Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	GLM-5.3 (max)OpenZ AI	44.8	$2.2	72	2.9 s
2	—	Kimi K3 (max)OpenKimi · 1 more variant	43.6	$6.0	43	3.7 s
3	—	GLM 5.3 FlashOpenZ AI	41.8	$0.24	95	2.5 s
4	—	Qwen3.8 2.4T A95BOpenAlibaba	39.9	$3.0	40	3.0 s
5	—	Qwen3.8-Flash-NextOpenAlibaba	39.8	$0.23	61	2.8 s
6	—	DeepSeek V4.1 Flash (Reasoning, Max Effort)OpenDeepSeek	39.5	$0.52	229	0.9 s
7	—	DeepSeek V4 Pro 0813 (Reasoning, Max Effort)OpenDeepSeek · 3 more variants	36.0	$2.0	105	1.7 s
8	—	DeepSeek V4 Flash 0731 (Reasoning, Max Effort)OpenDeepSeek · 3 more variants	34.3	$0.66	244	1.0 s
9	—	GLM-5.2 (max)OpenZ AI · 1 more variant	33.7	$2.2	76	5.8 s
10	—	Qwen3.8 27B (xhigh)OpenAlibaba · 3 more variants	33.7	$1.1	46	3.9 s
11	—	Motif 3OpenMotif Technologies	33.6	—	—	—
12	▲ 1	K2 Horizon 375B A23BOpenInstitute of Foundation Models	30.5	—	—	—
13	▲ 1	MiniMax-M3OpenMiniMax	29.2	$0.52	227	0.9 s
14	▲ 1	Nex-N2-Pro (based on Qwen3.5-397B-A17B)OpenNex AGI	28.2	—	—	—
15	▲ 1	GLM-5 (Reasoning)OpenZ AI · 1 more variant	27.9	$1.6	77	1.5 s
16	▲ 5	Inkling SmallOpenThinking Machines	27.8	$0.52	184	2.0 s
17	▼ 5	Kimi K2.6OpenKimi · 1 more variant	27.0	$1.7	36	3.1 s
18	▼ 1	Agnes 2.5 Pro AlphaOpenSapiens AI	26.8	$0.56	198	4.0 s
19	▼ 1	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	26.1	$2.0	39	1.8 s
20	▼ 1	MiMo-V2.5-ProOpenXiaomi · 1 more variant	26.0	$0.54	47	3.1 s
21	▼ 1	Kimi K2.7 CodeOpenKimi	25.8	$1.7	62	2.9 s
22	New	K2 Horizon MoVA 36B A4BOpenInstitute of Foundation Models	25.3	—	—	—
23	▼ 1	Hy3OpenTencent	25.3	$0.25	86	3.0 s
24	▲ 11	MiMo-V2.5OpenXiaomi	25.2	$0.18	33	5.3 s
25	▼ 2	Inkling (xhigh)OpenThinking Machines	25.0	$1.8	98	2.4 s
26	▼ 2	Ling 3.0 FlashOpenInclusionAI	24.9	$0.11	320	2.5 s
27	▼ 1	Solar Open2 250BOpenUpstage	24.7	—	—	—
28	▼ 3	Ling-3.0-flash-VLOpenInclusionAI	24.6	$0.000	147	2.3 s
29	▼ 2	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	23.5	$1.1	—	—
30	▼ 2	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	22.9	$1.0	189	2.4 s
31	▼ 1	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	22.9	$0.83	75	5.6 s
32	▼ 1	MiniMax-M2.5OpenMiniMax	22.8	$0.52	98	1.6 s
33	▼ 4	MiniMax-M2.7OpenMiniMax	22.8	$0.52	81	1.6 s
34	▼ 2	Hy3-preview (Reasoning)OpenTencent · 1 more variant	22.7	$0.100	—	—
35	▼ 2	A.X-K2OpenSK Telecom	22.7	—	—	—
36	New	Ling-3.0-flash-FinOpenInclusionAI	22.6	$0.000	161	2.6 s
37	▼ 3	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	22.4	—	—	—
38	▼ 2	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	22.2	$1.0	104	1.2 s
39	▼ 2	Kimi K2 ThinkingOpenKimi	22.0	$1.1	129	1.4 s
