Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	▲ 1	GLM-5.3 (max)OpenZ AI	44.9	$2.2	72	3.2 s
2	▼ 1	Kimi K3 (max)OpenKimi · 1 more variant	43.8	$6.0	37	4.9 s
3	▲ 1	GLM-5.3-FlashOpenZ AI	41.9	$0.24	109	2.4 s
4	▼ 1	Qwen3.8 2.4T A95BOpenAlibaba	40.0	$3.0	40	2.8 s
5	—	Qwen3.8-Flash-NextOpenAlibaba	39.9	$0.23	51	2.8 s
6	New	DeepSeek V4.1 Flash (Reasoning, Max Effort)OpenDeepSeek	39.5	$0.52	212	1.1 s
7	▼ 1	DeepSeek V4 Pro 0813 (Reasoning, Max Effort)OpenDeepSeek · 3 more variants	36.3	$2.0	78	1.7 s
8	▲ 1	DeepSeek V4 Flash 0731 (Reasoning, Max Effort)OpenDeepSeek · 3 more variants	34.5	$0.66	213	1.0 s
9	▼ 2	GLM-5.2 (max)OpenZ AI · 1 more variant	34.0	$2.2	75	7.3 s
10	▼ 2	Qwen3.8 27B (xhigh)OpenAlibaba · 3 more variants	33.9	$1.1	43	3.9 s
11	▼ 1	Motif 3OpenMotif Technologies	33.6	—	—	—
12	—	Kimi K2.6OpenKimi · 1 more variant	31.3	$1.7	36	3.0 s
13	▼ 2	K2 Horizon 375B A23BOpenMBZUAI Institute of Foundation Models	30.8	—	—	—
14	▼ 1	MiniMax-M3OpenMiniMax	29.6	$0.52	107	1.3 s
15	—	Nex-N2-ProOpenNex AGI	28.2	$1.0	—	—
16	▲ 2	GLM-5 (Reasoning)OpenZ AI · 1 more variant	27.9	$1.6	81	1.4 s
17	▲ 5	Agnes 2.5 Pro AlphaOpenSapiens AI	27.8	$0.56	174	4.0 s
18	▲ 3	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	26.4	$2.0	78	1.6 s
19	▼ 3	MiMo-V2.5-ProOpenXiaomi · 1 more variant	26.4	$0.54	43	7.6 s
20	▼ 6	Kimi K2.7 CodeOpenKimi	26.3	$1.7	49	2.9 s
21	▼ 2	Inkling SmallOpenThinking Machines	26.1	$0.52	167	2.2 s
22	▼ 5	Hy3OpenTencent	25.8	$0.24	91	2.7 s
23	▼ 3	Inkling (xhigh)OpenThinking Machines	25.5	$1.8	89	2.9 s
24	▲ 5	Ling 3.0 FlashOpenInclusionAI	24.9	$0.11	276	2.5 s
25	New	Ling-3.0-flash-VLOpenInclusionAI	24.8	$0.000	144	2.3 s
26	—	Solar Open2 250BOpenUpstage	24.7	—	—	—
27	▲ 1	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	23.5	$1.1	—	—
28	▼ 3	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	23.4	$1.1	203	2.3 s
29	▼ 6	MiniMax-M2.7OpenMiniMax	23.2	$0.52	52	1.7 s
30	—	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	22.9	$0.83	77	5.6 s
31	—	MiniMax-M2.5OpenMiniMax	22.8	$0.52	95	1.6 s
32	—	Hy3-preview (Reasoning)OpenTencent · 1 more variant	22.7	$0.100	—	—
33	—	A.X-K2OpenSK Telecom	22.7	—	—	—
34	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	22.4	—	—	—
35	▼ 11	MiMo-V2.5OpenXiaomi	22.3	$0.18	45	6.0 s
36	▼ 1	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	22.2	$1.0	103	1.2 s
37	▲ 1	Kimi K2 ThinkingOpenKimi	22.0	$1.1	123	1.4 s
38	▼ 11	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	21.9	$1.4	58	3.7 s
