Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Kimi K2.6OpenKimi	53.9	$1.7	78	2.5 s
2	—	MiMo-V2.5-ProOpenXiaomi	53.8	$1.5	57	2.7 s
3	—	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek	51.5	$2.2	30	1.9 s
4	—	GLM-5.1 (Reasoning)OpenZ AI	51.4	$2.2	56	1.4 s
5	—	DeepSeek V4 Pro (Reasoning, High Effort)OpenDeepSeek	49.8	$2.2	30	1.9 s
6	—	GLM-5 (Reasoning)OpenZ AI	49.8	$1.6	66	1.6 s
7	—	MiniMax-M2.7OpenMiniMax	49.6	$0.52	50	2.1 s
8	—	MiMo-V2.5OpenXiaomi	49.0	$0.72	94	3.3 s
9	—	Kimi K2.5 (Reasoning)OpenKimi	46.8	$1.2	38	3.0 s
10	—	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek	46.5	$0.18	110	1.2 s
11	—	DeepSeek V4 Flash (Reasoning, High Effort)OpenDeepSeek	46.0	$0.18	—	—
12	—	Qwen3.6 27B (Reasoning)OpenAlibaba	45.8	$1.4	61	3.8 s
13	—	Qwen3.5 397B A17B (Reasoning)OpenAlibaba	45.0	$1.4	52	2.6 s
14	—	GLM-5.1 (Non-reasoning)OpenZ AI	43.8	$2.2	45	1.8 s
15	—	Qwen3.6 35B A3B (Reasoning)OpenAlibaba	43.5	$0.56	191	2.5 s
16	—	Kimi K2.6 (Non-reasoning)OpenKimi	42.9	$1.7	55	2.2 s
17	—	GLM-4.7 (Reasoning)OpenZ AI	42.1	$1.0	90	1.3 s
18	—	Qwen3.5 27B (Reasoning)OpenAlibaba	42.1	$0.83	86	5.7 s
19	—	MiniMax-M2.5OpenMiniMax	41.9	$0.52	89	1.8 s
20	—	Hy3-preview (Reasoning)OpenTencent	41.9	$0.20	104	4.0 s
21	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek	41.7	$0.34	—	—
22	—	Qwen3.5 122B A10B (Reasoning)OpenAlibaba	41.6	$1.1	132	2.6 s
23	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi	41.5	$0.15	136	2.2 s
24	—	Kimi K2 ThinkingOpenKimi	40.9	$1.1	103	2.6 s
25	—	GLM-5 (Non-reasoning)OpenZ AI	40.6	$1.6	45	2.3 s
26	—	Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba	40.1	$1.4	52	2.7 s
27	—	MiniMax-M2.1OpenMiniMax	39.4	$0.52	97	1.7 s
28	—	DeepSeek V4 Pro (Non-reasoning)OpenDeepSeek	39.3	$2.2	30	1.9 s
29	—	MiMo-V2-Flash (Reasoning)OpenXiaomi	39.2	$0.15	142	2.3 s
30	—	Mistral Medium 3.5OpenMistral	39.2	$3.0	152	1.7 s
31	—	Gemma 4 31B (Reasoning)OpenGoogle	39.2	$0.000	35	1.7 s
32	New	Ring-2.6-1TOpenInclusionAI	38.5	—	—	—
33	▼ 1	Step 3.5 FlashOpenStepFun	37.8	$0.15	200	1.1 s
34	▼ 1	Kimi K2.5 (Non-reasoning)OpenKimi	37.3	$1.2	35	3.0 s
35	▼ 1	Qwen3.5 27B (Non-reasoning)OpenAlibaba	37.2	$0.84	89	5.8 s
36	New	Command A+OpenCohere	37.2	$0.000	267	0.3 s
37	▼ 2	Qwen3.6 27B (Non-reasoning)OpenAlibaba	37.1	$1.4	65	3.8 s
38	▼ 2	Qwen3.5 35B A3B (Reasoning)OpenAlibaba	37.1	$0.69	175	2.3 s
39	▼ 2	DeepSeek V4 Flash (Non-reasoning)OpenDeepSeek	36.5	$0.18	115	1.2 s
40	▼ 2	MiniMax-M2OpenMiniMax	36.1	$0.52	99	1.8 s
41	▼ 2	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	177	1.2 s
42	▼ 2	Qwen3.5 122B A10B (Non-reasoning)OpenAlibaba	35.9	$1.1	129	2.4 s
43	▼ 2	MiMo-V2.5-Pro (Non-reasoning)OpenXiaomi	35.6	$1.5	61	2.6 s
44	▼ 2	GLM-4.7 (Non-reasoning)OpenZ AI	34.2	$1.0	103	1.4 s
45	▼ 2	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek	33.9	$1.9	—	—
46	▼ 2	Hy3-preview (Non-reasoning)OpenTencent	33.7	$0.20	104	4.1 s
47	▼ 2	Ling-2.6-1TOpenInclusionAI	33.6	$0.85	—	—