40	▼ 1	G9v3-39A5BOpenAI9Stars	21.8	$0.000	—	—
41	▼ 1	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	21.5	$0.32	—	—
42	▼ 1	Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba · 1 more variant	21.4	$1.4	90	2.2 s
43	▼ 5	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	21.4	$1.4	59	3.7 s
44	▼ 2	MiniMax-M2.1OpenMiniMax	20.9	$0.52	108	1.7 s
45	New	K2 Horizon 7BOpenInstitute of Foundation Models	20.6	—	—	—
46	▼ 3	K-EXAONE 2.0 0803OpenLG AI Research	19.7	—	—	—
47	▼ 2	Step 3.7 FlashOpenStepFun	19.5	$0.44	193	2.5 s
48	▼ 2	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	19.3	$0.69	148	2.1 s
49	▼ 5	LongCat 2.0OpenLongCat	19.1	$0.52	—	—
50	▲ 7	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	19.0	$0.000	35	1.0 s
51	▼ 3	MiniMax-M2OpenMiniMax	18.6	$0.52	105	1.7 s
52	▼ 3	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	18.5	$0.96	39	3.6 s
53	▼ 6	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	18.2	$0.84	112	2.1 s
54	▼ 3	Qwen3.5 122B A10B (Non-reasoning)OpenAlibaba · 1 more variant	17.7	$1.1	147	2.3 s
55	▼ 5	Muse Glimmer (high)OpenMeta	17.5	$0.64	95	1.0 s
56	▼ 3	Ling-2.6-1TOpenInclusionAI	17.0	$0.85	—	—
57	▼ 3	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	16.7	$0.18	—	—
58	▼ 6	Ring-2.6-1TOpenInclusionAI	16.6	$0.85	134	3.7 s
59	▼ 4	Step 3.5 FlashOpenStepFun	16.6	$0.15	106	3.4 s
60	▼ 4	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	16.6	$0.32	—	—
61	New	K2 Horizon 3.7BOpenInstitute of Foundation Models	15.6	—	—	—
62	▼ 3	Kimi K2 0905OpenKimi · 1 more variant	15.3	$1.1	42	1.1 s
63	▲ 23	Ling 3.0 TinyOpenInclusionAI	15.3	$0.000	57	3.4 s
64	▼ 3	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	14.9	$0.15	75	1.7 s
65	▼ 3	Granite 4.2 30BOpenIBM	14.8	$0.28	75	0.9 s
66	▼ 8	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	14.8	$1.9	—	—
67	▼ 4	DeepSeek V3.2 SpecialeOpenDeepSeek	14.5	—	—	—
68	▼ 4	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	14.4	—	—	—
69	▼ 9	Mistral Medium 3.5OpenMistral	14.2	$3.0	138	2.3 s
70	▼ 5	Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant	14.2	$0.15	113	2.4 s
71	▼ 4	Apriel-v1.5-15B-ThinkerOpenServiceNow	13.8	$0.000	—	—
72	▼ 4	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	13.7	$0.85	—	—
73	▼ 4	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	13.7	$0.15	64	1.5 s
74	▼ 2	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	13.4	$1.3	53	2.9 s
75	▼ 2	Apriel-v1.6-15B-ThinkerOpenServiceNow	13.4	$0.000	—	—
76	▼ 2	EXAONE 4.5 33BOpenLG AI Research	13.2	—	—	—
77	▼ 11	Command A+OpenCohere · 1 more variant	13.1	$0.000	244	0.4 s
