Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Kimi K2.6OpenKimi	53.9	$1.7	38	3.0 s
2	New	MiMo-V2.5-ProOpenXiaomi	53.8	$1.5	60	3.3 s
3	New	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek	51.5	$2.2	34	1.9 s
4	▼ 2	GLM-5.1 (Reasoning)OpenZ AI	51.4	$2.2	48	1.4 s
5	New	DeepSeek V4 Pro (Reasoning, High Effort)OpenDeepSeek	49.8	$2.2	34	1.7 s
6	▼ 3	GLM-5 (Reasoning)OpenZ AI	49.8	$1.6	63	1.9 s
7	▼ 3	MiniMax-M2.7OpenMiniMax	49.6	$0.52	56	2.0 s
8	New	MiMo-V2.5OpenXiaomi	49.0	—	—	—
9	▼ 4	Kimi K2.5 (Reasoning)OpenKimi	46.8	$1.2	37	2.9 s
10	▼ 4	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek	46.5	$0.18	84	1.1 s
11	▼ 4	Qwen3.6 27B (Reasoning)OpenAlibaba	45.8	$1.4	60	3.8 s
12	▼ 4	Qwen3.5 397B A17B (Reasoning)OpenAlibaba	45.1	$1.4	52	2.5 s
13	▼ 4	DeepSeek V4 Flash (Reasoning, High Effort)OpenDeepSeek	44.9	$0.18	—	—
14	▼ 4	GLM-5.1 (Non-reasoning)OpenZ AI	43.8	$2.2	44	2.1 s
15	▼ 4	Qwen3.6 35B A3B (Reasoning)OpenAlibaba	43.5	$0.56	194	2.5 s
16	New	Kimi K2.6 (Non-reasoning)OpenKimi	43.0	$1.7	31	2.9 s
17	▼ 5	GLM-4.7 (Reasoning)OpenZ AI	42.1	$1.0	105	1.3 s
18	▼ 5	Qwen3.5 27B (Reasoning)OpenAlibaba	42.1	$0.83	86	5.8 s
19	▼ 5	MiniMax-M2.5OpenMiniMax	41.9	$0.52	85	1.8 s
20	New	Hy3-preview (Reasoning)OpenTencent	41.9	$0.000	73	3.7 s
21	▼ 6	DeepSeek V3.2 (Reasoning)OpenDeepSeek	41.7	$0.32	—	—
22	▼ 6	Qwen3.5 122B A10B (Reasoning)OpenAlibaba	41.6	$1.1	140	2.5 s
23	▼ 6	MiMo-V2-Flash (Feb 2026)OpenXiaomi	41.5	$0.15	124	3.6 s
24	▼ 6	Kimi K2 ThinkingOpenKimi	40.9	$1.1	99	2.5 s
25	▼ 6	GLM-5 (Non-reasoning)OpenZ AI	40.6	$1.6	63	2.3 s
26	▼ 6	Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba	40.1	$1.4	53	2.4 s
27	▼ 6	MiniMax-M2.1OpenMiniMax	39.4	$0.52	90	1.8 s
28	New	DeepSeek V4 Pro (Non-reasoning)OpenDeepSeek	39.3	$2.2	33	2.0 s
29	▼ 7	MiMo-V2-Flash (Reasoning)OpenXiaomi	39.2	$0.15	123	2.3 s
30	New	Mistral Medium 3.5OpenMistral	39.2	$3.0	165	1.8 s
31	▼ 8	Gemma 4 31B (Reasoning)OpenGoogle	39.2	$0.21	35	1.7 s
32	▼ 8	Step 3.5 FlashOpenStepFun	37.8	$0.15	133	1.4 s
33	▼ 8	Kimi K2.5 (Non-reasoning)OpenKimi	37.3	$1.2	32	2.8 s
34	▼ 8	Qwen3.5 27B (Non-reasoning)OpenAlibaba	37.2	$0.83	88	5.7 s
35	New	Qwen3.6 27B (Non-reasoning)OpenAlibaba	37.1	$1.4	62	3.9 s
36	▼ 9	Qwen3.5 35B A3B (Reasoning)OpenAlibaba	37.1	$0.69	177	2.2 s
37	New	DeepSeek V4 Flash (Non-reasoning)OpenDeepSeek	36.5	$0.18	80	1.2 s
38	▼ 10	MiniMax-M2OpenMiniMax	36.1	$0.52	91	1.7 s
39	▼ 10	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	193	1.5 s
40	▼ 10	Qwen3.5 122B A10B (Non-reasoning)OpenAlibaba	35.9	$1.1	150	2.5 s
41	New	MiMo-V2.5-Pro (Non-reasoning)OpenXiaomi	35.6	$1.5	62	3.3 s
42	▼ 11	GLM-4.7 (Non-reasoning)OpenZ AI	34.2	$0.94	85	1.4 s
43	▼ 11	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek	33.9	$1.9	—	—
44	New	Hy3-preview (Non-reasoning)OpenTencent	33.7	$0.000	73	3.7 s
45	▼ 12	Ling-2.6-1TOpenInclusionAI	33.6	$0.85	—	—
46	▼ 12	gpt-oss-120B (high)OpenOpenAI	33.3	$0.26	207	0.9 s
