Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	MiMo-V2.6-ProOpenXiaomi	46.3	$0.54	43	4.0 s
2	New	GLM-5.3 (Max)OpenZ AI	44.8	$2.2	72	2.7 s
3	New	Kimi K3 (Max)OpenKimi	43.6	$6.0	43	3.8 s
4	—	GLM 5.3 FlashOpenZ AI	41.8	$0.24	52	3.3 s
5	New	Ling 3.1 FlashOpenInclusionAI	41.1	$0.45	211	1.8 s
6	▼ 1	Qwen3.8 2.4T A95BOpenAlibaba	39.9	$3.0	38	2.8 s
7	▼ 1	Qwen3.8-Flash-NextOpenAlibaba	39.8	$0.23	55	2.5 s
8	New	DeepSeek V4.1 Flash (Max)OpenDeepSeek	39.5	$0.52	214	1.1 s
9	▼ 1	MiMo-V2.6-FlashOpenXiaomi	37.9	$0.18	52	5.2 s
10	New	DeepSeek V4 Pro 0813 (Max)OpenDeepSeek	36.0	$2.0	105	1.7 s
11	New	DeepSeek V4 Flash 0731 (Max)OpenDeepSeek	34.3	$0.66	217	1.0 s
12	New	GLM-5.3 (Low)OpenZ AI	34.3	$2.2	79	3.2 s
13	New	GLM-5.2 (Max)OpenZ AI	33.7	$2.2	94	2.9 s
14	New	Qwen3.8 27B (Xhigh)OpenAlibaba	33.7	$1.1	45	3.7 s
15	—	Motif 3OpenMotif Technologies	33.6	—	—	—
16	—	K2 Horizon 375B A23BOpenInstitute of Foundation Models	30.5	$0.000	119	14 s
17	New	DeepSeek V4 Pro 0424 (Max)OpenDeepSeek	30.4	$0.54	108	1.5 s
18	New	DeepSeek V4 Pro 0424 (High)OpenDeepSeek	30.1	$0.54	109	1.6 s
19	New	Kimi K3 (Low)OpenKimi	30.1	$6.0	43	3.6 s
20	▼ 1	MiniMax-M3OpenMiniMax	29.2	$0.52	94	2.0 s
21	New	Nex-N2-Pro (Based on Qwen3.5-397B-A17B)OpenNex AGI	28.2	—	—	—
22	▼ 1	GLM-5 (Reasoning)OpenZ AI	27.9	$1.6	81	1.4 s
23	New	Qwen3.8 27B (Medium)OpenAlibaba	27.6	$1.1	51	3.8 s
24	New	Kimi K2.6 (Reasoning)OpenKimi	27.0	$1.7	60	2.8 s
25	New	Qwen3.8 27B (Low)OpenAlibaba	26.2	$1.1	50	3.9 s
26	—	GLM-5.1 (Reasoning)OpenZ AI	26.1	$2.0	56	1.8 s
27	New	MiMo-V2.5-Pro (Reasoning)OpenXiaomi	26.0	$0.54	44	2.2 s
28	▲ 1	Kimi K2.7 CodeOpenKimi	25.8	$1.7	97	3.0 s
29	▼ 7	Inkling SmallOpenThinking Machines	25.7	$0.52	193	2.1 s
30	—	K2 Horizon MoVA 36B A4BOpenInstitute of Foundation Models	25.3	—	—	—
31	—	Hy3OpenTencent	25.3	$0.24	87	3.1 s
32	—	MiMo-V2.5OpenXiaomi	25.2	$0.18	62	2.4 s
33	New	Inkling (Xhigh)OpenThinking Machines	25.0	$1.8	172	1.8 s
34	▲ 1	Solar Open2 250BOpenUpstage	24.7	—	—	—
35	New	DeepSeek V4.1 Flash (Non-reasoning)OpenDeepSeek	24.7	$0.52	208	1.0 s
36	▲ 1	Ling-3.0-flash-VLOpenInclusionAI	24.6	$0.11	—	—
37	New	DeepSeek V4 Flash 0420 (High)OpenDeepSeek	24.4	$0.14	—	—
38	—	GLM-5.1 (Non-reasoning)OpenZ AI	24.2	$2.1	47	1.8 s
39	New	DeepSeek V4 Flash 0420 (Max)OpenDeepSeek	24.2	$0.17	—	—
40	—	Kimi K2.6 (Non-reasoning)OpenKimi	23.6	$1.7	66	2.9 s
41	—	Kimi K2.5 (Reasoning)OpenKimi	23.5	$1.1	—	—
42	—	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	22.9	$1.1	173	1.2 s