48	New	gpt-oss-120b (high)OpenOpenAI	33.3	$0.26	253	0.9 s
49	▼ 2	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek	32.9	$0.31	—	—
50	▼ 2	GLM-4.6 (Reasoning)OpenZ AI	32.5	$0.96	40	3.0 s
51	▼ 2	Qwen3.5 9B (Reasoning)OpenAlibaba	32.4	$0.11	63	0.7 s
52	▼ 2	Gemma 4 31B (Non-reasoning)OpenGoogle	32.3	$0.21	20	2.1 s
53	▼ 2	K-EXAONE (Reasoning)OpenLG AI Research	32.1	—	—	—
54	▼ 2	DeepSeek V3.2 (Non-reasoning)OpenDeepSeek	32.1	$0.78	—	—
55	▼ 2	Trinity Large ThinkingOpenArcee AI	31.9	$0.40	125	1.1 s
56	▼ 2	Qwen3.6 35B A3B (Non-reasoning)OpenAlibaba	31.5	$0.84	168	2.5 s
57	▼ 2	Gemma 4 26B A4B (Reasoning)OpenGoogle	31.2	$0.20	—	—
58	▼ 2	Kimi K2 0905OpenKimi	30.9	$1.1	17	2.9 s
59	▼ 2	Qwen3.5 35B A3B (Non-reasoning)OpenAlibaba	30.7	$0.69	174	2.2 s
60	▼ 2	MiMo-V2-Flash (Non-reasoning)OpenXiaomi	30.3	$0.15	133	2.3 s
61	▼ 2	GLM-4.6 (Non-reasoning)OpenZ AI	30.2	$1.0	35	3.7 s
62	▼ 2	EXAONE 4.5 33BOpenLG AI Research	30.2	—	—	—
63	▼ 2	GLM-4.7-Flash (Reasoning)OpenZ AI	30.1	$0.15	83	1.3 s
64	▼ 2	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba	29.5	$0.84	55	2.9 s
65	▼ 2	DeepSeek V3.2 SpecialeOpenDeepSeek	29.4	—	—	—
66	▼ 2	DeepSeek V3.1 Terminus (Non-reasoning)OpenDeepSeek	28.5	$0.45	—	—
67	▼ 2	DeepSeek V3.2 Exp (Non-reasoning)OpenDeepSeek	28.4	$0.31	—	—
68	▼ 2	Nemotron Cascade 2 30B A3BOpenNVIDIA	28.4	—	—	—
69	▼ 2	Qwen3 Coder NextOpenAlibaba	28.3	$0.56	93	1.7 s
70	▼ 2	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek	28.1	$0.83	—	—
71	▼ 2	Mistral Small 4 (Reasoning)OpenMistral	27.8	$0.26	135	0.8 s
72	▼ 2	DeepSeek V3.1 (Reasoning)OpenDeepSeek	27.7	$0.87	—	—
73	▼ 2	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.6	$2.2	35	4.2 s
74	▼ 2	Qwen3.5 9B (Non-reasoning)OpenAlibaba	27.3	—	—	—
75	▼ 2	Gemma 4 26B A4B (Non-reasoning)OpenGoogle	27.1	$0.20	73	1.3 s
76	▼ 2	Qwen3.5 4B (Reasoning)OpenAlibaba	27.1	$0.060	165	0.5 s
77	▼ 2	DeepSeek R1 0528 (May '25)OpenDeepSeek	27.1	$2.1	—	—
78	▼ 2	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.7	$1.9	146	2.2 s
79	▼ 2	GLM-4.5 (Reasoning)OpenZ AI	26.4	$1.0	50	3.6 s
80	▼ 2	Kimi K2OpenKimi	26.3	$1.0	27	2.9 s
81	▼ 2	Ling 2.6 FlashOpenInclusionAI	26.2	$0.15	—	—
82	▼ 2	Seed-OSS-36B-InstructOpenByteDance Seed	25.2	$0.30	36	3.5 s
83	▼ 2	Qwen3 235B A22B 2507 InstructOpenAlibaba	25.0	$0.36	61	2.4 s
84	▼ 2	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.8	$0.68	58	3.0 s
85	▼ 2	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.7	$2.6	90	2.7 s
86	▼ 2	gpt-oss-20B (high)OpenOpenAI	24.5	$0.088	239	0.8 s
87	New	gpt-oss-120b (low)OpenOpenAI	24.5	$0.26	281	0.8 s
88	▼ 2	MiniMax M1 80kOpenMiniMax	24.4	$0.96	—	—
89	▼ 2	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA	24.3	$0.096	150	1.4 s
90	▼ 2	LongCat Flash LiteOpenLongCat	23.9	$0.000	114	8.6 s
91	▼ 2	GLM-4.6V (Reasoning)OpenZ AI	23.4	$0.45	46	4.7 s
92	▼ 2	K-EXAONE (Non-reasoning)OpenLG AI Research	23.4	—	—	—
93	▼ 2	GLM-4.5-AirOpenZ AI	23.2	$0.37	61	3.1 s
94	▼ 2	Mistral Large 3OpenMistral	22.8	$0.75	48	1.1 s
