Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Kimi K3 (max)OpenKimi · 1 more variant	59.7	$6.0	40	3.1 s
2	New	GLM-5.3 (max)OpenZ AI	59.5	$2.2	74	1.6 s
3	▼ 1	Qwen3.8 2.4T A95BOpenAlibaba	57.7	$3.0	37	2.8 s
4	New	GLM-5.3-FlashOpenZ AI	57.5	$0.24	45	1.6 s
5	New	Qwen3.8-Flash-NextOpenAlibaba	55.8	$0.23	87	2.6 s
6	▼ 3	DeepSeek V4 Pro 0813 (Reasoning, Max Effort)OpenDeepSeek · 3 more variants	53.2	$2.0	49	1.5 s
7	▼ 3	GLM-5.2 (max)OpenZ AI · 1 more variant	52.6	$2.2	70	1.7 s
8	▼ 3	Qwen3.8 27B (xhigh)OpenAlibaba · 3 more variants	52.0	$1.1	47	3.9 s
9	▼ 3	DeepSeek V4 Flash 0731 (Reasoning, Max Effort)OpenDeepSeek · 3 more variants	51.8	$0.66	101	1.6 s
10	▼ 3	Motif 3OpenMotif Technologies	47.4	—	—	—
11	▼ 3	MiniMax-M3OpenMiniMax	45.4	$0.52	145	1.1 s
12	▼ 3	Kimi K2.6OpenKimi · 1 more variant	45.1	$1.7	35	2.8 s
13	▼ 3	Kimi K2.7 CodeOpenKimi	43.0	$1.7	45	2.8 s
14	▼ 3	MiMo-V2.5-ProOpenXiaomi · 1 more variant	42.9	$0.54	35	4.4 s
15	▼ 3	Inkling (xhigh)OpenThinking Machines	42.3	$1.8	77	2.4 s
16	▼ 3	Hy3OpenTencent	42.2	$0.24	96	2.7 s
17	▼ 3	Nex-N2-ProOpenNex AGI	41.7	$1.0	130	1.7 s
18	▼ 3	Inkling SmallOpenThinking Machines	41.2	$0.52	48	2.6 s
19	▼ 3	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	41.0	$2.1	56	1.7 s
20	▼ 3	GLM-5 (Reasoning)OpenZ AI · 1 more variant	40.6	$1.6	75	1.4 s
21	New	Agnes 2.5 Pro AlphaOpenSapiens AI	39.7	$0.56	134	3.2 s
22	▼ 4	MiniMax-M2.7OpenMiniMax	38.9	$0.52	70	1.5 s
23	▼ 4	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	38.3	$1.1	70	5.3 s
24	▼ 4	MiMo-V2.5OpenXiaomi	38.0	$0.18	64	3.0 s
25	▼ 4	Ling 3.0 FlashOpenInclusionAI	37.8	$0.11	359	2.7 s
26	▼ 4	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	37.7	$1.4	54	3.7 s
27	▼ 4	Solar Open2 250BOpenUpstage	37.4	—	—	—
28	▼ 4	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	36.0	$1.2	84	2.7 s
29	▼ 4	Muse Glimmer (high)OpenMeta	35.1	$0.58	102	0.9 s
30	▼ 4	A.X-K2OpenSK Telecom	35.0	—	—	—
31	▼ 4	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	34.6	$0.83	77	5.6 s
32	▼ 4	MiniMax-M2.5OpenMiniMax	34.5	$0.52	100	1.7 s
33	▼ 4	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	34.5	$1.0	92	1.2 s
34	▼ 4	Hy3-preview (Reasoning)OpenTencent · 1 more variant	34.4	$0.100	—	—
35	▼ 4	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	34.3	$1.4	79	2.2 s
36	▼ 4	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	34.0	—	—	—
37	▼ 4	G9v3-39A5BOpenAI9Stars	34.0	$0.000	—	—
38	▼ 4	LongCat 2.0OpenLongCat	34.0	$1.3	39	2.8 s
39	▼ 4	Kimi K2 ThinkingOpenKimi	33.5	$1.1	123	1.3 s
40	▼ 4	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	32.8	$1.1	130	2.3 s
41	▼ 4	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	32.8	$0.32	—	—
42	▼ 4	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	32.1	$0.84	122	2.0 s
43	▼ 4	MiniMax-M2.1OpenMiniMax	32.1	$0.52	92	1.7 s
44	▼ 4	Ring-2.6-1TOpenInclusionAI	31.7	$0.85	122	3.9 s
