Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	New	Kimi K3 (max)OpenKimi · 1 more variant	57.1	$6.0	35	2.8 s
2	▼ 1	GLM-5.2 (max)OpenZ AI · 1 more variant	51.1	$2.2	173	1.5 s
3	▲ 7	DeepSeek V4 Flash 0731 (Reasoning, Max Effort)OpenDeepSeek · 3 more variants	49.9	$0.18	—	—
4	▼ 2	MiniMax-M3OpenMiniMax	44.4	$0.52	85	1.3 s
5	▼ 2	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	44.3	$0.54	55	1.6 s
6	▼ 2	Kimi K2.6OpenKimi · 1 more variant	44.2	$1.7	39	2.8 s
7	▼ 2	MiMo-V2.5-ProOpenXiaomi · 1 more variant	42.2	$0.54	39	2.7 s
8	▼ 2	Kimi K2.7 CodeOpenKimi	41.9	$1.7	40	3.2 s
9	▼ 2	Hy3OpenTencent	41.2	$0.24	72	2.7 s
10	▼ 2	Nex-N2-ProOpenNex AGI	41.0	$1.0	129	1.4 s
11	▼ 2	Inkling (xhigh)OpenThinking Machines	40.7	$2.6	84	1.8 s
12	New	Inkling SmallOpenThinking Machines	40.2	$0.52	102	1.7 s
13	▼ 2	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	40.2	$2.1	72	1.6 s
14	▼ 2	GLM-5 (Reasoning)OpenZ AI · 1 more variant	39.5	$1.6	43	1.7 s
15	▼ 2	MiniMax-M2.7OpenMiniMax	38.1	$0.52	95	1.5 s
16	▼ 2	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	37.8	$1.2	162	1.5 s
17	▼ 2	MiMo-V2.5OpenXiaomi	37.2	$0.18	73	3.0 s
18	▼ 2	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	37.1	$1.4	58	3.7 s
19	▼ 2	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	35.4	$1.2	61	2.8 s
20	▼ 2	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	33.8	$0.83	77	5.6 s
21	▼ 2	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	33.7	$1.0	112	1.1 s
22	▼ 2	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	33.7	$1.4	67	2.4 s
23	▼ 2	MiniMax-M2.5OpenMiniMax	33.7	$0.52	77	1.7 s
24	▼ 2	Hy3-preview (Reasoning)OpenTencent · 1 more variant	33.6	$0.11	—	—
25	▼ 2	LongCat 2.0OpenLongCat	33.5	$1.3	43	2.7 s
26	▼ 2	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	33.2	—	—	—
27	▼ 2	Kimi K2 ThinkingOpenKimi	32.7	$1.1	122	1.4 s
28	▼ 2	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	32.3	$1.1	136	2.4 s
29	▼ 2	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	32.0	$0.32	—	—
30	▼ 2	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	31.6	$0.56	165	2.2 s
31	▼ 2	MiniMax-M2.1OpenMiniMax	31.4	$0.52	79	1.6 s
32	▼ 2	Ring-2.6-1TOpenInclusionAI	30.6	$0.85	125	3.0 s
33	▼ 2	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	30.4	$1.9	—	—
34	▼ 2	Step 3.7 FlashOpenStepFun	30.3	$0.44	410	1.1 s
35	▼ 2	Mistral Medium 3.5OpenMistral	29.9	$3.0	90	2.2 s
36	▼ 2	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	29.4	$0.000	35	1.1 s
37	▼ 2	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	29.3	$0.69	154	2.1 s
38	▼ 2	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	28.7	$0.96	53	2.3 s
39	▼ 2	MiniMax-M2OpenMiniMax	28.3	$0.52	67	1.8 s
40	▼ 2	Ling-2.6-1TOpenInclusionAI	26.1	$0.85	—	—