95	▼ 2	Ring-1TOpenInclusionAI	22.8	—	—	—
96	▼ 2	Qwen3.5 4B (Non-reasoning)OpenAlibaba	22.6	$0.060	161	0.5 s
97	▼ 2	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba	22.4	$0.67	139	2.4 s
98	▼ 2	DeepSeek V3 0324OpenDeepSeek	22.3	$1.2	—	—
99	▼ 2	INTELLECT-3OpenPrime Intellect	22.2	—	—	—
100	▼ 2	GLM-4.7-Flash (Non-reasoning)OpenZ AI	22.1	$0.15	134	1.8 s
101	▼ 2	Devstral 2OpenMistral	22.0	$0.000	47	1.3 s
102	▼ 2	Solar Open 100B (Reasoning)OpenUpstage	21.7	—	—	—
103	▼ 2	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	21.4	$0.13	301	1.0 s
104	▼ 2	MiniMax M1 40kOpenMiniMax	20.9	—	—	—
105	▼ 2	gpt-oss-20B (low)OpenOpenAI	20.8	$0.095	232	0.8 s
106	▼ 2	Qwen3 VL 235B A22B InstructOpenAlibaba	20.8	$0.70	50	2.8 s
107	▼ 2	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	146	2.4 s
108	▼ 2	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.35	94	2.7 s
109	▼ 2	Qwen3 235B A22B (Reasoning)OpenAlibaba	19.8	$2.6	60	2.9 s
110	▼ 2	QwQ 32BOpenAlibaba	19.7	$0.75	29	2.1 s
111	▼ 2	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.7	$0.34	111	2.4 s
112	▼ 2	Devstral Small 2OpenMistral	19.5	$0.000	50	1.2 s
113	▼ 2	Ling-1TOpenInclusionAI	19.0	—	—	—
114	▼ 2	DeepSeek R1 (Jan '25)OpenDeepSeek	18.8	$2.4	—	—
115	▼ 2	Gemma 4 E4B (Reasoning)OpenGoogle	18.8	—	—	—
116	▼ 2	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA	18.7	$0.18	50	1.3 s
117	▼ 2	Mistral Small 4 (Non-reasoning)OpenMistral	18.6	$0.26	137	0.9 s
118	▼ 2	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA	18.5	—	—	—
119	▼ 2	Llama 4 MaverickOpenMeta	18.4	$0.48	108	1.1 s
120	▼ 2	Qwen3 4B 2507 (Reasoning)OpenAlibaba	18.2	—	—	—
121	▼ 2	Magistral Small 1.2OpenMistral	18.2	$0.75	105	0.8 s
122	▼ 2	Sarvam 105B (high)OpenSarvam	18.2	$0.000	112	2.2 s
123	▼ 2	Devstral Small (May '25)OpenMistral	18.0	—	—	—
124	▼ 2	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	53	2.4 s
125	▼ 2	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	78	2.6 s
126	▼ 2	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	—	—	—
127	▼ 2	GLM-4.6V (Non-reasoning)OpenZ AI	17.1	$0.45	38	5.8 s
128	▼ 2	Qwen3 235B A22B (Non-reasoning)OpenAlibaba	17.0	$0.79	61	2.8 s
129	▼ 2	Magistral Small 1OpenMistral	16.8	—	—	—
130	▼ 2	EXAONE 4.0 32B (Reasoning)OpenLG AI Research	16.7	—	—	—
131	▼ 2	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.7	$0.66	108	2.5 s
132	▼ 2	Qwen3 32B (Reasoning)OpenAlibaba	16.5	$0.28	86	2.7 s
133	▼ 2	DeepSeek V3 (Dec '24)OpenDeepSeek	16.5	$0.52	—	—
134	▼ 2	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	—	—	—
135	▼ 2	Qwen3.5 2B (Reasoning)OpenAlibaba	16.3	$0.040	—	—
136	▼ 2	Qwen3 14B (Reasoning)OpenAlibaba	16.2	$0.73	58	2.8 s
137	▼ 2	Nanbeige4.1-3BOpenNanbeige	16.1	—	—	—
138	▼ 2	Qwen3 VL 30B A3B InstructOpenAlibaba	16.0	$0.30	111	2.2 s
139	▼ 2	Ministral 3 14BOpenMistral	16.0	$0.20	67	0.7 s
140	▼ 2	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	42	1.7 s
141	▼ 2	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	—	—	—
