1	$1.4	80	2.5 s
5	▼ 1	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	42.1	$1.0	69	1.4 s
6	▼ 1	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	42.1	$0.83	87	5.7 s
7	▼ 1	MiniMax-M2.5OpenMiniMax	41.9	$0.52	69	2.5 s
8	▼ 1	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	41.7	$0.32	46	2.1 s
9	▼ 1	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	41.6	$1.1	122	2.4 s
10	▼ 1	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	41.5	$0.15	130	2.2 s
11	▼ 1	Kimi K2 ThinkingOpenKimi	40.9	$1.1	76	1.6 s
12	▼ 1	MiniMax-M2.1OpenMiniMax	39.4	$0.52	69	2.2 s
13	New	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	39.2	$0.000	36	1.7 s
14	▼ 2	Step 3.5 FlashOpenStepFun	37.8	$0.15	165	2.3 s
15	▼ 2	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	37.1	$0.69	185	2.1 s
16	▼ 2	MiniMax-M2OpenMiniMax	36.1	$0.52	70	2.0 s
17	▼ 2	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	172	1.0 s
18	▼ 2	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	33.9	$0.80	—	—
19	▼ 2	gpt-oss-120B (high)OpenOpenAI · 1 more variant	33.3	$0.26	215	0.9 s
20	▼ 2	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	32.9	$0.32	45	2.2 s
21	▼ 2	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	32.5	$0.98	64	1.2 s
22	▼ 2	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	32.4	$0.096	105	0.7 s
23	▼ 2	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	32.1	—	—	—
24	New	Trinity Large ThinkingOpenArcee AI	31.9	$0.40	101	1.0 s
25	New	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	31.2	$0.20	—	—
26	▼ 4	Kimi K2 0905OpenKimi · 1 more variant	30.9	$1.2	50	1.1 s
27	▼ 4	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	30.2	$0.15	80	1.6 s
28	▼ 4	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	29.5	$2.6	38	3.1 s
29	▼ 4	DeepSeek V3.2 SpecialeOpenDeepSeek	29.4	—	—	—
30	▼ 4	Qwen3 Coder NextOpenAlibaba	28.3	$0.56	145	1.9 s
31	▼ 4	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	28.1	$0.84	—	—
32	▼ 4	Nemotron Cascade 2 30B A3BOpenNVIDIA	27.7	—	—	—
33	▼ 4	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.6	$2.6	55	2.9 s
34	▼ 4	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	27.2	$0.26	144	3.4 s
35	▼ 4	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	27.1	$0.060	190	0.7 s
36	▼ 4	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	27.1	$2.4	—	—
37	▼ 4	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.7	$1.9	172	2.2 s
38	▼ 4	GLM-4.5 (Reasoning)OpenZ AI	26.4	$0.84	48	2.9 s
39	▼ 4	Seed-OSS-36B-InstructOpenByteDance Seed	25.2	$0.30	36	3.1 s
40	▼ 4	Qwen3 235B A22B 2507 InstructOpenAlibaba	25.0	$1.2	55	2.4 s
41	▼ 4	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.8	$3.0	57	3.0 s
42	▼ 4	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.7	$2.6	90	2.8 s
43	▼ 4	gpt-oss-20B (high)OpenOpenAI · 1 more variant	24.5	$0.095	249	0.7 s
44	▼ 4	MiniMax M1 80kOpenMiniMax	24.4	$0.96	—	—
45	▼ 4	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	24.3	$0.11	101	1.7 s
46	▼ 4	LongCat Flash LiteOpenLongCat	23.9	$0.000	117	6.7 s
47	▼ 4	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	23.4	$0.45	26	2.3 s
48	▼ 4	GLM-4.5-AirOpenZ AI	23.2	$0.43	83	1.3 s
49	▼ 4	Mistral Large 3OpenMistral	22.8	$0.75	38	1.7 s
50	▼ 4	Ring-1TOpenInclusionAI	22.8	—	—	—
51	▼ 4	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	22.4	$0.75	150	2.5 s
52	▼ 4	DeepSeek V3 0324OpenDeepSeek · 1 more variant	22.3	$1.3	—	—
53	▼ 4	INTELLECT-3OpenPrime Intellect	22.2	—	—	—
54	▼ 4	Devstral 2OpenMistral	22.0	$0.000	71	0.9 s
55	▼ 4	Solar Open 100B (Reasoning)OpenUpstage	21.7	—	—	—
56	▼ 4	MiniMax M1 40kOpenMiniMax	20.9	—	—	—
57	▼ 4	Qwen3 VL 235B A22B InstructOpenAlibaba	20.8	$1.2	56	2.8 s
58	▼ 4	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	162	2.2 s
59	▼ 4	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.90	28	2.8 s
60	▼ 4	QwQ 32BOpenAlibaba	19.7	$0.75	31	2.1 s
61	▼ 4	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.7	$0.75	111	2.2 s
62	▼ 4	Devstral Small 2OpenMistral	19.5	$0.000	72	1.0 s
63	▼ 4	Ling-1TOpenInclusionAI	19.0	—	—	—
64	New	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	18.8	—	—	—
65	▼ 5	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	18.7	$0.18	55	1.5 s
66	▼ 5	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	18.5	—	—	—