41	▼ 2	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	25.7	$0.20	—	—
42	▼ 2	Step 3.5 FlashOpenStepFun	25.5	$0.15	258	1.0 s
43	▼ 2	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	25.4	$0.32	—	—
44	▼ 2	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	25.4	$0.35	142	1.8 s
45	▼ 2	gpt-oss-120b (high)OpenOpenAI · 1 more variant	23.8	$0.26	212	0.8 s
46	▼ 2	Kimi K2 0905OpenKimi · 1 more variant	23.5	$1.1	38	1.3 s
47	▼ 2	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	22.9	$0.15	97	1.1 s
48	▼ 2	Command A+OpenCohere · 1 more variant	22.5	$0.000	202	0.4 s
49	▼ 2	DeepSeek V3.2 SpecialeOpenDeepSeek	22.2	—	—	—
50	▼ 2	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	22.1	—	—	—
51	▼ 2	Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant	21.8	$0.15	109	2.3 s
52	▼ 2	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	21.4	$0.15	76	2.1 s
53	▼ 2	Apriel-v1.5-15B-ThinkerOpenServiceNow	21.2	$0.000	—	—
54	▼ 2	Qwen3 Coder NextOpenAlibaba	21.1	$0.56	142	1.7 s
55	▼ 2	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	21.0	$0.84	—	—
56	▼ 2	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	20.6	$2.6	56	2.9 s
57	▼ 2	Apriel-v1.6-15B-ThinkerOpenServiceNow	20.5	$0.000	—	—
58	▼ 2	EXAONE 4.5 33BOpenLG AI Research	20.2	—	—	—
59	▼ 2	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	20.1	$0.060	46	0.7 s
60	▼ 2	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	20.1	$2.1	—	—
61	▼ 2	North Mini CodeOpenCohere	19.8	$0.000	22	0.6 s
62	▼ 2	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	19.6	$2.6	49	3.0 s
63	▼ 2	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	19.6	$0.26	156	0.8 s
64	▼ 2	GLM-4.5 (Reasoning)OpenZ AI	19.5	—	—	—
65	▼ 2	Devstral 2OpenMistral	19.2	$0.000	46	1.5 s
66	▼ 2	Seed-OSS-36B-InstructOpenByteDance Seed	18.3	$0.30	34	3.0 s
67	▼ 2	Trinity Large ThinkingOpenArcee AI	18.2	$0.40	196	1.0 s
68	▼ 2	Qwen3 235B A22B 2507 InstructOpenAlibaba	18.2	$1.2	56	2.3 s
69	▼ 2	Qwen3 Coder 480B A35B InstructOpenAlibaba	18.0	$3.0	65	3.0 s
70	▼ 2	Qwen3 VL 32B (Reasoning)OpenAlibaba	17.9	$2.6	87	2.8 s
71	▼ 2	HyperNova 60B 2605OpenMultiverse Computing	17.8	$0.065	385	0.7 s
72	▼ 2	MiniMax M1 80kOpenMiniMax	17.7	$0.96	—	—
73	▼ 2	Nemotron Cascade 2 30B A3BOpenNVIDIA	17.6	—	—	—
74	▼ 2	Devstral Small 2OpenMistral	17.4	$0.000	65	1.8 s
75	▼ 2	K2 Think V2OpenMBZUAI Institute of Foundation Models	17.3	—	—	—
76	▼ 2	LongCat Flash LiteOpenLongCat	17.2	—	—	—
77	▼ 2	HyperCLOVA X SEED Think (32B)OpenNaver	17.0	—	—	—
78	▼ 2	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	16.8	$0.45	77	3.6 s
79	▼ 2	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	16.7	$1.9	203	2.3 s
80	▼ 2	GLM-4.5-AirOpenZ AI	16.5	$0.37	78	2.7 s