45	▼ 4	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	31.4	$1.9	—	—
46	▼ 4	K-EXAONE 2.0OpenLG AI Research	31.0	—	—	—
47	▼ 4	Step 3.7 FlashOpenStepFun	30.9	$0.44	96	2.9 s
48	▼ 4	Mistral Medium 3.5OpenMistral	30.4	$3.0	150	2.2 s
49	▼ 4	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	29.9	$0.69	146	2.1 s
50	▼ 4	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	29.7	$0.000	36	1.1 s
51	▼ 4	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	29.3	$0.96	49	2.6 s
52	▼ 4	MiniMax-M2OpenMiniMax	28.9	$0.52	99	1.7 s
53	▼ 4	Ling-2.6-1TOpenInclusionAI	26.6	$0.85	—	—
54	▼ 4	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	26.1	$0.18	—	—
55	▼ 4	Step 3.5 FlashOpenStepFun	26.0	$0.15	223	1.1 s
56	▼ 4	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	25.9	$0.32	—	—
57	▼ 4	Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	25.7	$0.35	140	1.8 s
58	▼ 4	Ling 3.0 TinyOpenInclusionAI	24.5	$0.000	169	2.5 s
59	▼ 4	gpt-oss-120b (high)OpenOpenAI · 1 more variant	24.1	$0.26	188	0.8 s
60	▼ 4	Kimi K2 0905OpenKimi · 1 more variant	24.0	$1.1	40	1.1 s
61	New	Granite 4.2 30BOpenIBM	23.7	$0.28	75	0.8 s
62	▼ 5	Nemotron 3.5 LightningOpenNVIDIA	23.6	$0.11	303	0.6 s
63	▼ 5	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	23.3	$0.15	91	1.1 s
64	▼ 5	Command A+OpenCohere · 1 more variant	22.8	$0.000	242	0.4 s
65	▼ 5	DeepSeek V3.2 SpecialeOpenDeepSeek	22.6	—	—	—
66	▼ 5	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	22.5	—	—	—
67	▼ 5	Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant	22.2	$0.15	110	2.5 s
68	▼ 5	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	21.8	$0.15	86	1.6 s
69	▼ 5	Apriel-v1.5-15B-ThinkerOpenServiceNow	21.6	$0.000	—	—
70	▼ 5	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	21.4	$0.85	—	—
71	▼ 5	Qwen3 Coder NextOpenAlibaba	21.3	$0.56	147	1.0 s
72	▼ 5	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	20.9	$1.3	57	2.9 s
73	▼ 5	Apriel-v1.6-15B-ThinkerOpenServiceNow	20.8	$0.000	—	—
74	▼ 5	EXAONE 4.5 33BOpenLG AI Research	20.5	—	—	—
75	▼ 5	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	20.4	$0.060	26	0.7 s
76	▼ 5	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	20.4	$1.8	—	—
77	▼ 5	North Mini CodeOpenCohere	20.2	$0.000	107	0.3 s
78	▼ 5	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	19.9	$0.75	69	2.7 s
79	▼ 5	GLM-4.5 (Reasoning)OpenZ AI	19.7	—	—	—
80	▼ 5	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	19.7	$0.26	165	0.8 s
81	New	Granite 4.2 8BOpenIBM	19.6	$0.11	145	0.6 s
82	▼ 6	Devstral 2OpenMistral	19.2	$0.000	45	2.3 s
83	▼ 6	Trinity Large ThinkingOpenArcee AI	18.7	$0.40	274	1.4 s
84	▼ 6	Seed-OSS-36B-InstructOpenByteDance Seed	18.5	$0.30	35	2.7 s
85	▼ 6	Qwen3 235B A22B 2507 InstructOpenAlibaba	18.4	$0.40	59	2.4 s
86	▼ 6	HyperNova 60B 2605OpenMultiverse Computing	18.3	$0.065	345	1.0 s
87	▼ 6	Qwen3 Coder 480B A35B InstructOpenAlibaba	18.2	$3.0	64	2.9 s