47	▼ 12	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek	32.9	$0.32	—	—
48	▼ 12	GLM-4.6 (Reasoning)OpenZ AI	32.5	$0.96	24	1.5 s
49	▼ 12	Qwen3.5 9B (Reasoning)OpenAlibaba	32.4	$0.11	51	0.7 s
50	▼ 12	Gemma 4 31B (Non-reasoning)OpenGoogle	32.3	—	—	—
51	▼ 12	K-EXAONE (Reasoning)OpenLG AI Research	32.1	—	—	—
52	▼ 12	DeepSeek V3.2 (Non-reasoning)OpenDeepSeek	32.1	$0.32	—	—
53	▼ 12	Trinity Large ThinkingOpenArcee AI	31.9	$0.40	133	0.9 s
54	▼ 12	Qwen3.6 35B A3B (Non-reasoning)OpenAlibaba	31.5	$0.84	190	2.4 s
55	▼ 12	Gemma 4 26B A4B (Reasoning)OpenGoogle	31.2	$0.20	—	—
56	▼ 12	Kimi K2 0905OpenKimi	30.9	$1.1	17	2.7 s
57	▼ 12	Qwen3.5 35B A3B (Non-reasoning)OpenAlibaba	30.7	$0.69	164	2.1 s
58	▼ 12	MiMo-V2-Flash (Non-reasoning)OpenXiaomi	30.4	$0.15	117	2.4 s
59	▼ 12	GLM-4.6 (Non-reasoning)OpenZ AI	30.2	$1.0	28	1.4 s
60	New	EXAONE 4.5 33BOpenLG AI Research	30.2	—	—	—
61	▼ 13	GLM-4.7-Flash (Reasoning)OpenZ AI	30.2	$0.15	100	1.2 s
62	▼ 13	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba	29.5	$2.6	51	2.9 s
63	▼ 13	DeepSeek V3.2 SpecialeOpenDeepSeek	29.4	—	—	—
64	▼ 13	DeepSeek V3.1 Terminus (Non-reasoning)OpenDeepSeek	28.5	$0.45	—	—
65	▼ 13	DeepSeek V3.2 Exp (Non-reasoning)OpenDeepSeek	28.4	$0.32	—	—
66	▼ 13	Nemotron Cascade 2 30B A3BOpenNVIDIA	28.4	—	—	—
67	▼ 13	Qwen3 Coder NextOpenAlibaba	28.3	$0.56	160	1.1 s
68	▼ 13	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek	28.1	$0.83	—	—
69	▼ 13	Mistral Small 4 (Reasoning)OpenMistral	27.8	$0.26	141	1.0 s
70	▼ 13	DeepSeek V3.1 (Reasoning)OpenDeepSeek	27.7	$0.87	—	—
71	▼ 13	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.6	$2.6	47	3.1 s
72	▼ 13	Qwen3.5 9B (Non-reasoning)OpenAlibaba	27.3	—	—	—
73	▼ 13	Gemma 4 26B A4B (Non-reasoning)OpenGoogle	27.1	—	—	—
74	▼ 13	Qwen3.5 4B (Reasoning)OpenAlibaba	27.1	$0.060	192	0.9 s
75	▼ 13	DeepSeek R1 0528 (May '25)OpenDeepSeek	27.1	$2.1	—	—
76	▼ 13	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.7	$1.9	169	2.2 s
77	▼ 13	GLM-4.5 (Reasoning)OpenZ AI	26.4	$1.0	50	3.2 s
78	▼ 13	Kimi K2OpenKimi	26.3	$1.0	35	2.0 s
79	▼ 13	Ling 2.6 FlashOpenInclusionAI	26.2	$0.15	209	1.5 s
80	▼ 13	Seed-OSS-36B-InstructOpenByteDance Seed	25.2	$0.30	35	3.4 s
81	▼ 13	Qwen3 235B A22B 2507 InstructOpenAlibaba	25.0	$1.2	56	2.5 s
82	▼ 13	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.8	$3.0	60	3.0 s
83	▼ 13	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.7	$2.6	89	2.6 s
84	▼ 13	gpt-oss-120B (low)OpenOpenAI	24.5	$0.26	218	0.9 s
84	▼ 13	gpt-oss-20B (high)OpenOpenAI	24.5	$0.088	240	0.7 s
86	▼ 13	MiniMax M1 80kOpenMiniMax	24.4	$0.96	—	—
87	▼ 13	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA	24.3	$0.096	184	1.3 s
88	▼ 13	LongCat Flash LiteOpenLongCat	23.9	$0.000	107	11 s
89	▼ 13	GLM-4.6V (Reasoning)OpenZ AI	23.4	$0.45	46	3.1 s
90	▼ 13	K-EXAONE (Non-reasoning)OpenLG AI Research	23.4	—	—	—
91	▼ 13	GLM-4.5-AirOpenZ AI	23.2	$0.37	83	2.8 s
92	▼ 13	Mistral Large 3OpenMistral	22.8	$0.75	49	1.4 s
93	▼ 13	Ring-1TOpenInclusionAI	22.8	—	—	—