81	▼ 2	Ring-1TOpenInclusionAI	16.2	—	—	—
82	▼ 2	G9v3-3BOpenAI9Stars	16.1	$0.000	—	—
83	▼ 2	Mistral Large 3OpenMistral	15.9	$0.75	49	1.1 s
84	▼ 2	INTELLECT-3OpenPrime Intellect	15.6	—	—	—
85	▼ 2	DeepSeek V3 0324OpenDeepSeek · 1 more variant	15.4	$0.48	—	—
86	▼ 2	Solar Open 100B (Reasoning)OpenUpstage	15.1	—	—	—
87	▼ 2	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	14.9	$0.13	309	1.0 s
88	▼ 2	gpt-oss-20b (high)OpenOpenAI · 1 more variant	14.9	$0.10	217	1.0 s
89	▼ 2	Mistral Small 3.1OpenMistral	14.7	$0.15	144	0.8 s
90	▼ 2	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	14.4	$0.75	138	2.4 s
91	▼ 2	MiniMax M1 40kOpenMiniMax	14.4	—	—	—
92	▼ 2	Qwen3 VL 235B A22B InstructOpenAlibaba	14.3	$1.2	49	2.7 s
93	▼ 2	Llama 4 MaverickOpenMeta	14.3	$0.42	108	0.9 s
94	▼ 2	K2-V2 (high)OpenMBZUAI Institute of Foundation Models · 2 more variants	14.2	—	—	—
95	▼ 2	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	14.2	$0.088	280	1.1 s
96	▼ 2	Ling 2.6 FlashOpenInclusionAI	14.1	$0.15	86	1.3 s
97	▼ 2	Qwen3 Next 80B A3B InstructOpenAlibaba	13.7	$0.88	179	2.2 s
98	▼ 2	Tri-21B-think PreviewOpenTrillion Labs	13.6	—	—	—
99	▼ 2	Qwen3 Coder 30B A3B InstructOpenAlibaba	13.6	$0.90	92	2.5 s
100	▼ 2	DiffusionGemma 26B A4BOpenGoogle	13.5	—	—	—
101	▼ 2	QwQ 32BOpenAlibaba	13.4	$0.75	31	2.3 s
102	▼ 2	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	13.3	$0.75	109	2.2 s
103	▼ 2	Ling-1TOpenInclusionAI	12.8	—	—	—
104	▼ 2	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	12.4	$0.40	107	4.6 s
105	▼ 2	Tri-21B-ThinkOpenTrillion Labs	12.4	—	—	—
106	▼ 2	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	12.2	—	—	—
107	▲ 1	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	12.2	$0.040	86	0.8 s
108	▼ 3	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	12.0	—	—	—
109	▼ 3	MiniCPM5-1B (Reasoning)OpenOpenBMB · 1 more variant	12.0	—	—	—
110	▼ 3	Sarvam 105B (high)OpenSarvam	11.9	$0.074	—	—
111	▼ 2	Devstral Small (May '25)OpenMistral · 1 more variant	11.8	—	—	—
112	▼ 2	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	11.5	$2.6	93	2.5 s
113	▼ 2	Magistral Small 1.2OpenMistral	11.3	$0.75	141	0.9 s
114	▼ 2	Nanbeige4.1-3BOpenNanbeige	11.1	—	—	—
115	▼ 2	Qwen3 VL 32B InstructOpenAlibaba	11.1	$1.2	66	2.7 s
116	▼ 2	Ministral 3 14BOpenMistral	11.1	$0.20	89	0.8 s
117	▼ 2	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	11.0	—	—	—
118	▼ 2	Magistral Small 1OpenMistral	10.7	—	—	—
119	▼ 2	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	10.6	—	—	—
120	▼ 2	Qwen3 VL 8B (Reasoning)OpenAlibaba	10.6	$0.66	113	2.3 s
121	▼ 2	Mistral Small 3.2OpenMistral	10.6	$0.15	153	0.8 s
122	▼ 2	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	10.4	$1.3	47	3.4 s