39	▲ 1	G9v3-39A5BOpenAI9Stars	21.8	$0.000	—	—
40	▲ 1	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	21.5	$0.32	—	—
41	▼ 4	Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba · 1 more variant	21.4	$1.4	86	2.2 s
42	▲ 1	MiniMax-M2.1OpenMiniMax	20.9	$0.52	94	1.7 s
43	▲ 4	K-EXAONE 2.0OpenLG AI Research	19.7	—	—	—
44	▼ 5	LongCat 2.0OpenLongCat	19.7	$0.52	—	—
45	▲ 3	Step 3.7 FlashOpenStepFun	19.5	$0.44	113	2.7 s
46	▲ 4	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	19.3	$0.69	153	2.1 s
47	▼ 11	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	18.8	$0.84	127	2.1 s
48	▲ 4	MiniMax-M2OpenMiniMax	18.6	$0.52	94	1.7 s
49	▲ 4	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	18.5	$0.96	37	3.6 s
50	▼ 6	Muse Glimmer (high)OpenMeta	18.1	$0.64	89	1.1 s
51	▼ 9	Qwen3.5 122B A10B (Non-reasoning)OpenAlibaba · 1 more variant	17.7	$1.1	142	2.4 s
52	▼ 7	Ring-2.6-1TOpenInclusionAI	17.3	$0.85	127	3.7 s
53	▲ 1	Ling-2.6-1TOpenInclusionAI	17.0	$0.85	—	—
54	▲ 1	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	16.7	$0.18	—	—
55	▲ 1	Step 3.5 FlashOpenStepFun	16.6	$0.15	159	3.4 s
56	▲ 1	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	16.6	$0.32	—	—
57	▼ 6	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	15.4	$0.000	35	1.0 s
58	▼ 12	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	15.4	$1.9	—	—
59	—	Kimi K2 0905OpenKimi · 1 more variant	15.3	$1.1	40	1.1 s
60	▼ 11	Mistral Medium 3.5OpenMistral	14.9	$3.0	152	2.2 s
61	▼ 1	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	14.9	$0.15	77	1.5 s
62	▼ 1	Granite 4.2 30BOpenIBM	14.8	$0.28	77	0.8 s
63	—	DeepSeek V3.2 SpecialeOpenDeepSeek	14.5	—	—	—
64	—	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	14.4	—	—	—
65	▲ 3	Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant	14.2	$0.15	110	2.4 s
66	—	Command A+OpenCohere · 1 more variant	13.9	$0.000	253	0.4 s
67	▲ 2	Apriel-v1.5-15B-ThinkerOpenServiceNow	13.8	$0.000	—	—
68	▲ 2	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	13.7	$0.85	—	—
69	▲ 2	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	13.7	$0.15	91	2.1 s
70	▼ 8	Nemotron 3.5 LightningOpenNVIDIA	13.6	$0.095	298	0.6 s
71	▼ 13	Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	13.6	$0.31	171	2.8 s
72	—	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	13.4	$1.3	57	2.8 s
73	—	Apriel-v1.6-15B-ThinkerOpenServiceNow	13.4	$0.000	—	—
74	▲ 1	EXAONE 4.5 33BOpenLG AI Research	13.2	—	—	—
75	New	MiniCPM5-2BOpenOpenBMB	13.1	—	—	—
76	▲ 1	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	13.1	$0.060	29	0.8 s