94	▼ 13	Qwen3.5 4B (Non-reasoning)OpenAlibaba	22.6	$0.060	196	1.0 s
95	▼ 13	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba	22.4	$0.75	129	2.5 s
96	▼ 13	DeepSeek V3 0324OpenDeepSeek	22.3	$1.2	—	—
97	▼ 13	INTELLECT-3OpenPrime Intellect	22.2	—	—	—
98	▼ 13	GLM-4.7-Flash (Non-reasoning)OpenZ AI	22.1	$0.15	108	1.6 s
99	▼ 13	Devstral 2OpenMistral	22.0	$0.000	70	1.0 s
100	▼ 13	Solar Open 100B (Reasoning)OpenUpstage	21.7	—	—	—
101	▼ 13	MiniMax M1 40kOpenMiniMax	20.9	—	—	—
102	▼ 13	gpt-oss-20B (low)OpenOpenAI	20.8	$0.095	236	0.7 s
103	▼ 13	Qwen3 VL 235B A22B InstructOpenAlibaba	20.8	$1.2	49	2.7 s
104	▼ 13	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	148	2.4 s
105	▼ 13	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.90	107	2.7 s
106	▼ 13	Qwen3 235B A22B (Reasoning)OpenAlibaba	19.8	$2.6	54	2.8 s
107	▼ 13	QwQ 32BOpenAlibaba	19.7	$0.75	30	2.0 s
108	▼ 13	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.7	$0.75	111	2.2 s
109	▼ 13	Devstral Small 2OpenMistral	19.5	$0.000	72	1.4 s
110	▼ 13	Ling-1TOpenInclusionAI	19.0	—	—	—
111	▼ 13	DeepSeek R1 (Jan '25)OpenDeepSeek	18.8	$2.4	—	—
112	▼ 13	Gemma 4 E4B (Reasoning)OpenGoogle	18.8	—	—	—
113	▼ 13	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA	18.7	$0.18	49	1.3 s
114	▼ 13	Mistral Small 4 (Non-reasoning)OpenMistral	18.6	$0.26	124	0.9 s
115	▼ 13	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA	18.5	—	—	—
116	▼ 13	Llama 4 MaverickOpenMeta	18.4	$0.48	110	1.1 s
117	▼ 13	Qwen3 4B 2507 (Reasoning)OpenAlibaba	18.2	—	—	—
118	▼ 13	Magistral Small 1.2OpenMistral	18.2	$0.75	102	0.8 s
118	▼ 13	Sarvam 105B (high)OpenSarvam	18.2	$0.000	88	2.3 s
120	▼ 13	Devstral Small (May '25)OpenMistral	18.0	—	—	—
121	▼ 13	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	29	2.4 s
122	▼ 13	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	75	2.6 s
123	▼ 13	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	—	—	—
124	▼ 13	GLM-4.6V (Non-reasoning)OpenZ AI	17.1	$0.45	50	11 s
125	▼ 13	Qwen3 235B A22B (Non-reasoning)OpenAlibaba	17.0	$1.2	55	2.9 s
126	▼ 13	Magistral Small 1OpenMistral	16.8	—	—	—
127	▼ 13	EXAONE 4.0 32B (Reasoning)OpenLG AI Research	16.7	—	—	—
128	▼ 13	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.7	$0.66	114	2.4 s
129	▼ 13	Qwen3 32B (Reasoning)OpenAlibaba	16.5	$2.6	87	2.5 s
130	▼ 13	DeepSeek V3 (Dec '24)OpenDeepSeek	16.5	$0.52	—	—
131	▼ 13	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	—	—	—
132	▼ 13	Qwen3.5 2B (Reasoning)OpenAlibaba	16.3	$0.040	—	—
133	▼ 13	Qwen3 14B (Reasoning)OpenAlibaba	16.2	$1.3	62	2.9 s
134	▼ 13	Nanbeige4.1-3BOpenNanbeige	16.1	—	—	—
135	▼ 13	Qwen3 VL 30B A3B InstructOpenAlibaba	16.1	$0.35	107	2.2 s
136	▼ 13	Ministral 3 14BOpenMistral	16.0	$0.20	119	0.7 s
137	▼ 13	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	44	1.9 s
138	▼ 13	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	—	—	—
139	▼ 13	Falcon-H1R-7BOpenTII UAE	15.8	—	—	—
140	▼ 13	Ling-flash-2.0OpenInclusionAI	15.7	$0.25	87	2.3 s