78	▼ 2	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	13.1	$0.060	19	0.8 s
79	▼ 2	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	13.1	$1.8	—	—
80	▼ 10	Nemotron 3.5 LightningOpenNVIDIA	12.9	$0.095	297	0.6 s
81	▼ 10	Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	12.8	$0.31	222	1.7 s
82	▼ 3	GLM-4.5 (Reasoning)OpenZ AI	12.8	—	—	—
83	▼ 3	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	12.7	$0.75	65	2.8 s
84	▼ 9	MiniCPM5-2BOpenOpenBMB	12.5	—	—	—
85	▼ 3	Seed-OSS-36B-InstructOpenByteDance Seed	12.1	$0.30	40	3.0 s
86	▼ 3	Qwen3 235B A22B 2507 InstructOpenAlibaba	12.0	$0.40	55	2.4 s
87	▼ 3	Qwen3 Coder 480B A35B InstructOpenAlibaba	11.9	$3.0	47	3.1 s
88	▼ 3	Qwen3 VL 32B (Reasoning)OpenAlibaba	11.9	$0.28	84	2.6 s
89	▼ 1	HyperNova 60B 2605 (high, based on gpt-oss-120b)OpenMultiverse Computing	11.7	—	—	—
90	▼ 1	MiniMax M1 80kOpenMiniMax	11.7	$0.96	—	—
91	▼ 1	Nemotron Cascade 2 30B A3BOpenNVIDIA	11.7	—	—	—
92	▼ 11	gpt-oss-120b (high)OpenOpenAI · 1 more variant	11.6	$0.26	208	0.8 s
93	▼ 2	K2 Think V2OpenInstitute of Foundation Models	11.5	—	—	—
94	▼ 2	LongCat Flash LiteOpenLongCat	11.5	—	—	—
95	▼ 1	HyperCLOVA X SEED Think (32B)OpenNaver	11.4	—	—	—
96	▼ 3	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	11.3	$0.26	155	0.7 s
97	▼ 2	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	11.2	$0.45	55	3.8 s
98	▼ 2	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	11.2	$0.41	186	2.3 s
99	▼ 2	GLM-4.5-AirOpenZ AI	11.1	$0.37	80	2.5 s
100	▼ 13	Granite 4.2 8BOpenIBM	11.1	$0.11	87	0.9 s
101	▼ 3	Ring-1TOpenInclusionAI	10.9	—	—	—
102	▼ 2	G9v3-3BOpenAI9Stars	10.8	$0.000	—	—
103	▼ 4	Trinity Large ThinkingOpenArcee AI	10.8	$0.41	293	1.4 s
104	▼ 3	INTELLECT-3OpenPrime Intellect	10.6	—	—	—
105	▼ 3	Solar Open 100B (Reasoning)OpenUpstage	10.4	—	—	—
106	▼ 3	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	10.3	$0.16	—	—
107	▲ 13	Llama 4 MaverickOpenMeta	10.0	$0.42	109	0.8 s
108	▼ 3	MiniMax M1 40kOpenMiniMax	10.0	—	—	—
109	▼ 3	gpt-oss-20b (low)OpenOpenAI · 1 more variant	10.0	$0.10	218	0.9 s
110	▼ 3	Qwen3 VL 235B A22B InstructOpenAlibaba	9.9	$0.70	49	2.7 s
111	▼ 33	North Mini CodeOpenCohere	9.9	$0.000	83	0.4 s
112	▼ 4	K2-V2 (high)OpenInstitute of Foundation Models · 2 more variants	9.9	—	—	—
113	▼ 4	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	9.8	$0.75	149	2.4 s
114	▼ 4	DeepSeek V3 0324OpenDeepSeek · 1 more variant	9.7	$0.93	—	—
115	▼ 3	Ling 2.6 FlashOpenInclusionAI	9.7	—	—	—
116	▼ 3	Qwen3 Next 80B A3B InstructOpenAlibaba	9.6	$0.41	178	2.2 s