77	▲ 1	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	13.1	$1.8	—	—
78	▲ 1	North Mini CodeOpenCohere	12.8	$0.000	75	0.4 s
79	▲ 1	GLM-4.5 (Reasoning)OpenZ AI	12.8	—	—	—
80	▲ 1	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	12.7	$0.75	64	2.8 s
81	▼ 14	gpt-oss-120b (high)OpenOpenAI · 1 more variant	12.3	$0.26	217	0.8 s
82	▲ 2	Seed-OSS-36B-InstructOpenByteDance Seed	12.1	$0.30	37	2.8 s
83	▲ 2	Qwen3 235B A22B 2507 InstructOpenAlibaba	12.0	$0.40	58	2.2 s
84	▲ 3	Qwen3 Coder 480B A35B InstructOpenAlibaba	11.9	$3.0	54	3.1 s
85	▲ 3	Qwen3 VL 32B (Reasoning)OpenAlibaba	11.9	$0.28	88	2.6 s
86	▼ 21	Ling 3.0 TinyOpenInclusionAI	11.9	$0.000	168	2.7 s
87	▼ 11	Granite 4.2 8BOpenIBM	11.8	$0.11	83	0.6 s
88	▲ 1	HyperNova 60B 2605 (high, based on gpt-oss-120b)OpenMultiverse Computing	11.7	$0.065	345	0.6 s
89	▲ 1	MiniMax M1 80kOpenMiniMax	11.7	$0.96	—	—
90	▲ 1	Nemotron Cascade 2 30B A3BOpenNVIDIA	11.7	—	—	—
91	▲ 1	K2 Think V2OpenMBZUAI Institute of Foundation Models	11.5	—	—	—
92	▲ 1	LongCat Flash LiteOpenLongCat	11.5	—	—	—
93	▼ 11	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	11.5	$0.26	169	0.7 s
94	▲ 2	HyperCLOVA X SEED Think (32B)OpenNaver	11.4	—	—	—
95	▲ 2	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	11.2	$0.45	66	3.2 s
96	▲ 3	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	11.2	$0.41	195	2.4 s
97	▲ 3	GLM-4.5-AirOpenZ AI	11.1	$0.37	68	2.5 s
98	▲ 3	Ring-1TOpenInclusionAI	10.9	—	—	—
99	▼ 13	Trinity Large ThinkingOpenArcee AI	10.9	$0.41	310	1.3 s
100	▲ 2	G9v3-3BOpenAI9Stars	10.8	$0.000	—	—
101	▲ 2	INTELLECT-3OpenPrime Intellect	10.6	—	—	—
102	▲ 2	Solar Open 100B (Reasoning)OpenUpstage	10.4	—	—	—
103	▲ 4	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	10.3	$0.16	—	—
104	▼ 30	Qwen3 Coder NextOpenAlibaba	10.1	$0.56	124	1.2 s
105	▲ 7	MiniMax M1 40kOpenMiniMax	10.0	—	—	—
106	—	gpt-oss-20b (low)OpenOpenAI · 1 more variant	10.0	$0.10	258	0.8 s
107	▲ 6	Qwen3 VL 235B A22B InstructOpenAlibaba	9.9	$0.70	52	2.6 s
108	▲ 6	K2-V2 (high)OpenMBZUAI Institute of Foundation Models · 2 more variants	9.9	—	—	—
109	▼ 1	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	9.8	$0.75	158	2.4 s
110	▼ 5	DeepSeek V3 0324OpenDeepSeek · 1 more variant	9.7	$0.93	—	—
111	▼ 16	Mistral Large 3OpenMistral	9.7	$0.75	74	1.1 s
112	▲ 3	Ling 2.6 FlashOpenInclusionAI	9.7	—	—	—
113	▲ 3	Qwen3 Next 80B A3B InstructOpenAlibaba	9.6	$0.41	181	2.2 s
114	▲ 3	Tri-21B-think PreviewOpenTrillion Labs	9.6	—	—	—
115	▲ 3	Qwen3 Coder 30B A3B InstructOpenAlibaba	9.6	$0.90	90	2.7 s