43	—	Qwen3.5 27B (Reasoning)OpenAlibaba	22.9	$0.83	76	5.7 s
44	—	MiniMax-M2.5OpenMiniMax	22.8	$0.52	94	1.4 s
45	—	MiniMax-M2.7OpenMiniMax	22.8	$0.52	65	1.5 s
46	—	Hy3-preview (Reasoning)OpenTencent	22.7	$0.100	—	—
47	—	A.X-K2OpenSK Telecom	22.7	—	—	—
48	—	Ling-3.0-flash-FinOpenInclusionAI	22.6	$0.11	338	1.7 s
49	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi	22.4	—	—	—
50	—	GLM-5.2 (Non-reasoning)OpenZ AI	22.4	$2.2	154	1.1 s
51	—	GLM-4.7 (Reasoning)OpenZ AI	22.2	$1.0	67	1.3 s
52	—	Kimi K2 ThinkingOpenKimi	22.0	$1.1	159	1.3 s
53	—	G9v3-39A5BOpenAI9Stars	21.8	$0.000	—	—
54	—	GLM-5 (Non-reasoning)OpenZ AI	21.8	$1.6	65	1.6 s
55	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek	21.5	$0.32	—	—
56	—	Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba	21.4	$1.4	82	2.1 s
57	—	Qwen3.6 27B (Reasoning)OpenAlibaba	21.4	$1.4	56	3.6 s
58	—	MiniMax-M2.1OpenMiniMax	20.9	$0.52	96	1.4 s
59	—	DeepSeek V4 Pro 0424 (Non-reasoning)OpenDeepSeek	20.8	$0.54	104	1.6 s
60	—	MiMo-V2-Flash (Reasoning)OpenXiaomi	20.8	$0.15	—	—
61	—	K2 Horizon 7BOpenInstitute of Foundation Models	20.6	—	—	—
62	New	DeepSeek V4 Pro 0813 (Non-reasoning)OpenDeepSeek	20.4	$1.4	170	1.6 s
63	▼ 1	Qwen3.8 27B (Non-reasoning)OpenAlibaba	20.2	$1.1	51	3.7 s
64	▼ 30	Ling 3.0 FlashOpenInclusionAI	20.1	$0.11	353	2.5 s
65	▼ 2	Qwen3.6 27B (Non-reasoning)OpenAlibaba	19.8	$1.4	56	3.6 s
66	▼ 2	K-EXAONE 2.0 0803OpenLG AI Research	19.7	—	—	—
67	▼ 2	Step 3.7 FlashOpenStepFun	19.5	$0.44	195	2.5 s
68	▼ 2	Kimi K2.5 (Non-reasoning)OpenKimi	19.4	$1.2	—	—
69	▼ 2	Qwen3.5 27B (Non-reasoning)OpenAlibaba	19.4	$0.83	80	5.6 s
70	▼ 2	Qwen3.5 35B A3B (Reasoning)OpenAlibaba	19.3	$0.69	145	2.2 s
71	▼ 2	LongCat 2.0OpenLongCat	19.1	$0.52	—	—
72	▼ 1	DeepSeek V4 Flash 0420 (Non-reasoning)OpenDeepSeek	18.9	$0.12	—	—
73	▼ 1	MiniMax-M2OpenMiniMax	18.6	$0.52	98	1.5 s
74	▼ 1	GLM-4.6 (Reasoning)OpenZ AI	18.5	$0.96	35	4.3 s
75	▼ 1	Qwen3.5 397B A17B (Reasoning)OpenAlibaba	18.4	$1.4	84	2.3 s
76	▼ 1	MiMo-V2.5-Pro (Non-reasoning)OpenXiaomi	18.3	$0.54	44	2.3 s
77	▼ 1	Qwen3.6 35B A3B (Reasoning)OpenAlibaba	18.2	$0.84	130	2.1 s
78	▼ 1	Qwen3.5 122B A10B (Non-reasoning)OpenAlibaba	17.7	$1.1	141	2.3 s
79	New	Muse Glimmer (High)OpenMeta	17.5	$0.58	131	0.9 s
80	▼ 1	GLM-4.7 (Non-reasoning)OpenZ AI	17.4	$1.0	65	1.3 s
81	▼ 1	Hy3-preview (Non-reasoning)OpenTencent	17.0	$0.100	—	—
82	▼ 1	Ling-2.6-1TOpenInclusionAI	17.0	$0.85	—	—
83	▼ 1	Gemma 4 26B A4B (Reasoning)OpenGoogle	16.7	$0.17	—	—