117	▼ 3	Tri-21B-think PreviewOpenTrillion Labs	9.6	—	—	—
118	▼ 3	Qwen3 Coder 30B A3B InstructOpenAlibaba	9.6	$0.90	85	2.7 s
119	▼ 3	DiffusionGemma 26B A4BOpenGoogle	9.5	—	—	—
120	▼ 3	QwQ 32BOpenAlibaba	9.5	$0.75	—	—
121	▼ 3	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	9.5	$0.75	107	2.2 s
122	▼ 11	Mistral Large 3OpenMistral	9.3	$0.75	75	1.0 s
123	▼ 19	Qwen3 Coder NextOpenAlibaba	9.2	$0.56	114	1.5 s
124	▼ 3	Ling-1TOpenInclusionAI	9.2	—	—	—
125	▼ 3	Granite 4.2 3BOpenIBM	9.1	$0.053	219	0.4 s
126	▼ 3	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	9.0	$0.40	129	4.0 s
127	▼ 3	Tri-21B-ThinkOpenTrillion Labs	9.0	—	—	—
128	▼ 3	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	8.9	—	—	—
129	▼ 3	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	8.9	$0.040	41	0.8 s
130	▼ 3	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	8.9	$0.088	129	1.2 s
131	▼ 3	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	8.8	—	—	—
132	▼ 3	MiniCPM5-1B (Reasoning)OpenOpenBMB · 1 more variant	8.8	—	—	—
133	▼ 3	Sarvam 105B (high)OpenSarvam	8.8	$0.074	—	—
134	▼ 3	Devstral Small (May '25)OpenMistral · 1 more variant	8.7	—	—	—
135	▼ 16	Devstral 2OpenMistral	8.6	$0.000	133	2.3 s
136	▼ 4	Magistral Small 1.2OpenMistral	8.6	$0.75	—	—
137	▲ 28	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	8.6	$0.28	100	2.5 s
138	▼ 5	Nanbeige4.1-3BOpenNanbeige	8.4	—	—	—
139	▼ 5	LFM2.5-2.6BOpenLiquid AI	8.4	$0.000	—	—
140	▼ 5	Qwen3 VL 32B InstructOpenAlibaba	8.4	$0.28	61	2.8 s
141	▼ 5	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	8.4	—	—	—
142	▲ 35	Mistral Small 3.2OpenMistral	8.2	$0.15	145	0.7 s
143	▼ 5	Magistral Small 1OpenMistral	8.2	—	—	—
144	▼ 5	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	8.2	—	—	—
145	▼ 5	Qwen3 VL 8B (Reasoning)OpenAlibaba	8.2	$0.66	108	2.4 s
146	▲ 38	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	8.2	$1.3	58	2.7 s
147	▼ 6	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	8.1	—	—	—
148	▲ 45	Llama 4 ScoutOpenMeta	8.1	$0.31	100	0.8 s
149	▼ 7	Qwen3 VL 30B A3B InstructOpenAlibaba	7.9	$0.35	108	2.1 s
150	▼ 7	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research · 1 more variant	7.9	—	—	—
151	▼ 7	DeepSeek R1 Distill Llama 70BOpenDeepSeek	7.9	$0.80	—	—
152	▼ 7	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	7.8	—	—	—
153	▼ 7	Falcon-H1R-7BOpenTII UAE	7.8	—	—	—
154	▼ 7	Ling-flash-2.0OpenInclusionAI	7.8	$0.25	9	2.7 s
155	▼ 7	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	7.8	—	—	—
156	▼ 7	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	7.8	$0.43	98	2.0 s