88	▼ 6	Qwen3 VL 32B (Reasoning)OpenAlibaba	18.1	$0.28	89	2.6 s
89	▼ 6	MiniMax M1 80kOpenMiniMax	17.9	$0.96	—	—
90	▼ 6	Nemotron Cascade 2 30B A3BOpenNVIDIA	17.8	—	—	—
91	▼ 6	Devstral Small 2OpenMistral	17.7	$0.000	133	2.2 s
92	▼ 6	K2 Think V2OpenMBZUAI Institute of Foundation Models	17.4	—	—	—
93	▼ 6	LongCat Flash LiteOpenLongCat	17.4	—	—	—
94	▼ 6	HyperCLOVA X SEED Think (32B)OpenNaver	17.2	—	—	—
95	▼ 6	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	16.9	$0.45	81	3.0 s
96	▼ 6	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	16.9	$0.41	197	2.3 s
97	▼ 6	GLM-4.5-AirOpenZ AI	16.7	$0.37	39	2.5 s
98	▼ 6	Ring-1TOpenInclusionAI	16.3	—	—	—
99	▼ 6	G9v3-3BOpenAI9Stars	16.2	$0.000	—	—
100	▼ 6	Mistral Large 3OpenMistral	15.9	$0.75	74	1.1 s
101	▼ 6	INTELLECT-3OpenPrime Intellect	15.7	—	—	—
102	▼ 6	Solar Open 100B (Reasoning)OpenUpstage	15.2	—	—	—
103	▼ 6	DeepSeek V3 0324OpenDeepSeek · 1 more variant	15.2	$0.48	—	—
104	▼ 6	gpt-oss-20b (high)OpenOpenAI · 1 more variant	15.2	$0.093	125	1.0 s
105	▼ 6	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	15.0	$0.13	324	1.0 s
106	▼ 6	Mistral Small 3.1OpenMistral	14.9	$0.15	146	0.8 s
107	▼ 6	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	14.6	$0.75	127	2.4 s
108	▼ 6	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	14.5	$0.088	292	1.2 s
109	▼ 6	Llama 4 MaverickOpenMeta	14.5	$0.42	98	0.8 s
110	▼ 6	MiniMax M1 40kOpenMiniMax	14.5	—	—	—
111	▼ 6	Qwen3 VL 235B A22B InstructOpenAlibaba	14.4	$0.70	50	2.7 s
112	New	Granite 4.2 3BOpenIBM	14.3	$0.053	220	0.4 s
113	▼ 7	K2-V2 (high)OpenMBZUAI Institute of Foundation Models · 2 more variants	14.2	—	—	—
114	▼ 7	Ling 2.6 FlashOpenInclusionAI	14.2	—	—	—
115	▼ 7	Qwen3 Next 80B A3B InstructOpenAlibaba	13.8	$0.41	180	2.2 s
116	▼ 7	Tri-21B-think PreviewOpenTrillion Labs	13.6	—	—	—
117	▼ 7	Qwen3 Coder 30B A3B InstructOpenAlibaba	13.6	$0.90	93	2.6 s
118	▼ 7	DiffusionGemma 26B A4BOpenGoogle	13.5	—	—	—
119	▼ 7	QwQ 32BOpenAlibaba	13.4	$0.75	—	—
120	▼ 7	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	13.4	$0.75	113	2.1 s
121	▼ 7	Ling-1TOpenInclusionAI	12.7	—	—	—
122	▼ 7	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	12.4	$0.40	35	9.3 s
123	▼ 7	Tri-21B-ThinkOpenTrillion Labs	12.3	—	—	—
124	▼ 7	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	12.2	—	—	—
125	▼ 7	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	12.2	$0.040	44	0.9 s
126	▼ 7	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	11.9	—	—	—
127	▼ 7	MiniCPM5-1B (Reasoning)OpenOpenBMB · 1 more variant	11.9	—	—	—
128	▼ 7	Sarvam 105B (high)OpenSarvam	11.9	$0.074	—	—
129	▼ 7	Devstral Small (May '25)OpenMistral · 1 more variant	11.8	—	—	—
130	▼ 7	Magistral Small 1.2OpenMistral	11.5	$0.75	—	—
131	▼ 7	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	11.4	$0.28	104	2.5 s
132	▼ 7	Ministral 3 14BOpenMistral	11.2	$0.20	100	0.8 s