84	▼ 1	Ring-2.6-1TOpenInclusionAI	16.6	$0.85	116	3.6 s
85	▼ 1	Step 3.5 FlashOpenStepFun	16.6	$0.15	105	3.4 s
86	▼ 1	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek	16.6	$0.32	—	—
87	▼ 1	MiMo-V2-Flash (Non-reasoning)OpenXiaomi	16.0	—	—	—
88	▼ 1	DeepSeek V3.2 (Non-reasoning)OpenDeepSeek	16.0	$0.32	—	—
89	▼ 1	K2 Horizon 3.7BOpenInstitute of Foundation Models	15.6	—	—	—
90	▼ 1	Qwen3.5 122B A10B (Reasoning)OpenAlibaba	15.6	$1.1	129	2.3 s
91	▼ 1	Kimi K2 0905OpenKimi	15.3	$1.1	54	1.2 s
92	—	Qwen3.6 35B A3B (Non-reasoning)OpenAlibaba	15.2	$0.84	134	2.1 s
93	—	Qwen3.5 35B A3B (Non-reasoning)OpenAlibaba	15.1	$0.69	163	2.1 s
94	—	GLM-4.6 (Non-reasoning)OpenZ AI	14.9	$0.98	37	4.4 s
95	—	GLM-4.7-Flash (Reasoning)OpenZ AI	14.9	$0.15	81	1.5 s
96	—	Granite 4.2 30BOpenIBM	14.8	$0.28	77	0.9 s
97	—	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek	14.8	$1.9	—	—
98	▼ 28	Gemma 4 31B (Reasoning)OpenGoogle	14.7	$0.000	36	1.1 s
99	▼ 1	DeepSeek V3.2 SpecialeOpenDeepSeek	14.5	—	—	—
100	▼ 1	K-EXAONE (Reasoning)OpenLG AI Research	14.4	—	—	—
101	▼ 1	Mistral Medium 3.5OpenMistral	14.2	$3.0	164	2.2 s
102	▼ 1	Gemma 4 12B (Reasoning)OpenGoogle	14.2	$0.15	112	2.4 s
103	▼ 1	DeepSeek V3.1 Terminus (Non-reasoning)OpenDeepSeek	13.9	$0.45	—	—
104	▼ 1	Gemma 4 31B (Non-reasoning)OpenGoogle	13.9	$0.21	41	1.9 s
105	▼ 1	DeepSeek V3.2 Exp (Non-reasoning)OpenDeepSeek	13.9	$0.32	—	—
106	▼ 1	Apriel-v1.5-15B-ThinkerOpenServiceNow	13.8	$0.000	—	—
107	▼ 1	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek	13.7	$0.84	—	—
108	—	DeepSeek V3.1 (Reasoning)OpenDeepSeek	13.5	$0.86	—	—
109	—	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	13.4	$1.3	58	3.0 s
110	—	Apriel-v1.6-15B-ThinkerOpenServiceNow	13.4	$0.000	—	—
111	—	Qwen3.5 9B (Non-reasoning)OpenAlibaba	13.3	$0.19	100	0.8 s
112	New	EXAONE 4.5 33B (Reasoning)OpenLG AI Research	13.2	—	—	—
113	—	Command A+OpenCohere	13.1	$0.000	156	0.5 s
114	—	Gemma 4 26B A4B (Non-reasoning)OpenGoogle	13.1	$0.20	99	1.1 s
115	—	Qwen3.5 4B (Reasoning)OpenAlibaba	13.1	$0.060	19	0.9 s
116	—	DeepSeek R1 0528 (May '25)OpenDeepSeek	13.1	$1.8	—	—
117	—	Nemotron 3.5 LightningOpenNVIDIA	12.9	$0.095	299	0.6 s
118	—	Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	12.8	$0.45	156	1.3 s
119	—	GLM-4.5 (Reasoning)OpenZ AI	12.8	—	—	—
120	—	Kimi K2OpenKimi	12.7	$1.0	53	1.5 s
121	—	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba	12.7	$0.75	65	2.7 s
122	—	MiniCPM5-2BOpenOpenBMB	12.5	—	—	—
123	—	Seed-OSS-36B-InstructOpenByteDance Seed	12.1	$0.30	41	2.9 s