157	▼ 7	Qwen2.5 Instruct 72BOpenAlibaba	7.7	$0.48	—	—
158	▼ 7	Step3 VL 10BOpenStepFun	7.7	—	—	—
159	▼ 7	Llama 3.3 Instruct 70BOpenMeta	7.7	$0.71	82	1.5 s
160	▼ 7	QwQ 32B-PreviewOpenAlibaba	7.6	—	—	—
161	▼ 7	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	7.6	$0.90	41	2.8 s
162	▼ 7	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	7.6	—	—	—
163	▼ 26	Devstral Small 2OpenMistral	7.5	$0.000	131	2.3 s
164	▼ 8	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	7.5	—	—	—
165	▼ 8	Qwen3 30B A3B 2507 InstructOpenAlibaba	7.5	$0.35	134	1.9 s
166	▼ 8	ERNIE 4.5 300B A47BOpenBaidu	7.5	$0.49	—	—
167	▼ 8	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research · 1 more variant	7.5	$1.5	44	2.4 s
168	▼ 8	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	7.5	$0.30	122	3.7 s
169	▼ 8	Granite 4.1 30BOpenIBM	7.4	—	—	—
170	▼ 8	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	7.4	$0.070	117	9.1 s
171	▼ 8	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	7.4	—	—	—
172	▼ 6	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	7.3	—	—	—
173	▼ 6	Kimi Linear 48B A3B InstructOpenKimi	7.3	—	—	—
174	▼ 6	Llama 3.1 Instruct 405BOpenMeta	7.3	—	—	—
175	▲ 33	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	7.3	$0.66	41	3.7 s
176	▼ 7	Qwen3 VL 8B InstructOpenAlibaba	7.3	$0.31	112	2.2 s
177	▼ 7	LFM2.5-8B-A1BOpenLiquid AI	7.2	$0.000	—	—
178	▼ 7	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	7.2	—	—	—
179	▼ 7	Ring-flash-2.0OpenInclusionAI	7.2	$0.25	—	—
180	▼ 7	Pixtral LargeOpenMistral	7.1	—	—	—
181	▼ 7	Olmo 3.1 32B ThinkOpenAllen Institute for AI	7.1	$0.000	—	—
182	▼ 18	Mistral Small 3.1OpenMistral	7.1	$0.15	139	0.7 s
183	▼ 8	Grok 2 (Dec '24)OpenSpaceXAI	7.1	—	—	—
184	▼ 8	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.0	—	—	—
185	▼ 7	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	6.9	—	—	—
186	▼ 7	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	6.9	$1.2	166	3.3 s
187	▼ 7	Llama 3.1 Instruct 8BOpenMeta	6.9	$0.028	141	0.8 s
188	▼ 7	Qwen2.5 Instruct 32BOpenAlibaba	6.9	—	—	—
189	▼ 7	Qwen3 4B 2507 InstructOpenAlibaba	6.7	—	—	—
190	▼ 7	Qwen2.5 Coder Instruct 32BOpenAlibaba	6.7	—	—	—
191	▼ 6	Mistral Small 3OpenMistral	6.7	$0.15	141	0.7 s
192	▼ 6	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	6.6	—	—	—
193	▼ 6	Llama 3.1 Instruct 70BOpenMeta	6.6	$0.56	66	1.7 s
194	▼ 6	Granite 4.1 8BOpenIBM	6.6	$0.063	66	0.8 s
195	▼ 6	Sarvam 30B (high)OpenSarvam	6.6	$0.047	—	—
196	▼ 6	Olmo 3.1 32B InstructOpenAllen Institute for AI	6.5	—	—	—