133	▼ 7	Nanbeige4.1-3BOpenNanbeige	11.0	—	—	—
134	▼ 7	LFM2.5-2.6BOpenLiquid AI	11.0	$0.000	—	—
135	▼ 7	Qwen3 VL 32B InstructOpenAlibaba	11.0	$0.28	63	2.7 s
136	▼ 7	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	11.0	—	—	—
137	▼ 7	Mistral Small 3.2OpenMistral	10.7	$0.15	139	0.8 s
138	▼ 7	Magistral Small 1OpenMistral	10.6	—	—	—
139	▼ 7	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	10.5	—	—	—
140	▼ 7	Qwen3 VL 8B (Reasoning)OpenAlibaba	10.5	$0.66	115	2.4 s
141	▼ 7	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	10.4	$1.3	62	2.8 s
142	▼ 7	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	10.3	—	—	—
143	▼ 7	Llama 4 ScoutOpenMeta	10.3	$0.30	132	0.8 s
144	▼ 7	Qwen3 VL 30B A3B InstructOpenAlibaba	9.9	$0.35	112	2.2 s
145	▼ 7	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research · 1 more variant	9.9	$0.20	86	1.5 s
146	▼ 7	DeepSeek R1 Distill Llama 70BOpenDeepSeek	9.8	$0.80	26	1.1 s
147	▼ 7	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	9.7	—	—	—
148	▼ 7	Falcon-H1R-7BOpenTII UAE	9.7	—	—	—
149	▼ 7	Ling-flash-2.0OpenInclusionAI	9.6	$0.25	54	2.7 s
150	▼ 7	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	9.5	—	—	—
151	▼ 7	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	9.5	$0.43	100	1.9 s
152	▼ 7	Qwen2.5 Instruct 72BOpenAlibaba	9.4	$0.48	—	—
153	▼ 7	Step3 VL 10BOpenStepFun	9.3	—	—	—
154	▼ 7	Llama 3.3 Instruct 70BOpenMeta	9.3	$0.67	89	1.6 s
155	▼ 7	QwQ 32B-PreviewOpenAlibaba	9.1	—	—	—
156	▼ 7	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	9.0	$0.90	84	1.9 s
157	▼ 7	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	9.0	—	—	—
158	▼ 7	Ministral 3 8BOpenMistral	9.0	$0.15	127	0.7 s
159	▼ 7	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	8.9	$0.90	52	2.4 s
160	▼ 7	Qwen3 30B A3B 2507 InstructOpenAlibaba	8.9	$0.35	150	1.9 s
161	▼ 7	ERNIE 4.5 300B A47BOpenBaidu	8.9	$0.49	—	—
162	▼ 7	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research · 1 more variant	8.8	$1.5	38	2.5 s
163	▼ 7	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	8.8	$0.30	29	11 s
164	▼ 7	Granite 4.1 30BOpenIBM	8.7	—	—	—
165	▼ 7	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	8.7	$0.070	227	3.8 s
166	▼ 7	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	8.6	—	—	—
167	▼ 7	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	8.4	—	—	—
168	▼ 7	Kimi Linear 48B A3B InstructOpenKimi	8.4	—	—	—
169	▼ 7	Llama 3.1 Instruct 405BOpenMeta	8.3	—	—	—
170	▼ 7	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	8.3	$0.66	40	3.8 s
171	▼ 7	Qwen3 VL 8B InstructOpenAlibaba	8.2	$0.31	119	2.2 s
172	▼ 7	LFM2.5-8B-A1BOpenLiquid AI	8.1	$0.000	336	2.2 s
173	▼ 7	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	8.1	—	—	—
174	▼ 7	Ring-flash-2.0OpenInclusionAI	8.0	$0.25	—	—
175	▼ 7	Pixtral LargeOpenMistral	8.0	—	—	—
176	▼ 7	Olmo 3.1 32B ThinkOpenAllen Institute for AI	7.9	$0.000	—	—
177	▼ 7	Grok 2 (Dec '24)OpenSpaceXAI	7.8	—	—	—