141	▼ 13	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	91	2.0 s
142	▼ 13	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.000	28	3.6 s
143	▼ 13	Step3 VL 10BOpenStepFun	15.5	—	—	—
144	▼ 13	Qwen3 30B A3B (Reasoning)OpenAlibaba	15.3	$0.75	77	2.4 s
145	▼ 13	Devstral Small (Jul '25)OpenMistral	15.2	$0.15	211	0.6 s
145	▼ 13	Gemma 4 E2B (Reasoning)OpenGoogle	15.2	—	—	—
147	▼ 13	QwQ 32B-PreviewOpenAlibaba	15.2	—	—	—
148	▼ 13	GLM-4.5V (Reasoning)OpenZ AI	15.1	$0.90	41	2.2 s
148	▼ 13	Mistral Large 2 (Nov '24)OpenMistral	15.1	$3.0	38	1.7 s
150	▼ 13	Mistral Small 3.2OpenMistral	15.1	$0.15	162	0.7 s
151	▼ 13	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	40	2.5 s
152	▼ 13	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.35	101	2.0 s
153	▼ 13	ERNIE 4.5 300B A47BOpenBaidu	15.0	$0.49	23	3.5 s
154	▼ 13	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA	14.9	$0.30	128	1.1 s
155	▼ 13	Ministral 3 8BOpenMistral	14.8	$0.15	137	0.6 s
156	▼ 13	Gemma 4 E4B (Non-reasoning)OpenGoogle	14.8	—	—	—
157	▼ 13	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA	14.8	$0.070	120	0.7 s
158	New	Granite 4.1 30BOpenIBM	14.7	—	—	—
159	▼ 14	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
160	▼ 14	Qwen3.5 2B (Non-reasoning)OpenAlibaba	14.7	$0.040	239	0.9 s
161	▼ 14	Llama Nemotron Super 49B v1.5 (Non-reasoning)OpenNVIDIA	14.6	$0.18	50	1.3 s
162	▼ 14	Qwen3 32B (Non-reasoning)OpenAlibaba	14.5	$1.2	85	2.5 s
163	▼ 14	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.62	90	1.5 s
164	▼ 14	Mistral Small 3.1OpenMistral	14.5	$0.15	131	1.0 s
165	▼ 14	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
166	▼ 14	Kimi Linear 48B A3B InstructOpenKimi	14.4	—	—	—
167	▼ 14	Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)OpenNVIDIA	14.3	—	—	—
168	▼ 14	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	119	2.4 s
169	▼ 14	Qwen3 4B (Reasoning)OpenAlibaba	14.2	$0.40	95	2.5 s
170	▼ 14	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	89	2.4 s
171	▼ 14	Pixtral LargeOpenMistral	14.0	$3.0	53	1.9 s
172	▼ 14	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
173	▼ 14	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	—	—	—
174	▼ 14	Llama 4 ScoutOpenMeta	13.5	$0.29	127	0.9 s
175	▼ 14	Command AOpenCohere	13.5	$4.4	44	2.0 s
176	▼ 14	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	36	2.2 s
177	▼ 14	Qwen2.5 Instruct 32BOpenAlibaba	13.2	—	—	—
178	▼ 14	Qwen3 8B (Reasoning)OpenAlibaba	13.2	$0.66	89	2.2 s
179	▼ 14	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)OpenNVIDIA	13.2	$0.088	95	0.4 s
180	▼ 14	NVIDIA Nemotron Nano 9B V2 (Non-reasoning)OpenNVIDIA	13.2	$0.086	132	1.1 s
181	▼ 14	Mistral Large 2 (Jul '24)OpenMistral	13.0	$3.0	—	—
182	▼ 14	Qwen3 4B 2507 InstructOpenAlibaba	12.9	—	—	—
183	▼ 14	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	—	—	—
184	▼ 14	Qwen3 14B (Non-reasoning)OpenAlibaba	12.8	$0.61	62	2.7 s
185	▼ 14	GLM-4.5V (Non-reasoning)OpenZ AI	12.7	$0.90	43	33 s