197	▼ 6	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.5	—	—	—
198	▼ 6	Olmo 3 32B ThinkOpenAllen Institute for AI	6.5	—	—	—
199	▼ 5	R1 1776OpenPerplexity	6.4	—	—	—
200	▼ 5	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.4	—	—	—
200	▼ 5	Solar MiniOpenUpstage	6.4	$0.15	—	—
202	▼ 5	Grok-1OpenSpaceXAI	6.3	—	—	—
203	▼ 5	Qwen2 Instruct 72BOpenAlibaba	6.3	—	—	—
204	▼ 5	Phi-4 Mini InstructOpenMicrosoft	6.3	$0.000	45	0.8 s
205	▼ 5	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	6.1	—	—	—
206	▼ 5	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	6.1	—	—	—
207	▼ 5	Jamba 1.7 LargeOpenAI21 Labs	6.1	—	—	—
208	▼ 5	Granite 4.0 H SmallOpenIBM	6.0	$0.11	20	25 s
209	▼ 5	Ministral 3 14BOpenMistral	6.0	$0.20	87	0.9 s
210	▼ 5	Jamba 1.5 LargeOpenAI21 Labs	6.0	$3.5	—	—
211	▼ 5	Qwen3 Omni 30B A3B InstructOpenAlibaba	6.0	$0.43	92	1.9 s
212	▼ 5	Hermes 3 - Llama-3.1 70BOpenNous Research	6.0	$0.70	30	2.1 s
213	▼ 4	DeepSeek-Coder-V2OpenDeepSeek	6.0	—	—	—
214	▼ 4	OLMo 2 32BOpenAllen Institute for AI	6.0	—	—	—
215	▼ 4	Jamba 1.6 LargeOpenAI21 Labs	6.0	—	—	—
216	▼ 4	LFM2 24B A2BOpenLiquid AI	5.9	—	—	—
217	▼ 4	Phi-4OpenMicrosoft	5.9	$0.22	30	2.9 s
218	▼ 4	Granite 4.1 3BOpenIBM	5.9	—	—	—
219	▼ 4	Mistral Small (Sep '24)OpenMistral	5.8	$0.30	143	0.8 s
220	▼ 4	Phi-3 Mini Instruct 3.8BOpenMicrosoft	5.8	—	—	—
221	▼ 4	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	5.8	—	—	—
222	▼ 4	Phi-4 Multimodal InstructOpenMicrosoft	5.8	$0.000	17	0.8 s
223	▼ 4	Qwen2.5 Coder Instruct 7BOpenAlibaba	5.8	—	—	—
224	▼ 4	Mixtral 8x22B InstructOpenMistral	5.7	—	—	—
225	▼ 4	Llama 2 Chat 7BOpenMeta	5.7	$0.10	—	—
226	▼ 4	Llama 3.2 Instruct 3BOpenMeta	5.7	—	—	—
227	▼ 4	MiniCPM-V 4.6 1.3BOpenOpenBMB	5.7	—	—	—
228	▼ 4	Jamba Reasoning 3BOpenAI21 Labs	5.7	—	—	—
229	▼ 4	Qwen3 VL 4B InstructOpenAlibaba	5.7	—	—	—
230	▼ 4	Qwen1.5 Chat 110BOpenAlibaba	5.7	—	—	—
231	▼ 4	Reka Flash 3OpenReka AI	5.6	$0.35	—	—
232	▼ 4	Olmo 3 7B ThinkOpenAllen Institute for AI	5.6	—	—	—
233	▼ 4	OLMo 2 7BOpenAllen Institute for AI	5.6	—	—	—
234	▼ 4	Molmo 7B-DOpenAllen Institute for AI	5.6	—	—	—
235	▼ 4	Ling-mini-2.0OpenInclusionAI	5.5	—	—	—
236	▼ 4	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	5.5	—	—	—
237	▼ 4	DeepSeek-V2-ChatOpenDeepSeek	5.5	—	—	—
238	▼ 4	Ministral 3 8BOpenMistral	5.5	$0.15	93	0.9 s
239	▼ 4	Llama 3 Instruct 70BOpenMeta	5.5	$1.2	—	—
240	▼ 4	Arctic InstructOpenSnowflake	5.4	—	—	—
240	▼ 4	Qwen Chat 72BOpenAlibaba	5.4	—	—	—
242	▼ 4	Llama 3.2 Instruct 11B (Vision)OpenMeta	5.4	$0.35	22	1.6 s
243	▼ 4	DeepSeek Coder V2 Lite InstructOpenDeepSeek	5.3	—	—	—