178	▼ 7	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.7	—	—	—
179	▼ 7	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	7.4	—	—	—
180	▼ 7	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	7.4	$1.2	33	13 s
181	▼ 7	Llama 3.1 Instruct 8BOpenMeta	7.4	$0.028	139	0.8 s
182	▼ 7	Gemma 3 27B InstructOpenGoogle	7.4	$0.000	—	—
183	▼ 7	Qwen2.5 Instruct 32BOpenAlibaba	7.2	—	—	—
184	▼ 7	Ministral 3 3BOpenMistral	7.1	$0.10	199	0.6 s
185	▼ 7	Qwen3 4B 2507 InstructOpenAlibaba	6.9	—	—	—
186	▼ 7	Qwen2.5 Coder Instruct 32BOpenAlibaba	6.9	—	—	—
187	▼ 7	Mistral Small 3OpenMistral	6.7	$0.15	145	0.9 s
188	▼ 7	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	6.5	—	—	—
189	▼ 7	Llama 3.1 Instruct 70BOpenMeta	6.5	$0.56	56	1.6 s
190	▼ 7	Granite 4.1 8BOpenIBM	6.4	$0.063	110	0.7 s
191	▼ 7	Sarvam 30B (high)OpenSarvam	6.4	$0.047	—	—
192	▼ 7	Olmo 3.1 32B InstructOpenAllen Institute for AI	6.2	—	—	—
193	▼ 7	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.2	—	—	—
194	▼ 7	Olmo 3 32B ThinkOpenAllen Institute for AI	6.1	—	—	—
195	▼ 7	R1 1776OpenPerplexity	6.0	—	—	—
196	▼ 7	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.0	—	—	—
196	▼ 7	Solar MiniOpenUpstage	6.0	$0.15	—	—
198	▼ 7	Grok-1OpenSpaceXAI	5.8	—	—	—
199	▼ 7	Qwen2 Instruct 72BOpenAlibaba	5.7	—	—	—
200	▼ 7	Phi-4 Mini InstructOpenMicrosoft	5.7	$0.000	45	0.9 s
201	▼ 7	Gemma 3 12B InstructOpenGoogle	5.5	$0.000	—	—
202	▼ 7	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	5.2	—	—	—
203	▼ 7	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	5.0	—	—	—
204	▼ 7	Jamba 1.7 LargeOpenAI21 Labs	5.0	—	—	—
205	▼ 7	Granite 4.0 H SmallOpenIBM	4.9	$0.11	30	17 s
206	▼ 7	Jamba 1.5 LargeOpenAI21 Labs	4.8	$3.5	—	—
207	▼ 7	Qwen3 Omni 30B A3B InstructOpenAlibaba	4.8	$0.43	94	1.9 s
208	▼ 7	Hermes 3 - Llama-3.1 70BOpenNous Research	4.8	$0.70	34	2.0 s
209	▼ 7	DeepSeek-Coder-V2OpenDeepSeek	4.7	—	—	—
210	▼ 7	OLMo 2 32BOpenAllen Institute for AI	4.7	—	—	—
211	▼ 7	Jamba 1.6 LargeOpenAI21 Labs	4.7	—	—	—
212	▼ 7	LFM2 24B A2BOpenLiquid AI	4.6	—	—	—
213	▼ 7	Phi-4OpenMicrosoft	4.6	$0.22	42	2.5 s
214	▼ 7	Granite 4.1 3BOpenIBM	4.4	—	—	—
215	▼ 7	Mistral Small (Sep '24)OpenMistral	4.3	$0.30	152	0.8 s
216	▼ 7	Phi-3 Mini Instruct 3.8BOpenMicrosoft	4.3	—	—	—
217	▼ 7	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	4.2	—	—	—
218	▼ 7	Phi-4 Multimodal InstructOpenMicrosoft	4.2	$0.000	18	0.8 s
219	▼ 7	Qwen2.5 Coder Instruct 7BOpenAlibaba	4.1	—	—	—
220	▼ 7	Mixtral 8x22B InstructOpenMistral	4.0	—	—	—
221	▼ 7	Llama 2 Chat 7BOpenMeta	3.9	$0.10	—	—
222	▼ 7	Llama 3.2 Instruct 3BOpenMeta	3.9	—	—	—
223	▼ 7	MiniCPM-V 4.6 1.3BOpenOpenBMB	3.8	—	—	—
224	▼ 7	Jamba Reasoning 3BOpenAI21 Labs	3.8	—	—	—
225	▼ 7	Qwen3 VL 4B InstructOpenAlibaba	3.7	—	—	—
226	▼ 7	Qwen1.5 Chat 110BOpenAlibaba	3.7	—	—	—
227	▼ 7	Reka Flash 3OpenReka AI	3.7	$0.35	—	—
228	▼ 7	Olmo 3 7B ThinkOpenAllen Institute for AI	3.6	—	—	—