116	▲ 3	DiffusionGemma 26B A4BOpenGoogle	9.5	—	—	—
117	▲ 3	QwQ 32BOpenAlibaba	9.5	$0.75	—	—
118	▲ 3	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	9.5	$0.75	111	2.2 s
119	▼ 36	Devstral 2OpenMistral	9.4	$0.000	144	2.3 s
120	▼ 9	Llama 4 MaverickOpenMeta	9.3	$0.42	93	0.8 s
121	▲ 1	Ling-1TOpenInclusionAI	9.2	—	—	—
122	▼ 24	Granite 4.2 3BOpenIBM	9.1	$0.053	216	0.4 s
123	—	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	9.0	$0.40	84	4.7 s
124	—	Tri-21B-ThinkOpenTrillion Labs	9.0	—	—	—
125	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	8.9	—	—	—
126	—	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	8.9	$0.040	42	0.9 s
127	▼ 17	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	8.9	$0.088	261	1.2 s
128	▼ 1	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	8.8	—	—	—
129	▼ 1	MiniCPM5-1B (Reasoning)OpenOpenBMB · 1 more variant	8.8	—	—	—
130	▼ 1	Sarvam 105B (high)OpenSarvam	8.8	$0.074	—	—
131	▼ 1	Devstral Small (May '25)OpenMistral · 1 more variant	8.7	—	—	—
132	▼ 1	Magistral Small 1.2OpenMistral	8.6	$0.75	—	—
133	▲ 1	Nanbeige4.1-3BOpenNanbeige	8.4	—	—	—
134	▲ 1	LFM2.5-2.6BOpenLiquid AI	8.4	$0.000	—	—
135	▲ 1	Qwen3 VL 32B InstructOpenAlibaba	8.4	$0.28	57	2.8 s
136	▲ 1	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	8.4	—	—	—
137	▼ 43	Devstral Small 2OpenMistral	8.4	$0.000	138	2.2 s
138	▲ 1	Magistral Small 1OpenMistral	8.2	—	—	—
139	▲ 1	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	8.2	—	—	—
140	▲ 1	Qwen3 VL 8B (Reasoning)OpenAlibaba	8.2	$0.66	114	2.4 s
141	▲ 2	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	8.1	—	—	—
142	▲ 3	Qwen3 VL 30B A3B InstructOpenAlibaba	7.9	$0.35	112	2.2 s
143	▲ 3	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research · 1 more variant	7.9	—	—	—
144	▲ 3	DeepSeek R1 Distill Llama 70BOpenDeepSeek	7.9	$0.80	23	1.0 s
145	▲ 3	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	7.8	—	—	—
146	▲ 3	Falcon-H1R-7BOpenTII UAE	7.8	—	—	—
147	▲ 3	Ling-flash-2.0OpenInclusionAI	7.8	$0.25	5	2.7 s
148	▲ 3	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	7.8	—	—	—
149	▲ 3	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	7.8	$0.43	101	1.9 s
150	▲ 3	Qwen2.5 Instruct 72BOpenAlibaba	7.7	$0.48	—	—
151	▲ 3	Step3 VL 10BOpenStepFun	7.7	—	—	—
152	▲ 3	Llama 3.3 Instruct 70BOpenMeta	7.7	$0.67	88	1.6 s
153	▲ 3	QwQ 32B-PreviewOpenAlibaba	7.6	—	—	—
154	▲ 3	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	7.6	$0.90	37	2.7 s