142	▼ 2	Falcon-H1R-7BOpenTII UAE	15.8	—	—	—
143	▼ 2	Ling-flash-2.0OpenInclusionAI	15.7	$0.25	82	2.4 s
144	▼ 2	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	86	2.1 s
145	▼ 2	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.37	28	3.6 s
146	▼ 2	Step3 VL 10BOpenStepFun	15.5	—	—	—
147	▼ 2	Qwen3 30B A3B (Reasoning)OpenAlibaba	15.3	$0.18	60	2.5 s
148	▼ 2	Devstral Small (Jul '25)OpenMistral	15.2	$0.15	223	0.7 s
149	▼ 2	Gemma 4 E2B (Reasoning)OpenGoogle	15.2	—	—	—
150	▼ 2	QwQ 32B-PreviewOpenAlibaba	15.2	—	—	—
151	▼ 2	GLM-4.5V (Reasoning)OpenZ AI	15.1	$0.90	38	2.2 s
152	▼ 2	Mistral Large 2 (Nov '24)OpenMistral	15.1	$3.0	32	2.0 s
153	▼ 2	Mistral Small 3.2OpenMistral	15.1	$0.13	98	0.7 s
154	▼ 2	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	41	2.6 s
155	▼ 2	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.21	105	2.1 s
156	▼ 2	ERNIE 4.5 300B A47BOpenBaidu	15.0	$0.49	23	3.5 s
157	▼ 2	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA	14.9	$0.30	—	—
158	▼ 2	Ministral 3 8BOpenMistral	14.8	$0.15	85	0.7 s
159	▼ 2	Gemma 4 E4B (Non-reasoning)OpenGoogle	14.8	—	—	—
160	▼ 2	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA	14.8	$0.070	115	0.6 s
161	▼ 2	Granite 4.1 30BOpenIBM	14.7	—	—	—
162	▼ 2	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
163	▼ 2	Qwen3.5 2B (Non-reasoning)OpenAlibaba	14.7	$0.040	327	0.4 s
164	▼ 2	Llama Nemotron Super 49B v1.5 (Non-reasoning)OpenNVIDIA	14.6	$0.18	49	1.3 s
165	▼ 2	Qwen3 32B (Non-reasoning)OpenAlibaba	14.5	$0.26	89	2.7 s
166	▼ 2	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.62	80	1.7 s
167	▼ 2	Mistral Small 3.1OpenMistral	14.5	$0.14	140	0.7 s
168	▼ 2	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
169	▼ 2	Kimi Linear 48B A3B InstructOpenKimi	14.4	—	—	—
170	▼ 2	Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)OpenNVIDIA	14.3	—	—	—
171	▼ 2	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	120	2.3 s
172	▼ 2	Qwen3 4B (Reasoning)OpenAlibaba	14.2	$0.40	95	2.4 s
173	▼ 2	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	—	—
174	▼ 2	Pixtral LargeOpenMistral	14.0	$3.0	52	1.7 s
175	▼ 2	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
176	▼ 2	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	—	—	—
177	▼ 2	Llama 4 ScoutOpenMeta	13.5	$0.29	119	0.9 s
178	▼ 2	Command AOpenCohere	13.5	$4.4	37	2.3 s
179	▼ 2	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	287	0.5 s
180	▼ 2	Qwen2.5 Instruct 32BOpenAlibaba	13.2	—	—	—
181	▼ 2	Qwen3 8B (Reasoning)OpenAlibaba	13.2	$0.37	39	3.7 s
182	▼ 2	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)OpenNVIDIA	13.2	$0.088	74	0.5 s
183	▼ 2	NVIDIA Nemotron Nano 9B V2 (Non-reasoning)OpenNVIDIA	13.2	$0.086	128	1.1 s
184	▼ 2	Mistral Large 2 (Jul '24)OpenMistral	13.0	$3.0	—	—
185	▼ 2	Qwen3 4B 2507 InstructOpenAlibaba	12.9	—	—	—
186	▼ 2	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	—	—	—
187	▼ 2	Qwen3 14B (Non-reasoning)OpenAlibaba	12.8	$0.38	58	2.8 s