67	▼ 5	Llama 4 MaverickOpenMeta	18.4	$0.46	110	1.0 s
68	▼ 5	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	18.2	—	—	—
69	▼ 5	Magistral Small 1.2OpenMistral	18.2	$0.75	162	0.8 s
69	▼ 5	Sarvam 105B (high)OpenSarvam	18.2	$0.000	112	2.5 s
71	▼ 5	Devstral Small (May '25)OpenMistral · 1 more variant	18.0	$0.075	—	—
72	▼ 5	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	29	2.4 s
73	▼ 5	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	73	2.6 s
74	▼ 5	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	$0.27	44	1.4 s
75	▼ 5	Magistral Small 1OpenMistral	16.8	—	—	—
76	▼ 5	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	16.7	—	—	—
77	▼ 5	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.7	$0.66	115	2.4 s
78	▼ 5	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	16.5	$2.6	98	2.4 s
79	▼ 5	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	—	—	—
80	▼ 5	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	16.3	$0.040	—	—
81	▼ 5	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	16.2	$1.3	61	2.6 s
82	▼ 5	Nanbeige4.1-3BOpenNanbeige	16.1	—	—	—
83	▼ 5	Qwen3 VL 30B A3B InstructOpenAlibaba	16.1	$0.35	111	2.2 s
84	▼ 5	Ministral 3 14BOpenMistral	16.0	$0.20	108	0.7 s
85	▼ 5	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	39	3.0 s
86	▼ 5	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	—	—	—
87	▼ 5	Falcon-H1R-7BOpenTII UAE	15.8	—	—	—
88	▼ 5	Ling-flash-2.0OpenInclusionAI	15.7	$0.25	62	2.4 s
89	▼ 5	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	91	1.9 s
90	▼ 5	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.000	28	3.5 s
91	▼ 5	Step3 VL 10BOpenStepFun	15.5	—	—	—
92	New	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	15.2	—	—	—
93	▼ 6	QwQ 32B-PreviewOpenAlibaba	15.2	$0.14	45	1.1 s
94	▼ 6	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	15.1	$0.90	50	1.9 s
94	▼ 6	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	15.1	$3.0	39	1.6 s
96	▼ 6	Mistral Small 3.2OpenMistral	15.1	$0.15	121	0.8 s
97	▼ 6	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	41	2.5 s
98	▼ 6	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.35	85	2.0 s
99	▼ 6	ERNIE 4.5 300B A47BOpenBaidu	15.0	$0.49	25	3.5 s
100	▼ 6	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	14.9	$0.30	142	0.6 s
101	▼ 6	Ministral 3 8BOpenMistral	14.8	$0.15	180	0.6 s
102	▼ 6	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	14.8	$0.070	157	0.6 s
103	▼ 6	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
104	▼ 6	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.61	87	1.4 s
105	▼ 6	Mistral Small 3.1OpenMistral	14.5	$0.15	125	1.6 s
106	▼ 6	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
107	▼ 6	Kimi Linear 48B A3B InstructOpenKimi	14.4	—	—	—
108	▼ 6	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	121	2.3 s
109	▼ 6	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	85	2.6 s
110	▼ 6	Pixtral LargeOpenMistral	14.0	$3.0	52	1.5 s
111	▼ 6	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
112	▼ 6	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	—	—	—
113	▼ 6	Llama 4 ScoutOpenMeta	13.5	$0.29	143	0.8 s
114	▼ 6	Command AOpenCohere	13.5	$4.4	32	2.1 s
115	▼ 6	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	46	1.9 s
116	▼ 6	Qwen2.5 Instruct 32BOpenAlibaba	13.2	—	—	—
117	▼ 6	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	13.2	$0.66	78	2.2 s
118	▼ 6	Qwen3 4B 2507 InstructOpenAlibaba	12.9	—	—	—
119	▼ 6	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	—	—	—
120	▼ 6	Mistral Small 3OpenMistral	12.7	$0.15	123	1.5 s
121	▼ 6	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	12.5	—	—	—
122	▼ 6	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	27	2.1 s
123	▼ 6	Sarvam 30B (high)OpenSarvam	12.3	$0.000	142	1.9 s
124	▼ 6	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	—	—	—
125	▼ 6	R1 1776OpenPerplexity	12.0	—	—	—
126	▼ 6	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$0.72	54	1.1 s
126	▼ 6	Solar MiniOpenUpstage	11.9	$0.15	—	—
128	▼ 6	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	150	0.8 s
129	▼ 6	Grok-1OpenxAI	11.7	—	—	—
130	▼ 6	Qwen2 Instruct 72BOpenAlibaba	11.7	—	—	—
131	▼ 6	Ministral 3 3BOpenMistral	11.2	$0.10	279	0.5 s
132	▼ 6	Jamba 1.7 LargeOpenAI21 Labs	10.9	$3.5	59	1.4 s