124	—	Qwen3 235B A22B 2507 InstructOpenAlibaba	12.0	$0.40	61	2.4 s
125	—	Qwen3 Coder 480B A35B InstructOpenAlibaba	11.9	$3.0	50	3.0 s
126	—	Qwen3 VL 32B (Reasoning)OpenAlibaba	11.9	$0.28	91	2.7 s
127	New	HyperNova 60B 2605 (High, Based on gpt-oss-120b)OpenMultiverse Computing	11.7	—	—	—
128	—	MiniMax M1 80kOpenMiniMax	11.7	$0.96	—	—
129	—	Nemotron Cascade 2 30B A3BOpenNVIDIA	11.7	—	—	—
130	New	gpt-oss-120b (High)OpenOpenAI	11.6	$0.26	193	0.8 s
131	—	K2 Think V2OpenInstitute of Foundation Models	11.5	—	—	—
132	—	LongCat Flash LiteOpenLongCat	11.5	—	—	—
133	—	DeepSeek R1 (Jan '25)OpenDeepSeek	11.4	$2.5	—	—
134	—	HyperCLOVA X SEED Think (32B)OpenNaver	11.4	—	—	—
135	—	Mistral Small 4 (Reasoning)OpenMistral	11.3	$0.26	177	0.7 s
136	—	GLM-4.6V (Reasoning)OpenZ AI	11.2	$0.45	88	3.4 s
137	—	K-EXAONE (Non-reasoning)OpenLG AI Research	11.2	—	—	—
138	—	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	11.2	$0.41	194	2.3 s
139	▼ 32	Qwen3.5 9B (Reasoning)OpenAlibaba	11.2	$0.15	72	0.9 s
140	▼ 1	GLM-4.5-AirOpenZ AI	11.1	$0.37	80	2.4 s
141	▼ 1	Granite 4.2 8BOpenIBM	11.1	$0.11	49	1.0 s
142	▼ 51	Ling 3.0 TinyOpenInclusionAI	11.1	$0.000	53	2.6 s
143	▼ 2	Ring-1TOpenInclusionAI	10.9	—	—	—
144	▼ 2	G9v3-3BOpenAI9Stars	10.8	$0.000	—	—
145	▼ 2	Trinity Large ThinkingOpenArcee AI	10.8	$0.39	335	1.3 s
146	▼ 2	Qwen3.5 4B (Non-reasoning)OpenAlibaba	10.8	$0.060	15	0.9 s
147	New	INTELLECT-3 (Based on GLM-4.5-Air)OpenPrime Intellect	10.6	—	—	—
148	▼ 2	GLM-4.7-Flash (Non-reasoning)OpenZ AI	10.6	$0.15	116	1.5 s
149	▼ 2	Solar Open 100B (Reasoning)OpenUpstage	10.4	—	—	—
150	▼ 2	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	10.3	$0.42	269	0.4 s
151	New	gpt-oss-120b (Low)OpenOpenAI	10.2	$0.25	214	0.8 s
152	▼ 2	Llama 4 MaverickOpenMeta	10.0	$0.42	68	1.2 s
153	▼ 2	MiniMax M1 40kOpenMiniMax	10.0	—	—	—
154	New	gpt-oss-20b (Low)OpenOpenAI	10.0	$0.11	257	0.9 s
155	▼ 2	Qwen3 VL 235B A22B InstructOpenAlibaba	9.9	$0.70	53	2.7 s
156	▼ 2	North Mini CodeOpenCohere	9.9	$0.000	90	0.4 s
157	New	K2-V2 (High)OpenInstitute of Foundation Models	9.9	—	—	—
158	▼ 2	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba	9.8	$0.75	146	2.4 s
159	▼ 2	DeepSeek V3 0324OpenDeepSeek	9.7	$0.41	—	—
160	▼ 2	Ling 2.6 FlashOpenInclusionAI	9.7	—	—	—
161	▼ 2	Qwen3 Next 80B A3B InstructOpenAlibaba	9.6	$0.41	178	2.2 s
162	▼ 2	Tri-21B-think PreviewOpenTrillion Labs	9.6	—	—	—
163	▼ 2	Qwen3 Coder 30B A3B InstructOpenAlibaba	9.6	$0.90	87	2.7 s