155	▲ 3	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	7.6	—	—	—
156	▲ 4	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	7.5	—	—	—
157	▲ 4	Qwen3 30B A3B 2507 InstructOpenAlibaba	7.5	$0.35	141	1.9 s
158	▲ 4	ERNIE 4.5 300B A47BOpenBaidu	7.5	$0.49	—	—
159	▲ 4	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research · 1 more variant	7.5	$1.5	44	2.5 s
160	▲ 4	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	7.5	$0.30	82	4.3 s
161	▲ 4	Granite 4.1 30BOpenIBM	7.4	—	—	—
162	▲ 4	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	7.4	$0.070	96	5.6 s
163	▲ 4	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	7.4	—	—	—
164	▼ 55	Mistral Small 3.1OpenMistral	7.4	$0.15	151	0.7 s
165	▼ 33	Qwen3 32B (Non-reasoning)OpenAlibaba · 1 more variant	7.3	$0.28	106	2.5 s
166	▲ 2	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	7.3	—	—	—
167	▲ 2	Kimi Linear 48B A3B InstructOpenKimi	7.3	—	—	—
168	▲ 2	Llama 3.1 Instruct 405BOpenMeta	7.3	—	—	—
169	▲ 3	Qwen3 VL 8B InstructOpenAlibaba	7.3	$0.31	117	2.2 s
170	▲ 3	LFM2.5-8B-A1BOpenLiquid AI	7.2	$0.000	—	—
171	▲ 3	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	7.2	—	—	—
172	▲ 3	Ring-flash-2.0OpenInclusionAI	7.2	$0.25	—	—
173	▲ 3	Pixtral LargeOpenMistral	7.1	—	—	—
174	▲ 3	Olmo 3.1 32B ThinkOpenAllen Institute for AI	7.1	$0.000	—	—
175	▲ 3	Grok 2 (Dec '24)OpenSpaceXAI	7.1	—	—	—
176	▲ 3	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.0	—	—	—
177	▼ 39	Mistral Small 3.2OpenMistral	7.0	$0.15	151	0.8 s
178	▲ 2	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	6.9	—	—	—
179	▲ 2	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	6.9	$1.2	91	4.3 s
180	▲ 2	Llama 3.1 Instruct 8BOpenMeta	6.9	$0.028	139	0.9 s
181	▲ 3	Qwen2.5 Instruct 32BOpenAlibaba	6.9	—	—	—
182	▲ 4	Qwen3 4B 2507 InstructOpenAlibaba	6.7	—	—	—
183	▲ 4	Qwen2.5 Coder Instruct 32BOpenAlibaba	6.7	—	—	—
184	▼ 42	Qwen3 14B (Non-reasoning)OpenAlibaba · 1 more variant	6.7	$0.61	64	2.7 s
185	▲ 3	Mistral Small 3OpenMistral	6.7	$0.15	149	0.7 s
186	▲ 3	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	6.6	—	—	—
187	▲ 3	Llama 3.1 Instruct 70BOpenMeta	6.6	$0.56	55	1.7 s
188	▲ 3	Granite 4.1 8BOpenIBM	6.6	$0.063	126	0.8 s
189	▲ 3	Sarvam 30B (high)OpenSarvam	6.6	$0.047	—	—
190	▲ 3	Olmo 3.1 32B InstructOpenAllen Institute for AI	6.5	—	—	—
191	▲ 2	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.5	—	—	—
192	▲ 1	Olmo 3 32B ThinkOpenAllen Institute for AI	6.5	—	—	—
193	▼ 49	Llama 4 ScoutOpenMeta	6.5	$0.31	119	0.8 s
194	▼ 1	R1 1776OpenPerplexity	6.4	—	—	—