244	▼ 4	Sarvam M (Reasoning)OpenSarvam	5.3	$0.000	—	—
245	▼ 4	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	5.3	—	—	—
245	▼ 4	Llama 2 Chat 70BOpenMeta	5.3	—	—	—
247	▼ 4	Llama 2 Chat 13BOpenMeta	5.3	—	—	—
248	▼ 4	Command-R+ (Apr '24)OpenCohere · 1 more variant	5.3	—	—	—
249	▼ 4	OpenChat 3.5 (1210)OpenOpenChat	5.3	—	—	—
250	▼ 4	DBRX InstructOpenDatabricks	5.3	—	—	—
251	▼ 4	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	5.3	—	—	—
252	▼ 4	Olmo 3 7B InstructOpenAllen Institute for AI	5.2	$0.13	—	—
253	▼ 4	LFM2.5-1.2B-ThinkingOpenLiquid AI	5.2	—	—	—
254	▼ 4	Jamba 1.7 MiniOpenAI21 Labs	5.2	—	—	—
255	▼ 4	LFM2 2.6BOpenLiquid AI	5.2	—	—	—
256	▼ 4	LFM2.5-1.2B-InstructOpenLiquid AI	5.2	—	—	—
257	▼ 4	Jamba 1.5 MiniOpenAI21 Labs	5.2	$0.25	—	—
258	▼ 4	Granite 4.0 H 1BOpenIBM	5.2	—	—	—
259	▼ 4	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	5.2	—	—	—
260	▼ 4	Jamba 1.6 MiniOpenAI21 Labs	5.2	—	—	—
261	▼ 4	Mixtral 8x7B InstructOpenMistral	5.1	$0.51	—	—
262	▼ 4	Gemma 3 270MOpenGoogle	5.1	—	—	—
263	▼ 4	Apertus 70B InstructOpenSwiss AI Initiative	5.1	$1.3	—	—
264	▼ 4	Granite 4.0 MicroOpenIBM	5.1	—	—	—
265	▼ 4	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	5.1	—	—	—
266	▼ 4	Llama 65BOpenMeta	5.0	—	—	—
266	▼ 4	Mistral 7B InstructOpenMistral	5.0	$0.25	91	0.8 s
266	▼ 4	Qwen Chat 14BOpenAlibaba	5.0	—	—	—
269	▼ 4	Granite 4.0 1BOpenIBM	5.0	—	—	—
270	▼ 4	Molmo2-8BOpenAllen Institute for AI	5.0	—	—	—
271	▼ 4	LFM2 8B A1BOpenLiquid AI	4.9	—	—	—
272	▼ 4	Granite 3.3 8B (Non-reasoning)OpenIBM	4.9	$0.085	16	26 s
273	▼ 4	Gemma 3 27B InstructOpenGoogle	4.9	$0.000	—	—
274	▼ 4	Ministral 3 3BOpenMistral	4.8	$0.10	211	0.7 s
275	▼ 4	Apertus 8B InstructOpenSwiss AI Initiative	4.8	$0.13	—	—
275	▼ 4	Gemma 3 1B InstructOpenGoogle	4.8	$0.000	—	—
275	▼ 4	Gemma 3 4B InstructOpenGoogle	4.8	$0.000	—	—
275	▼ 4	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
275	▼ 4	Gemma 3n E4B InstructOpenGoogle	4.8	—	—	—
275	▼ 4	Granite 4.0 350MOpenIBM	4.8	—	—	—
275	▼ 4	Granite 4.0 H 350MOpenIBM	4.8	—	—	—
275	▼ 4	LFM2 1.2BOpenLiquid AI	4.8	—	—	—
275	▼ 4	LFM2.5-VL-1.6BOpenLiquid AI	4.8	$0.000	—	—
275	▼ 4	Llama 3 Instruct 8BOpenMeta	4.8	$0.070	—	—
275	▼ 4	Llama 3.2 Instruct 1BOpenMeta	4.8	—	—	—
275	▼ 4	Qwen3 0.6B (Non-reasoning)OpenAlibaba · 1 more variant	4.8	—	—	—
275	▼ 4	Tiny Aya GlobalOpenCohere	4.8	$0.000	—	—
288	▼ 4	Gemma 3 12B InstructOpenGoogle	3.8	$0.000	—	—
289	New	K2 Horizon 0.9BOpenInstitute of Foundation Models	3.0	—	—	—

239 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