164	▼ 2	DiffusionGemma 26B A4BOpenGoogle	9.5	—	—	—
165	▼ 2	Qwen3 235B A22B (Reasoning)OpenAlibaba	9.5	$2.6	63	2.7 s
166	▼ 2	QwQ 32BOpenAlibaba	9.5	$0.75	—	—
167	▼ 2	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	9.5	$0.75	113	2.2 s
168	▼ 2	Gemma 4 12B (Non-reasoning)OpenGoogle	9.4	$0.15	112	2.4 s
169	▼ 2	Mistral Large 3OpenMistral	9.3	$0.75	81	1.0 s
170	▼ 2	Qwen3 Coder NextOpenAlibaba	9.2	$0.56	100	1.3 s
171	▼ 2	Ling-1TOpenInclusionAI	9.2	—	—	—
172	▼ 2	Granite 4.2 3BOpenIBM	9.1	$0.053	221	0.5 s
173	New	K2-V2 (Medium)OpenInstitute of Foundation Models	9.0	—	—	—
174	▼ 2	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA	9.0	—	—	—
175	▼ 2	Mistral Small 4 (Non-reasoning)OpenMistral	9.0	$0.26	166	0.7 s
176	▼ 2	Tri-21B-ThinkOpenTrillion Labs	9.0	—	—	—
177	New	gpt-oss-20b (High)OpenOpenAI	9.0	$0.098	200	0.8 s
178	▼ 2	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA	8.9	—	—	—
179	▼ 2	Gemma 4 E4B (Reasoning)OpenGoogle	8.9	$0.040	39	1.2 s
180	▼ 2	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA	8.9	$0.088	210	1.0 s
181	▼ 2	Qwen3 4B 2507 (Reasoning)OpenAlibaba	8.8	—	—	—
182	▼ 2	MiniCPM5-1B (Reasoning)OpenOpenBMB	8.8	—	—	—
183	New	Sarvam 105B (High)OpenSarvam	8.8	$0.074	—	—
184	▼ 2	Devstral Small (May '25)OpenMistral	8.7	—	—	—
185	▼ 2	MiniCPM5-1B (Non-reasoning)OpenOpenBMB	8.7	—	—	—
186	▼ 2	Devstral 2OpenMistral	8.6	—	—	—
187	▼ 2	Magistral Small 1.2OpenMistral	8.6	$0.75	—	—
188	▼ 2	Qwen3 32B (Reasoning)OpenAlibaba	8.6	$0.28	107	2.5 s
189	▼ 2	DeepSeek V3 (Dec '24)OpenDeepSeek	8.5	$0.46	—	—
190	▼ 2	Nanbeige4.1-3BOpenNanbeige	8.4	—	—	—
191	▼ 2	LFM2.5-2.6BOpenLiquid AI	8.4	$0.000	—	—
192	▼ 2	Qwen3 VL 32B InstructOpenAlibaba	8.4	$0.28	71	2.7 s
193	▼ 2	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	8.4	—	—	—
194	▼ 2	GLM-4.6V (Non-reasoning)OpenZ AI	8.4	$0.45	90	3.5 s
195	▼ 2	Qwen3 235B A22B (Non-reasoning)OpenAlibaba	8.3	$1.2	64	2.7 s
196	▼ 2	Mistral Small 3.2OpenMistral	8.2	$0.11	—	—
197	▼ 2	Magistral Small 1OpenMistral	8.2	—	—	—
198	▼ 2	EXAONE 4.0 32B (Reasoning)OpenLG AI Research	8.2	—	—	—
199	▼ 2	Qwen3 VL 8B (Reasoning)OpenAlibaba	8.2	$0.66	115	2.3 s
200	▼ 2	Qwen3 14B (Reasoning)OpenAlibaba	8.2	$1.3	63	2.8 s
201	▼ 2	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	8.1	—	—	—
202	▼ 2	Llama 4 ScoutOpenMeta	8.1	$0.31	78	0.9 s
203	▼ 2	Qwen3 VL 30B A3B InstructOpenAlibaba	7.9	$0.35	113	2.2 s
204	▼ 2	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research	7.9	—	—	—