188	▼ 2	GLM-4.5V (Non-reasoning)OpenZ AI	12.7	$0.90	33	25 s
189	▼ 2	Mistral Small 3OpenMistral	12.7	$0.10	126	0.8 s
190	▼ 2	MiniCPM-V 4.6 1.3BOpenOpenBMB	12.7	—	—	—
191	▼ 2	Qwen3 30B A3B (Non-reasoning)OpenAlibaba	12.5	$0.13	68	2.4 s
192	▼ 2	DeepSeek-V2.5 (Dec '24)OpenDeepSeek	12.5	—	—	—
193	▼ 2	Qwen3 4B (Non-reasoning)OpenAlibaba	12.5	$0.19	96	2.5 s
194	▼ 2	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	32	1.9 s
195	▼ 2	Granite 4.1 8BOpenIBM	12.4	$0.063	114	0.8 s
196	▼ 2	Sarvam 30B (high)OpenSarvam	12.3	$0.000	262	1.9 s
197	▼ 2	DeepSeek-V2.5OpenDeepSeek	12.3	—	—	—
198	▼ 2	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	—	—	—
199	▼ 2	Gemma 4 E2B (Non-reasoning)OpenGoogle	12.1	—	—	—
200	▼ 2	R1 1776OpenPerplexity	12.0	—	—	—
201	▼ 2	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$1.4	58	1.3 s
201	▼ 2	Solar MiniOpenUpstage	11.9	$0.15	—	—
203	▼ 2	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	155	0.8 s
204	▼ 2	Grok-1OpenxAI	11.7	—	—	—
205	▼ 2	Qwen2 Instruct 72BOpenAlibaba	11.7	—	—	—
206	▼ 2	EXAONE 4.0 32B (Non-reasoning)OpenLG AI Research	11.7	—	—	—
207	▼ 2	Ministral 3 3BOpenMistral	11.2	$0.10	150	0.5 s
208	▼ 2	Jamba 1.7 LargeOpenAI21 Labs	10.9	$3.5	57	1.5 s
209	▼ 2	Granite 4.0 H SmallOpenIBM	10.8	$0.11	388	10 s
210	▼ 2	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
211	▼ 2	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	96	2.0 s
212	▼ 2	Qwen3 8B (Non-reasoning)OpenAlibaba	10.6	$0.19	40	3.8 s
213	▼ 2	DeepSeek-Coder-V2OpenDeepSeek	10.6	—	—	—
214	▼ 2	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	58	1.5 s
215	▼ 2	Qwen3.5 0.8B (Reasoning)OpenAlibaba	10.5	$0.020	—	—
216	▼ 2	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	209	0.6 s
217	▼ 2	Phi-4OpenMicrosoft	10.4	$0.22	18	2.5 s
218	▼ 2	Gemma 3 27B InstructOpenGoogle	10.3	$0.14	—	—
219	▼ 2	Mistral Small (Sep '24)OpenMistral	10.2	$0.30	133	0.8 s
220	▼ 2	Phi-3 Mini Instruct 3.8BOpenMicrosoft	10.1	—	—	—
221	▼ 2	NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)OpenNVIDIA	10.1	$0.30	236	1.1 s
222	▼ 2	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
223	▼ 2	Phi-4 Multimodal InstructOpenMicrosoft	10.0	$0.000	16	0.9 s
224	▼ 2	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	—	—	—
225	▼ 2	Qwen3.5 0.8B (Non-reasoning)OpenAlibaba	9.9	$0.020	117	0.4 s
226	▼ 2	Mixtral 8x22B InstructOpenMistral	9.8	—	—	—
227	▼ 2	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
228	▼ 2	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.15	51	1.2 s
229	▼ 2	Jamba Reasoning 3BOpenAI21 Labs	9.6	—	—	—
230	▼ 2	Qwen3 VL 4B InstructOpenAlibaba	9.6	—	—	—
231	▼ 2	Qwen1.5 Chat 110BOpenAlibaba	9.5	—	—	—
232	▼ 2	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
233	▼ 2	Ling-mini-2.0OpenInclusionAI	9.2	—	—	—
234	▼ 2	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	—	—	—
235	▼ 2	DeepSeek-V2-ChatOpenDeepSeek	9.1	—	—	—
236	▼ 2	Llama 3 Instruct 70BOpenMeta	8.9	$1.2	—	—