195	▼ 2	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.4	—	—	—
195	▼ 2	Solar MiniOpenUpstage	6.4	$0.15	—	—
197	▼ 4	Grok-1OpenSpaceXAI	6.3	—	—	—
198	▼ 5	Qwen2 Instruct 72BOpenAlibaba	6.3	—	—	—
199	▼ 6	Phi-4 Mini InstructOpenMicrosoft	6.3	$0.000	45	0.9 s
200	▼ 7	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	6.1	—	—	—
201	▼ 8	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	6.1	—	—	—
202	▼ 9	Jamba 1.7 LargeOpenAI21 Labs	6.1	—	—	—
203	▼ 10	Granite 4.0 H SmallOpenIBM	6.0	$0.11	12	33 s
204	▼ 71	Ministral 3 14BOpenMistral	6.0	$0.20	101	0.9 s
205	▼ 12	Jamba 1.5 LargeOpenAI21 Labs	6.0	$3.5	—	—
206	▼ 13	Qwen3 Omni 30B A3B InstructOpenAlibaba	6.0	$0.43	96	1.9 s
207	▼ 14	Hermes 3 - Llama-3.1 70BOpenNous Research	6.0	$0.70	29	2.1 s
208	▼ 37	Qwen3 8B (Non-reasoning)OpenAlibaba · 1 more variant	6.0	$0.31	40	3.7 s
209	▼ 16	DeepSeek-Coder-V2OpenDeepSeek	6.0	—	—	—
210	▼ 17	OLMo 2 32BOpenAllen Institute for AI	6.0	—	—	—
211	▼ 18	Jamba 1.6 LargeOpenAI21 Labs	6.0	—	—	—
212	▼ 19	LFM2 24B A2BOpenLiquid AI	5.9	—	—	—
213	▼ 20	Phi-4OpenMicrosoft	5.9	$0.22	39	2.6 s
214	▼ 21	Granite 4.1 3BOpenIBM	5.9	—	—	—
215	▼ 22	Mistral Small (Sep '24)OpenMistral	5.8	$0.30	155	0.7 s
216	▼ 23	Phi-3 Mini Instruct 3.8BOpenMicrosoft	5.8	—	—	—
217	▼ 24	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	5.8	—	—	—
218	▼ 25	Phi-4 Multimodal InstructOpenMicrosoft	5.8	$0.000	17	0.9 s
219	▼ 26	Qwen2.5 Coder Instruct 7BOpenAlibaba	5.8	—	—	—
220	▼ 27	Mixtral 8x22B InstructOpenMistral	5.7	—	—	—
221	▼ 28	Llama 2 Chat 7BOpenMeta	5.7	$0.10	—	—
222	▼ 29	Llama 3.2 Instruct 3BOpenMeta	5.7	—	—	—
223	▼ 30	MiniCPM-V 4.6 1.3BOpenOpenBMB	5.7	—	—	—
224	▼ 31	Jamba Reasoning 3BOpenAI21 Labs	5.7	—	—	—
225	▼ 32	Qwen3 VL 4B InstructOpenAlibaba	5.7	—	—	—
226	▼ 33	Qwen1.5 Chat 110BOpenAlibaba	5.7	—	—	—
227	▼ 34	Reka Flash 3OpenReka AI	5.6	$0.35	—	—
228	▼ 35	Olmo 3 7B ThinkOpenAllen Institute for AI	5.6	—	—	—
229	▼ 36	OLMo 2 7BOpenAllen Institute for AI	5.6	—	—	—
230	▼ 37	Molmo 7B-DOpenAllen Institute for AI	5.6	—	—	—
231	▼ 38	Ling-mini-2.0OpenInclusionAI	5.5	—	—	—
232	▼ 39	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	5.5	—	—	—
233	▼ 40	DeepSeek-V2-ChatOpenDeepSeek	5.5	—	—	—
234	▼ 75	Ministral 3 8BOpenMistral	5.5	$0.15	88	0.7 s
235	▼ 42	Llama 3 Instruct 70BOpenMeta	5.5	$1.2	—	—
236	▼ 43	Arctic InstructOpenSnowflake	5.4	—	—	—
236	▼ 43	Qwen Chat 72BOpenAlibaba	5.4	—	—	—
238	▼ 45	Llama 3.2 Instruct 11B (Vision)OpenMeta	5.4	$0.35	24	1.3 s
239	▼ 46	DeepSeek Coder V2 Lite InstructOpenDeepSeek	5.3	—	—	—