205	▼ 2	DeepSeek R1 Distill Llama 70BOpenDeepSeek	7.9	$0.80	—	—
206	▼ 2	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	7.8	—	—	—
207	▼ 2	Falcon-H1R-7BOpenTII UAE	7.8	—	—	—
208	▼ 2	Ling-flash-2.0OpenInclusionAI	7.8	$0.25	5	2.5 s
209	▼ 2	Gemma 4 E2B (Reasoning)OpenGoogle	7.8	—	—	—
210	▼ 2	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	7.8	$0.43	103	1.9 s
211	▼ 2	Qwen2.5 Instruct 72BOpenAlibaba	7.7	$0.48	—	—
212	▼ 2	Step3 VL 10BOpenStepFun	7.7	—	—	—
213	▼ 2	Llama 3.3 Instruct 70BOpenMeta	7.7	$0.71	82	1.7 s
214	▼ 2	Qwen3 30B A3B (Reasoning)OpenAlibaba	7.6	$0.75	109	2.2 s
215	▼ 2	Devstral Small (Jul '25)OpenMistral	7.6	—	—	—
216	▼ 2	QwQ 32B-PreviewOpenAlibaba	7.6	—	—	—
217	▼ 2	GLM-4.5V (Reasoning)OpenZ AI	7.6	$0.90	47	2.8 s
218	▼ 2	Mistral Large 2 (Nov '24)OpenMistral	7.6	—	—	—
219	▼ 2	Devstral Small 2OpenMistral	7.5	—	—	—
220	▼ 2	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	7.5	—	—	—
221	▼ 2	Qwen3 30B A3B 2507 InstructOpenAlibaba	7.5	$0.35	145	1.9 s
222	▼ 2	ERNIE 4.5 300B A47BOpenBaidu	7.5	$0.49	—	—
223	▼ 2	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research	7.5	$1.5	42	2.3 s
224	▼ 2	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA	7.5	—	—	—
225	▼ 2	Gemma 4 E4B (Non-reasoning)OpenGoogle	7.5	$0.040	37	0.9 s
226	▼ 2	Granite 4.1 30BOpenIBM	7.4	—	—	—
227	▼ 2	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA	7.4	$0.070	16	62 s
228	▼ 2	Hermes 4 - Llama-3.1 405B (Non-reasoning)OpenNous Research	7.4	$1.5	43	2.3 s
229	▼ 1	Llama Nemotron Super 49B v1.5 (Non-reasoning)OpenNVIDIA	7.4	—	—	—
230	▼ 1	Qwen3 32B (Non-reasoning)OpenAlibaba	7.3	$0.28	107	2.5 s
231	New	K2-V2 (Low)OpenInstitute of Foundation Models	7.3	—	—	—
232	▼ 1	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	7.3	—	—	—
233	▼ 1	Kimi Linear 48B A3B InstructOpenKimi	7.3	—	—	—
234	▼ 1	Llama 3.1 Instruct 405BOpenMeta	7.3	—	—	—
235	▼ 1	Qwen3 8B (Reasoning)OpenAlibaba	7.3	$0.66	42	3.7 s
236	▼ 1	Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)OpenNVIDIA	7.3	—	—	—
237	▼ 1	Qwen3 VL 8B InstructOpenAlibaba	7.3	$0.31	120	2.3 s
238	▼ 1	Qwen3 4B (Reasoning)OpenAlibaba	7.2	—	—	—
239	▼ 1	LFM2.5-8B-A1BOpenLiquid AI	7.2	—	—	—
240	▼ 1	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	7.2	—	—	—
241	▼ 1	Ring-flash-2.0OpenInclusionAI	7.2	$0.25	—	—
242	▼ 1	Pixtral LargeOpenMistral	7.1	—	—	—
243	▼ 1	Olmo 3.1 32B ThinkOpenAllen Institute for AI	7.1	$0.000	—	—
244	▼ 1	Mistral Small 3.1OpenMistral	7.1	$0.13	—	—
245	▼ 1	Grok 2 (Dec '24)OpenSpaceXAI	7.1	—	—	—