123	▼ 2	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	10.4	—	—	—
124	▼ 2	Llama 4 ScoutOpenMeta	10.0	$0.30	129	0.8 s
125	▼ 2	Qwen3 VL 30B A3B InstructOpenAlibaba	10.0	$0.35	114	2.2 s
126	▼ 2	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research · 1 more variant	10.0	$0.20	83	1.4 s
127	▼ 2	DeepSeek R1 Distill Llama 70BOpenDeepSeek	9.9	$0.79	28	0.9 s
128	▼ 2	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	9.8	—	—	—
129	▼ 2	Falcon-H1R-7BOpenTII UAE	9.8	—	—	—
130	▼ 2	Ling-flash-2.0OpenInclusionAI	9.7	$0.25	62	1.6 s
131	—	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	9.7	—	—	—
132	▼ 3	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	9.6	$0.43	99	2.0 s
133	▼ 3	Qwen2.5 Instruct 72BOpenAlibaba	9.6	$0.48	—	—
134	▼ 2	Step3 VL 10BOpenStepFun	9.5	—	—	—
135	▼ 2	Llama 3.3 Instruct 70BOpenMeta	9.4	$0.63	84	1.6 s
136	▼ 2	QwQ 32B-PreviewOpenAlibaba	9.2	—	—	—
137	▼ 2	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	9.1	$0.90	86	1.7 s
138	▼ 2	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	9.1	—	—	—
139	▼ 2	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	9.1	$0.90	52	2.3 s
140	▼ 2	Qwen3 30B A3B 2507 InstructOpenAlibaba	9.1	$0.35	152	1.9 s
141	▼ 2	ERNIE 4.5 300B A47BOpenBaidu	9.0	$0.49	—	—
142	▼ 2	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research · 1 more variant	9.0	$1.5	41	2.4 s
143	▼ 2	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	9.0	$0.30	108	4.4 s
144	▼ 2	Ministral 3 8BOpenMistral	9.0	$0.15	118	0.8 s
145	▼ 2	Granite 4.1 30BOpenIBM	8.9	—	—	—
146	▼ 2	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	8.8	$0.070	225	4.0 s
147	▼ 2	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	8.7	—	—	—
148	▼ 2	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	8.5	—	—	—
149	▼ 2	Kimi Linear 48B A3B InstructOpenKimi	8.5	—	—	—
150	▼ 2	Llama 3.1 Instruct 405BOpenMeta	8.5	$4.4	—	—
151	▼ 2	Qwen3 VL 8B InstructOpenAlibaba	8.4	$0.31	117	2.2 s
152	▼ 2	LFM2.5-8B-A1BOpenLiquid AI	8.3	$0.000	337	2.5 s
153	▼ 2	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	8.3	$0.66	41	3.7 s
154	▼ 2	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	8.3	—	—	—
155	▼ 2	Ring-flash-2.0OpenInclusionAI	8.2	$0.25	—	—
156	▼ 2	Pixtral LargeOpenMistral	8.1	—	—	—
157	▼ 2	Olmo 3.1 32B ThinkOpenAllen Institute for AI	8.1	$0.000	—	—
158	▼ 2	Grok 2 (Dec '24)OpenSpaceXAI	8.0	—	—	—
159	▼ 2	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.9	—	—	—
160	▲ 5	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	7.6	—	—	—
161	▼ 3	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	7.6	$1.2	105	5.6 s
162	▼ 3	Llama 3.1 Instruct 8BOpenMeta	7.6	$0.079	143	0.9 s
163	▼ 3	Qwen2.5 Instruct 32BOpenAlibaba	7.5	—	—	—