229	▼ 7	OLMo 2 7BOpenAllen Institute for AI	3.5	—	—	—
230	▼ 7	Molmo 7B-DOpenAllen Institute for AI	3.4	—	—	—
231	▼ 7	Ling-mini-2.0OpenInclusionAI	3.4	—	—	—
232	▼ 7	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	3.3	—	—	—
233	▼ 7	DeepSeek-V2-ChatOpenDeepSeek	3.3	—	—	—
234	▼ 7	Llama 3 Instruct 70BOpenMeta	3.1	$1.2	—	—
235	▼ 7	Arctic InstructOpenSnowflake	3.0	—	—	—
235	▼ 7	Qwen Chat 72BOpenAlibaba	3.0	—	—	—
237	▼ 7	Llama 3.2 Instruct 11B (Vision)OpenMeta	3.0	$0.35	29	1.1 s
238	▼ 7	DeepSeek Coder V2 Lite InstructOpenDeepSeek	2.7	—	—	—
239	▼ 7	Sarvam M (Reasoning)OpenSarvam	2.6	$0.000	—	—
240	▼ 7	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	2.6	—	—	—
240	▼ 7	Llama 2 Chat 70BOpenMeta	2.6	—	—	—
242	▼ 7	Llama 2 Chat 13BOpenMeta	2.6	—	—	—
243	▼ 7	Command-R+ (Apr '24)OpenCohere · 1 more variant	2.6	$6.0	—	—
244	▼ 7	OpenChat 3.5 (1210)OpenOpenChat	2.6	—	—	—
245	▼ 7	DBRX InstructOpenDatabricks	2.6	—	—	—
246	▼ 7	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	2.5	—	—	—
247	▼ 7	Olmo 3 7B InstructOpenAllen Institute for AI	2.4	$0.13	—	—
248	▼ 7	LFM2.5-1.2B-ThinkingOpenLiquid AI	2.3	—	—	—
249	▼ 7	Jamba 1.7 MiniOpenAI21 Labs	2.3	—	—	—
250	▼ 7	LFM2 2.6BOpenLiquid AI	2.3	—	—	—
251	▼ 7	LFM2.5-1.2B-InstructOpenLiquid AI	2.3	—	—	—
252	▼ 7	Jamba 1.5 MiniOpenAI21 Labs	2.3	$0.25	—	—
253	▼ 7	Granite 4.0 H 1BOpenIBM	2.2	—	—	—
254	▼ 7	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	2.2	—	—	—
255	▼ 7	Jamba 1.6 MiniOpenAI21 Labs	2.1	—	—	—
256	▼ 7	Mixtral 8x7B InstructOpenMistral	2.0	$0.51	—	—
257	▼ 7	Gemma 3 270MOpenGoogle	2.0	—	—	—
258	▼ 7	Apertus 70B InstructOpenSwiss AI Initiative	2.0	$1.3	—	—
259	▼ 7	Granite 4.0 MicroOpenIBM	2.0	—	—	—
260	▼ 7	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	1.9	—	—	—
261	▼ 7	Llama 65BOpenMeta	1.7	—	—	—
261	▼ 7	Mistral 7B InstructOpenMistral	1.7	$0.25	126	0.7 s
261	▼ 7	Qwen Chat 14BOpenAlibaba	1.7	—	—	—
264	▼ 7	Granite 4.0 1BOpenIBM	1.6	—	—	—
265	▼ 7	Molmo2-8BOpenAllen Institute for AI	1.6	—	—	—
266	▼ 7	LFM2 8B A1BOpenLiquid AI	1.3	—	—	—
267	▼ 7	Granite 3.3 8B (Non-reasoning)OpenIBM	1.3	$0.085	15	27 s
268	▼ 7	Apertus 8B InstructOpenSwiss AI Initiative	1.0	$0.13	—	—
268	▼ 7	Gemma 3 1B InstructOpenGoogle	1.0	$0.000	—	—
268	▼ 7	Gemma 3 4B InstructOpenGoogle	1.0	$0.000	—	—
268	▼ 7	Gemma 3n E2B InstructOpenGoogle	1.0	$0.000	—	—
268	▼ 7	Gemma 3n E4B InstructOpenGoogle	1.0	$0.075	—	—
268	▼ 7	Granite 4.0 350MOpenIBM	1.0	—	—	—
268	▼ 7	Granite 4.0 H 350MOpenIBM	1.0	—	—	—
268	▼ 7	LFM2 1.2BOpenLiquid AI	1.0	—	—	—
268	▼ 7	LFM2.5-VL-1.6BOpenLiquid AI	1.0	$0.000	355	1.5 s
268	▼ 7	Llama 3 Instruct 8BOpenMeta	1.0	$0.070	—	—
268	▼ 7	Llama 3.2 Instruct 1BOpenMeta	1.0	—	—	—
268	▼ 7	Qwen3 0.6B (Non-reasoning)OpenAlibaba · 1 more variant	1.0	—	—	—
268	▼ 7	Tiny Aya GlobalOpenCohere	1.0	$0.000	—	—

230 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