246	▼ 1	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.0	—	—	—
247	▼ 1	Command AOpenCohere	7.0	$4.4	64	1.7 s
248	▼ 1	Qwen3.5 2B (Reasoning)OpenAlibaba	6.9	—	—	—
249	▼ 1	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	6.9	—	—	—
250	▼ 1	Llama 3.1 Instruct 8BOpenMeta	6.9	$0.028	140	0.8 s
251	▼ 1	Qwen2.5 Instruct 32BOpenAlibaba	6.9	—	—	—
252	▼ 1	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)OpenNVIDIA	6.8	$0.088	237	0.9 s
253	▼ 1	NVIDIA Nemotron Nano 9B V2 (Non-reasoning)OpenNVIDIA	6.8	$0.086	92	8.7 s
254	▼ 1	Mistral Large 2 (Jul '24)OpenMistral	6.8	$3.0	—	—
255	▼ 1	Qwen3 4B 2507 InstructOpenAlibaba	6.7	—	—	—
256	▼ 1	Qwen2.5 Coder Instruct 32BOpenAlibaba	6.7	—	—	—
257	▼ 1	Qwen3 14B (Non-reasoning)OpenAlibaba	6.7	$0.61	63	2.7 s
258	▼ 1	GLM-4.5V (Non-reasoning)OpenZ AI	6.7	$0.90	54	2.8 s
259	▼ 1	Mistral Small 3OpenMistral	6.7	$0.058	—	—
260	▼ 1	Hermes 4 - Llama-3.1 70B (Non-reasoning)OpenNous Research	6.7	—	—	—
261	▼ 1	Qwen3 30B A3B (Non-reasoning)OpenAlibaba	6.6	$0.35	107	2.2 s
262	▼ 1	DeepSeek-V2.5 (Dec '24)OpenDeepSeek	6.6	—	—	—
263	▼ 1	Qwen3 4B (Non-reasoning)OpenAlibaba	6.6	—	—	—
264	▼ 1	Llama 3.1 Instruct 70BOpenMeta	6.6	$0.56	42	1.9 s
265	▼ 1	Granite 4.1 8BOpenIBM	6.6	—	—	—
266	New	Sarvam 30B (High)OpenSarvam	6.6	$0.047	—	—
267	▼ 1	DeepSeek-V2.5OpenDeepSeek	6.6	—	—	—
268	▼ 1	Olmo 3.1 32B InstructOpenAllen Institute for AI	6.5	—	—	—
269	▼ 1	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.5	—	—	—
270	▼ 1	Gemma 4 E2B (Non-reasoning)OpenGoogle	6.5	—	—	—
271	▼ 1	Olmo 3 32B ThinkOpenAllen Institute for AI	6.5	—	—	—
272	▼ 1	R1 1776OpenPerplexity	6.4	—	—	—
273	▼ 1	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.4	—	—	—
273	▼ 1	Solar MiniOpenUpstage	6.4	$0.15	—	—
275	▼ 1	Grok-1OpenSpaceXAI	6.3	—	—	—
276	▼ 1	Qwen2 Instruct 72BOpenAlibaba	6.3	—	—	—
277	▼ 1	Phi-4 Mini InstructOpenMicrosoft	6.3	$0.000	45	0.8 s
278	▼ 1	EXAONE 4.0 32B (Non-reasoning)OpenLG AI Research	6.3	—	—	—
279	▼ 1	Qwen3.5 2B (Non-reasoning)OpenAlibaba	6.2	—	—	—
280	▼ 1	Qwen3.5 0.8B (Reasoning)OpenAlibaba	6.1	—	—	—
281	▼ 1	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	6.1	—	—	—
282	▼ 1	Jamba 1.7 LargeOpenAI21 Labs	6.1	—	—	—
283	▼ 1	Granite 4.0 H SmallOpenIBM	6.0	$0.11	14	36 s
284	▼ 1	Ministral 3 14BOpenMistral	6.0	$0.20	89	1.0 s
285	▼ 1	Jamba 1.5 LargeOpenAI21 Labs	6.0	$3.5	—	—
286	▼ 1	Qwen3 Omni 30B A3B InstructOpenAlibaba	6.0	$0.43	97	1.9 s
287	▼ 1	Hermes 3 - Llama-3.1 70BOpenNous Research	6.0	$0.70	31	2.2 s