240	▼ 47	Sarvam M (Reasoning)OpenSarvam	5.3	$0.000	—	—
241	▼ 48	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	5.3	—	—	—
241	▼ 48	Llama 2 Chat 70BOpenMeta	5.3	—	—	—
243	▼ 50	Llama 2 Chat 13BOpenMeta	5.3	—	—	—
244	▼ 51	Command-R+ (Apr '24)OpenCohere · 1 more variant	5.3	—	—	—
245	▼ 52	OpenChat 3.5 (1210)OpenOpenChat	5.3	—	—	—
246	▼ 53	DBRX InstructOpenDatabricks	5.3	—	—	—
247	▼ 54	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	5.3	—	—	—
248	▼ 55	Olmo 3 7B InstructOpenAllen Institute for AI	5.2	$0.13	—	—
249	▼ 56	LFM2.5-1.2B-ThinkingOpenLiquid AI	5.2	—	—	—
250	▼ 57	Jamba 1.7 MiniOpenAI21 Labs	5.2	—	—	—
251	▼ 58	LFM2 2.6BOpenLiquid AI	5.2	—	—	—
252	▼ 59	LFM2.5-1.2B-InstructOpenLiquid AI	5.2	—	—	—
253	▼ 60	Jamba 1.5 MiniOpenAI21 Labs	5.2	$0.25	—	—
254	▼ 61	Granite 4.0 H 1BOpenIBM	5.2	—	—	—
255	▼ 62	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	5.2	—	—	—
256	▼ 63	Jamba 1.6 MiniOpenAI21 Labs	5.2	—	—	—
257	▼ 64	Mixtral 8x7B InstructOpenMistral	5.1	$0.51	—	—
258	▼ 65	Gemma 3 270MOpenGoogle	5.1	—	—	—
259	▼ 66	Apertus 70B InstructOpenSwiss AI Initiative	5.1	$1.3	—	—
260	▼ 67	Granite 4.0 MicroOpenIBM	5.1	—	—	—
261	▼ 68	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	5.1	—	—	—
262	▼ 69	Llama 65BOpenMeta	5.0	—	—	—
262	▼ 69	Mistral 7B InstructOpenMistral	5.0	$0.25	90	0.7 s
262	▼ 69	Qwen Chat 14BOpenAlibaba	5.0	—	—	—
265	▼ 72	Granite 4.0 1BOpenIBM	5.0	—	—	—
266	▼ 73	Molmo2-8BOpenAllen Institute for AI	5.0	—	—	—
267	▼ 74	LFM2 8B A1BOpenLiquid AI	4.9	—	—	—
268	▼ 75	Granite 3.3 8B (Non-reasoning)OpenIBM	4.9	$0.085	33	11 s
269	▼ 86	Gemma 3 27B InstructOpenGoogle	4.9	$0.000	—	—
270	▼ 85	Ministral 3 3BOpenMistral	4.8	$0.10	211	0.6 s
271	▼ 78	Apertus 8B InstructOpenSwiss AI Initiative	4.8	$0.13	—	—
271	▼ 78	Gemma 3 1B InstructOpenGoogle	4.8	$0.000	—	—
271	▼ 78	Gemma 3 4B InstructOpenGoogle	4.8	$0.000	—	—
271	▼ 78	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
271	▼ 78	Gemma 3n E4B InstructOpenGoogle	4.8	—	—	—
271	▼ 78	Granite 4.0 350MOpenIBM	4.8	—	—	—
271	▼ 78	Granite 4.0 H 350MOpenIBM	4.8	—	—	—
271	▼ 78	LFM2 1.2BOpenLiquid AI	4.8	—	—	—
271	▼ 78	LFM2.5-VL-1.6BOpenLiquid AI	4.8	$0.000	—	—
271	▼ 78	Llama 3 Instruct 8BOpenMeta	4.8	$0.070	—	—
271	▼ 78	Llama 3.2 Instruct 1BOpenMeta	4.8	—	—	—
271	▼ 78	Qwen3 0.6B (Non-reasoning)OpenAlibaba · 1 more variant	4.8	—	—	—
271	▼ 78	Tiny Aya GlobalOpenCohere	4.8	$0.000	—	—
284	▼ 91	Gemma 3 12B InstructOpenGoogle	3.8	$0.000	—	—

234 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