237	▼ 2	Arctic InstructOpenSnowflake	8.8	—	—	—
237	▼ 2	Qwen Chat 72BOpenAlibaba	8.8	—	—	—
239	▼ 2	Gemma 3 12B InstructOpenGoogle	8.8	$0.14	—	—
240	▼ 2	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.25	48	0.8 s
241	▼ 2	Granite 4.1 3BOpenIBM	8.5	—	—	—
242	▼ 2	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	—	—	—
243	▼ 2	Sarvam M (Reasoning)OpenSarvam	8.4	$0.000	—	—
244	▼ 2	Phi-4 Mini InstructOpenMicrosoft	8.4	$0.000	—	—
245	▼ 2	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	—	—	—
245	▼ 2	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
247	▼ 2	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
248	▼ 2	Command-R+ (Apr '24)OpenCohere	8.3	$6.0	—	—
249	▼ 2	OpenChat 3.5 (1210)OpenOpenChat	8.3	—	—	—
250	▼ 2	DBRX InstructOpenDatabricks	8.3	—	—	—
251	▼ 2	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research	8.3	—	—	—
252	▼ 2	Exaone 4.0 1.2B (Non-reasoning)OpenLG AI Research	8.1	—	—	—
253	▼ 2	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
254	▼ 2	Jamba 1.7 MiniOpenAI21 Labs	8.1	—	—	—
255	▼ 2	LFM2 2.6BOpenLiquid AI	8.0	$0.000	—	—
256	▼ 2	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
257	▼ 2	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
258	▼ 2	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
259	▼ 2	Qwen3 1.7B (Reasoning)OpenAlibaba	8.0	$0.40	126	1.9 s
260	▼ 2	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	182	0.8 s
261	▼ 2	Mixtral 8x7B InstructOpenMistral	7.7	$0.51	—	—
262	▼ 2	Gemma 3 270MOpenGoogle	7.7	—	—	—
263	▼ 2	Apertus 70B InstructOpenSwiss AI Initiative	7.7	$1.3	—	—
264	▼ 2	Granite 4.0 MicroOpenIBM	7.7	—	—	—
265	▼ 2	Command-R (Mar '24)OpenCohere	7.4	$0.75	—	—
265	▼ 2	Llama 65BOpenMeta	7.4	—	—	—
265	▼ 2	Mistral 7B InstructOpenMistral	7.4	$0.21	84	0.7 s
265	▼ 2	Qwen Chat 14BOpenAlibaba	7.4	—	—	—
269	▼ 2	Granite 4.0 1BOpenIBM	7.3	—	—	—
270	▼ 2	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
271	▼ 2	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	343	27 s
272	▼ 2	Qwen3 1.7B (Non-reasoning)OpenAlibaba	6.8	$0.19	127	1.8 s
273	▼ 2	Qwen3 0.6B (Reasoning)OpenAlibaba	6.5	$0.40	195	1.7 s
274	▼ 2	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
275	▼ 2	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	57	1.3 s
276	▼ 2	LFM2 1.2BOpenLiquid AI	6.3	$0.000	—	—
277	▼ 2	Gemma 3 4B InstructOpenGoogle	6.3	$0.050	—	—
278	▼ 2	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	87	0.9 s
279	▼ 2	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	—	—
280	▼ 2	Granite 4.0 350MOpenIBM	6.1	—	—	—
281	▼ 2	Apertus 8B InstructOpenSwiss AI Initiative	5.9	$0.13	—	—
282	▼ 2	Qwen3 0.6B (Non-reasoning)OpenAlibaba	5.7	$0.19	194	1.7 s
283	▼ 2	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	—	—
284	▼ 2	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
285	▼ 2	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
286	▼ 2	Tiny Aya GlobalOpenCohere	4.7	$0.000	—	—

236 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