186	▼ 14	Mistral Small 3OpenMistral	12.7	$0.15	135	1.0 s
187	▼ 14	Qwen3 30B A3B (Non-reasoning)OpenAlibaba	12.5	$0.35	75	2.4 s
188	▼ 14	DeepSeek-V2.5 (Dec '24)OpenDeepSeek	12.5	—	—	—
189	▼ 14	Qwen3 4B (Non-reasoning)OpenAlibaba	12.5	$0.19	96	2.4 s
190	▼ 14	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	31	1.9 s
191	New	Granite 4.1 8BOpenIBM	12.4	$0.063	125	0.8 s
192	▼ 15	Sarvam 30B (high)OpenSarvam	12.3	$0.000	182	2.1 s
193	▼ 15	DeepSeek-V2.5OpenDeepSeek	12.3	—	—	—
194	▼ 15	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	—	—	—
195	▼ 15	Gemma 4 E2B (Non-reasoning)OpenGoogle	12.1	—	—	—
196	▼ 15	R1 1776OpenPerplexity	12.0	—	—	—
197	▼ 15	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$1.4	58	1.2 s
197	▼ 15	Solar MiniOpenUpstage	11.9	$0.15	—	—
199	▼ 15	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	144	0.9 s
200	▼ 15	Grok-1OpenxAI	11.7	—	—	—
201	▼ 15	Qwen2 Instruct 72BOpenAlibaba	11.7	—	—	—
202	▼ 15	EXAONE 4.0 32B (Non-reasoning)OpenLG AI Research	11.7	—	—	—
203	▼ 15	Ministral 3 3BOpenMistral	11.2	$0.10	264	0.5 s
204	▼ 15	Jamba 1.7 LargeOpenAI21 Labs	10.9	$3.5	61	1.5 s
205	▼ 15	Granite 4.0 H SmallOpenIBM	10.8	$0.11	370	10 s
206	▼ 15	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
207	▼ 15	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	95	1.9 s
208	▼ 15	Qwen3 8B (Non-reasoning)OpenAlibaba	10.6	$0.31	81	2.2 s
209	▼ 15	DeepSeek-Coder-V2OpenDeepSeek	10.6	—	—	—
210	▼ 15	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	60	1.4 s
211	▼ 15	Qwen3.5 0.8B (Reasoning)OpenAlibaba	10.5	$0.020	—	—
212	▼ 15	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	180	0.5 s
213	▼ 15	Phi-4OpenMicrosoft	10.4	$0.22	35	2.1 s
214	▼ 15	Gemma 3 27B InstructOpenGoogle	10.3	$0.000	24	2.0 s
215	▼ 15	Mistral Small (Sep '24)OpenMistral	10.2	$0.30	126	1.0 s
216	▼ 15	Phi-3 Mini Instruct 3.8BOpenMicrosoft	10.1	—	—	—
217	▼ 15	NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)OpenNVIDIA	10.1	$0.30	156	1.1 s
218	▼ 15	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
219	▼ 15	Phi-4 Multimodal InstructOpenMicrosoft	10.0	$0.000	17	0.8 s
220	▼ 15	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	—	—	—
221	▼ 15	Qwen3.5 0.8B (Non-reasoning)OpenAlibaba	9.9	$0.020	277	0.8 s
222	▼ 15	Mixtral 8x22B InstructOpenMistral	9.8	—	—	—
223	▼ 15	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
224	▼ 15	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.15	52	1.1 s
225	▼ 15	Jamba Reasoning 3BOpenAI21 Labs	9.6	—	—	—
226	▼ 15	Qwen3 VL 4B InstructOpenAlibaba	9.6	—	—	—
227	▼ 15	Qwen1.5 Chat 110BOpenAlibaba	9.5	—	—	—
228	▼ 15	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
229	▼ 15	Ling-mini-2.0OpenInclusionAI	9.2	—	—	—
230	▼ 15	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	—	—	—
231	▼ 15	DeepSeek-V2-ChatOpenDeepSeek	9.1	—	—	—
232	▼ 15	Llama 3 Instruct 70BOpenMeta	8.9	$1.2	—	—
233	▼ 15	Arctic InstructOpenSnowflake	8.8	—	—	—
233	▼ 15	Qwen Chat 72BOpenAlibaba	8.8	—	—	—