133	▼ 6	Granite 4.0 H SmallOpenIBM	10.8	$0.11	442	10 s
134	▼ 6	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
135	▼ 6	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	95	1.9 s
136	▼ 6	DeepSeek-Coder-V2OpenDeepSeek	10.6	—	—	—
137	▼ 6	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	59	1.4 s
138	▼ 6	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	10.5	$0.020	—	—
139	▼ 6	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	52	0.5 s
140	▼ 6	Phi-4OpenMicrosoft Azure	10.4	$0.22	34	2.1 s
141	▼ 6	Gemma 3 27B InstructOpenGoogle	10.3	$0.000	28	2.7 s
142	▼ 6	Mistral Small (Sep '24)OpenMistral	10.2	$0.30	121	2.4 s
143	▼ 6	Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure	10.1	—	—	—
144	▼ 6	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
145	▼ 6	Phi-4 Multimodal InstructOpenMicrosoft Azure	10.0	$0.000	17	0.8 s
146	▼ 6	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	—	—	—
147	▼ 6	Mixtral 8x22B InstructOpenMistral	9.8	—	—	—
148	▼ 6	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
149	▼ 6	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.085	51	0.9 s
150	▼ 6	Jamba Reasoning 3BOpenAI21 Labs	9.6	—	—	—
151	▼ 6	Qwen3 VL 4B InstructOpenAlibaba	9.6	—	—	—
152	▼ 6	Qwen1.5 Chat 110BOpenAlibaba	9.5	—	—	—
153	▼ 6	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
154	▼ 6	Ling-mini-2.0OpenInclusionAI	9.2	—	—	—
155	▼ 6	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	—	—	—
156	▼ 6	DeepSeek-V2-ChatOpenDeepSeek	9.1	—	—	—
157	▼ 6	Llama 3 Instruct 70BOpenMeta	8.9	$0.87	—	—
158	▼ 6	Arctic InstructOpenSnowflake	8.8	—	—	—
158	▼ 6	Qwen Chat 72BOpenAlibaba	8.8	—	—	—
160	▼ 6	Gemma 3 12B InstructOpenGoogle	8.8	$0.000	29	35 s
161	▼ 6	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.16	52	0.8 s
162	▼ 6	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	—	—	—
163	▼ 6	Phi-4 Mini InstructOpenMicrosoft Azure	8.4	$0.000	43	0.8 s
163	▼ 6	Sarvam M (Reasoning)OpenSarvam	8.4	—	—	—
165	▼ 6	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	—	—	—
165	▼ 6	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
167	▼ 6	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
168	▼ 6	Command-R+ (Apr '24)OpenCohere · 1 more variant	8.3	$6.0	—	—
169	▼ 6	OpenChat 3.5 (1210)OpenOpenChat	8.3	—	—	—
170	▼ 6	DBRX InstructOpenDatabricks	8.3	—	—	—
171	▼ 6	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	8.3	—	—	—
172	▼ 6	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
173	▼ 6	Jamba 1.7 MiniOpenAI21 Labs	8.1	—	—	—
174	▼ 6	LFM2 2.6BOpenLiquid AI	8.0	$0.000	—	—
174	▼ 6	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
176	▼ 6	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
177	▼ 6	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
178	▼ 6	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	8.0	$0.40	124	1.7 s
179	▼ 6	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	174	0.9 s
180	▼ 6	Mixtral 8x7B InstructOpenMistral	7.7	$0.56	—	—
181	▼ 6	Gemma 3 270MOpenGoogle	7.7	—	—	—
182	▼ 6	Apertus 70B InstructOpenSwiss AI Initiative	7.7	$1.3	—	—
183	▼ 6	Granite 4.0 MicroOpenIBM	7.7	—	—	—
184	▼ 6	Llama 65BOpenMeta	7.4	—	—	—
184	▼ 6	Mistral 7B InstructOpenMistral	7.4	$0.25	180	0.6 s
184	▼ 6	Qwen Chat 14BOpenAlibaba	7.4	—	—	—
187	▼ 6	Granite 4.0 1BOpenIBM	7.3	—	—	—
188	▼ 6	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
189	▼ 6	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	321	21 s
190	▼ 6	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	6.5	$0.40	159	1.6 s
191	▼ 6	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	38	1.1 s
191	▼ 6	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
193	▼ 6	LFM2 1.2BOpenLiquid AI	6.3	$0.000	—	—
194	▼ 6	Gemma 3 4B InstructOpenGoogle	6.3	$0.000	30	1.6 s
195	▼ 6	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	88	1.0 s
196	▼ 6	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	—	—
197	▼ 6	Granite 4.0 350MOpenIBM	6.1	—	—	—
198	▼ 6	Apertus 8B InstructOpenSwiss AI Initiative	5.9	$0.13	—	—
199	▼ 6	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	37	0.8 s
200	▼ 6	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
201	▼ 6	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
202	▼ 6	Tiny Aya GlobalOpenCohere	4.7	—	—	—

152 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