164	▼ 3	Gemma 3 27B InstructOpenGoogle	7.4	$0.000	—	—
165	▼ 3	Qwen3 4B 2507 InstructOpenAlibaba	7.1	—	—	—
166	▼ 3	Qwen2.5 Coder Instruct 32BOpenAlibaba	7.1	—	—	—
167	▼ 3	Mistral Small 3OpenMistral	6.9	$0.15	149	0.8 s
168	▲ 3	Ministral 3 3BOpenMistral	6.8	$0.10	230	0.6 s
169	▼ 3	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	6.8	—	—	—
170	▼ 3	Llama 3.1 Instruct 70BOpenMeta	6.8	$0.56	63	1.4 s
171	▼ 3	Granite 4.1 8BOpenIBM	6.7	$0.063	106	0.8 s
172	▼ 3	Sarvam 30B (high)OpenSarvam	6.6	$0.047	—	—
173	▼ 3	Olmo 3.1 32B InstructOpenAllen Institute for AI	6.5	—	—	—
174	▼ 2	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.4	—	—	—
175	▼ 2	Olmo 3 32B ThinkOpenAllen Institute for AI	6.4	—	—	—
176	▼ 2	R1 1776OpenPerplexity	6.3	—	—	—
177	▼ 2	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.2	—	—	—
177	▼ 2	Solar MiniOpenUpstage	6.2	$0.15	—	—
179	▼ 2	Grok-1OpenSpaceXAI	6.0	—	—	—
180	▼ 2	Qwen2 Instruct 72BOpenAlibaba	6.0	—	—	—
181	▼ 2	Phi-4 Mini InstructOpenMicrosoft	6.0	$0.000	44	0.8 s
182	▼ 1	Gemma 3 12B InstructOpenGoogle	5.5	$0.000	—	—
183	▼ 3	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	5.5	—	—	—
184	▼ 2	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	5.3	—	—	—
185	▼ 2	Jamba 1.7 LargeOpenAI21 Labs	5.3	$3.5	59	1.4 s
186	▼ 2	Granite 4.0 H SmallOpenIBM	5.2	$0.11	49	10 s
187	▼ 2	Jamba 1.5 LargeOpenAI21 Labs	5.1	$3.5	—	—
188	▼ 2	Qwen3 Omni 30B A3B InstructOpenAlibaba	5.1	$0.43	95	1.8 s
189	▼ 2	Hermes 3 - Llama-3.1 70BOpenNous Research	5.1	$0.70	33	1.9 s
190	▼ 2	DeepSeek-Coder-V2OpenDeepSeek	5.1	—	—	—
191	▼ 2	OLMo 2 32BOpenAllen Institute for AI	5.0	—	—	—
192	▼ 2	Jamba 1.6 LargeOpenAI21 Labs	5.0	$3.5	56	1.4 s
193	▼ 2	LFM2 24B A2BOpenLiquid AI	4.9	—	—	—
194	▼ 2	Phi-4OpenMicrosoft	4.9	$0.22	—	—
195	▼ 2	Granite 4.1 3BOpenIBM	4.7	—	—	—
196	▼ 2	Mistral Small (Sep '24)OpenMistral	4.7	$0.30	145	0.9 s
197	▼ 2	Phi-3 Mini Instruct 3.8BOpenMicrosoft	4.6	—	—	—
198	▼ 2	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	4.6	—	—	—
199	▼ 2	Phi-4 Multimodal InstructOpenMicrosoft	4.5	$0.000	18	0.8 s
200	▼ 2	Qwen2.5 Coder Instruct 7BOpenAlibaba	4.5	—	—	—
201	▼ 2	Mixtral 8x22B InstructOpenMistral	4.4	—	—	—
202	▼ 2	Llama 2 Chat 7BOpenMeta	4.3	$0.10	—	—
203	▼ 2	Llama 3.2 Instruct 3BOpenMeta	4.2	—	—	—
204	▼ 2	MiniCPM-V 4.6 1.3BOpenOpenBMB	4.2	—	—	—
205	▼ 2	Jamba Reasoning 3BOpenAI21 Labs	4.1	—	—	—
206	▼ 2	Qwen3 VL 4B InstructOpenAlibaba	4.1	—	—	—
207	▼ 2	Qwen1.5 Chat 110BOpenAlibaba	4.1	—	—	—
208	▼ 2	Reka Flash 3OpenReka AI	4.1	$0.35	—	—
209	▼ 2	Olmo 3 7B ThinkOpenAllen Institute for AI	4.0	—	—	—
210	▼ 2	OLMo 2 7BOpenAllen Institute for AI	3.9	—	—	—
211	▼ 2	Molmo 7B-DOpenAllen Institute for AI	3.8	—	—	—
212	▼ 2	Ling-mini-2.0OpenInclusionAI	3.8	—	—	—