235	▼ 15	Gemma 3 12B InstructOpenGoogle	8.8	$0.000	24	3.8 s
236	▼ 15	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.25	51	0.8 s
237	New	Granite 4.1 3BOpenIBM	8.5	—	—	—
238	▼ 16	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	—	—	—
239	▼ 16	Phi-4 Mini InstructOpenMicrosoft	8.4	$0.000	43	0.8 s
239	▼ 16	Sarvam M (Reasoning)OpenSarvam	8.4	$0.000	—	—
241	▼ 16	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	—	—	—
241	▼ 16	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
243	▼ 16	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
244	▼ 16	Command-R+ (Apr '24)OpenCohere	8.3	$6.0	—	—
245	▼ 16	OpenChat 3.5 (1210)OpenOpenChat	8.3	—	—	—
246	▼ 16	DBRX InstructOpenDatabricks	8.3	—	—	—
247	▼ 16	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research	8.3	—	—	—
248	▼ 16	Exaone 4.0 1.2B (Non-reasoning)OpenLG AI Research	8.1	—	—	—
249	▼ 16	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
250	▼ 16	Jamba 1.7 MiniOpenAI21 Labs	8.1	—	—	—
251	▼ 16	LFM2 2.6BOpenLiquid AI	8.0	$0.000	—	—
251	▼ 16	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
253	▼ 16	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
254	▼ 16	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
255	▼ 16	Qwen3 1.7B (Reasoning)OpenAlibaba	8.0	$0.40	123	1.8 s
256	▼ 16	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	180	0.9 s
257	▼ 16	Mixtral 8x7B InstructOpenMistral	7.7	$0.51	—	—
258	▼ 16	Gemma 3 270MOpenGoogle	7.7	—	—	—
259	▼ 16	Apertus 70B InstructOpenSwiss AI Initiative	7.7	$1.3	—	—
260	▼ 16	Granite 4.0 MicroOpenIBM	7.7	—	—	—
261	▼ 16	Command-R (Mar '24)OpenCohere	7.4	$0.75	—	—
261	▼ 16	Llama 65BOpenMeta	7.4	—	—	—
261	▼ 16	Mistral 7B InstructOpenMistral	7.4	$0.25	137	0.6 s
261	▼ 16	Qwen Chat 14BOpenAlibaba	7.4	—	—	—
265	▼ 16	Granite 4.0 1BOpenIBM	7.3	—	—	—
266	▼ 16	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
267	▼ 16	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	356	26 s
268	▼ 16	Qwen3 1.7B (Non-reasoning)OpenAlibaba	6.8	$0.19	128	1.9 s
269	▼ 16	Qwen3 0.6B (Reasoning)OpenAlibaba	6.5	$0.40	176	1.8 s
270	▼ 16	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	15	1.2 s
270	▼ 16	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
272	▼ 16	LFM2 1.2BOpenLiquid AI	6.3	$0.000	—	—
273	▼ 16	Gemma 3 4B InstructOpenGoogle	6.3	$0.000	26	1.5 s
274	▼ 16	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	99	1.0 s
275	▼ 16	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	—	—
276	▼ 16	Granite 4.0 350MOpenIBM	6.1	—	—	—
277	▼ 16	Apertus 8B InstructOpenSwiss AI Initiative	5.9	$0.13	—	—
278	▼ 16	Qwen3 0.6B (Non-reasoning)OpenAlibaba	5.7	$0.19	180	1.6 s
279	▼ 16	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	57	0.8 s
280	▼ 16	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
281	▼ 16	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
282	▼ 16	Tiny Aya GlobalOpenCohere	4.7	$0.000	—	—

232 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