213	▼ 2	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	3.7	—	—	—
214	▼ 2	DeepSeek-V2-ChatOpenDeepSeek	3.6	—	—	—
215	▼ 2	Llama 3 Instruct 70BOpenMeta	3.5	$1.2	—	—
216	▼ 2	Arctic InstructOpenSnowflake	3.4	—	—	—
216	▼ 2	Qwen Chat 72BOpenAlibaba	3.4	—	—	—
218	▼ 2	Llama 3.2 Instruct 11B (Vision)OpenMeta	3.3	$0.35	48	1.3 s
219	▼ 2	DeepSeek Coder V2 Lite InstructOpenDeepSeek	3.1	—	—	—
220	▼ 2	Sarvam M (Reasoning)OpenSarvam	3.0	$0.000	—	—
221	▼ 2	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	3.0	—	—	—
221	▼ 2	Llama 2 Chat 70BOpenMeta	3.0	—	—	—
223	▼ 2	Llama 2 Chat 13BOpenMeta	3.0	—	—	—
224	▼ 2	Command-R+ (Apr '24)OpenCohere · 1 more variant	3.0	$6.0	—	—
225	▼ 2	OpenChat 3.5 (1210)OpenOpenChat	3.0	—	—	—
226	▼ 2	DBRX InstructOpenDatabricks	3.0	—	—	—
227	▼ 2	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	2.9	—	—	—
228	▼ 2	Olmo 3 7B InstructOpenAllen Institute for AI	2.8	$0.13	—	—
229	▼ 2	LFM2.5-1.2B-ThinkingOpenLiquid AI	2.7	—	—	—
230	▼ 2	Jamba 1.7 MiniOpenAI21 Labs	2.7	—	—	—
231	▼ 2	LFM2 2.6BOpenLiquid AI	2.7	—	—	—
232	▼ 2	LFM2.5-1.2B-InstructOpenLiquid AI	2.7	—	—	—
233	▼ 2	Jamba 1.5 MiniOpenAI21 Labs	2.7	$0.25	—	—
234	▼ 2	Granite 4.0 H 1BOpenIBM	2.7	—	—	—
235	▼ 2	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	2.6	—	—	—
236	▼ 2	Jamba 1.6 MiniOpenAI21 Labs	2.6	$0.25	178	0.8 s
237	▼ 2	Mixtral 8x7B InstructOpenMistral	2.4	$0.51	—	—
238	▼ 2	Gemma 3 270MOpenGoogle	2.4	—	—	—
239	▼ 2	Apertus 70B InstructOpenSwiss AI Initiative	2.4	$1.3	—	—
240	▼ 2	Granite 4.0 MicroOpenIBM	2.4	—	—	—
241	▼ 2	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	2.3	—	—	—
242	▼ 2	Llama 65BOpenMeta	2.1	—	—	—
242	▼ 2	Mistral 7B InstructOpenMistral	2.1	$0.25	113	0.8 s
242	▼ 2	Qwen Chat 14BOpenAlibaba	2.1	—	—	—
245	▼ 2	Granite 4.0 1BOpenIBM	2.1	—	—	—
246	▼ 2	Molmo2-8BOpenAllen Institute for AI	2.0	—	—	—
247	▼ 2	LFM2 8B A1BOpenLiquid AI	1.8	—	—	—
248	▼ 2	Granite 3.3 8B (Non-reasoning)OpenIBM	1.8	$0.085	16	28 s
249	▼ 2	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	1.3	—	—	—
250	▼ 2	Llama 3 Instruct 8BOpenMeta	1.2	$0.070	—	—
251	▼ 2	Gemma 3n E4B InstructOpenGoogle	1.2	$0.075	41	1.3 s
252	▼ 2	LFM2 1.2BOpenLiquid AI	1.1	—	—	—
253	▼ 2	Gemma 3 4B InstructOpenGoogle	1.1	$0.000	—	—
254	▼ 2	Llama 3.2 Instruct 1BOpenMeta	1.1	—	—	—
255	▼ 2	LFM2.5-VL-1.6BOpenLiquid AI	1.0	$0.000	381	1.5 s
256	▼ 2	Apertus 8B InstructOpenSwiss AI Initiative	1.0	$0.13	—	—
256	▼ 2	Gemma 3 1B InstructOpenGoogle	1.0	$0.000	—	—
256	▼ 2	Gemma 3n E2B InstructOpenGoogle	1.0	$0.000	—	—
256	▼ 2	Granite 4.0 350MOpenIBM	1.0	—	—	—
256	▼ 2	Granite 4.0 H 350MOpenIBM	1.0	—	—	—
256	▼ 2	Tiny Aya GlobalOpenCohere	1.0	$0.000	—	—

211 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