288	▼ 1	Qwen3 8B (Non-reasoning)OpenAlibaba	6.0	$0.31	42	3.6 s
289	▼ 1	DeepSeek-Coder-V2OpenDeepSeek	6.0	—	—	—
290	▼ 1	OLMo 2 32BOpenAllen Institute for AI	6.0	—	—	—
291	▼ 1	Jamba 1.6 LargeOpenAI21 Labs	6.0	—	—	—
292	▼ 1	LFM2 24B A2BOpenLiquid AI	5.9	—	—	—
293	▼ 1	Phi-4OpenMicrosoft	5.9	$0.22	38	2.6 s
294	▼ 1	Granite 4.1 3BOpenIBM	5.9	—	—	—
295	▼ 1	Mistral Small (Sep '24)OpenMistral	5.8	—	—	—
296	▼ 1	Phi-3 Mini Instruct 3.8BOpenMicrosoft	5.8	—	—	—
297	▼ 1	NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)OpenNVIDIA	5.8	$0.30	197	1.1 s
298	▼ 1	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	5.8	—	—	—
299	▼ 1	Phi-4 Multimodal InstructOpenMicrosoft	5.8	$0.000	—	—
300	▼ 1	Qwen2.5 Coder Instruct 7BOpenAlibaba	5.8	—	—	—
301	▼ 1	Mixtral 8x22B InstructOpenMistral	5.7	—	—	—
302	▼ 1	Llama 2 Chat 7BOpenMeta	5.7	$0.10	—	—
303	▼ 1	Llama 3.2 Instruct 3BOpenMeta	5.7	—	—	—
304	▼ 1	MiniCPM-V 4.6 1.3BOpenOpenBMB	5.7	—	—	—
305	▼ 1	Jamba Reasoning 3BOpenAI21 Labs	5.7	—	—	—
306	▼ 1	Qwen3 VL 4B InstructOpenAlibaba	5.7	—	—	—
307	▼ 1	Qwen1.5 Chat 110BOpenAlibaba	5.7	—	—	—
308	▼ 1	Reka Flash 3OpenReka AI	5.6	$0.35	91	1.3 s
309	▼ 1	Olmo 3 7B ThinkOpenAllen Institute for AI	5.6	—	—	—
310	▼ 1	OLMo 2 7BOpenAllen Institute for AI	5.6	—	—	—
311	▼ 1	Molmo 7B-DOpenAllen Institute for AI	5.6	—	—	—
312	▼ 1	Ling-mini-2.0OpenInclusionAI	5.5	—	—	—
313	▼ 1	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	5.5	—	—	—
314	▼ 1	DeepSeek-V2-ChatOpenDeepSeek	5.5	—	—	—
315	▼ 1	Ministral 3 8BOpenMistral	5.5	$0.15	97	0.7 s
316	▼ 1	Llama 3 Instruct 70BOpenMeta	5.5	$1.2	—	—
317	▼ 1	Arctic InstructOpenSnowflake	5.4	—	—	—
317	▼ 1	Qwen Chat 72BOpenAlibaba	5.4	—	—	—
319	▼ 1	Llama 3.2 Instruct 11B (Vision)OpenMeta	5.4	$0.35	16	3.0 s
320	▼ 1	Qwen3.5 0.8B (Non-reasoning)OpenAlibaba	5.4	—	—	—
321	▼ 1	DeepSeek Coder V2 Lite InstructOpenDeepSeek	5.3	—	—	—
322	New	Sarvam M (Reasoning, Based on Mistral Small 3.1)OpenSarvam	5.3	$0.000	—	—
323	▼ 1	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	5.3	—	—	—
323	▼ 1	Llama 2 Chat 70BOpenMeta	5.3	—	—	—
325	▼ 1	Llama 2 Chat 13BOpenMeta	5.3	—	—	—
326	▼ 1	Command-R+ (Apr '24)OpenCohere	5.3	—	—	—
327	▼ 1	OpenChat 3.5 (1210)OpenOpenChat	5.3	—	—	—
328	▼ 1	DBRX InstructOpenDatabricks	5.3	—	—	—
329	▼ 1	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research	5.3	—	—	—
330	▼ 1	Olmo 3 7B InstructOpenAllen Institute for AI	5.2	$0.13	—	—
331	▼ 1	Exaone 4.0 1.2B (Non-reasoning)OpenLG AI Research	5.2	—	—	—
332	▼ 1	LFM2.5-1.2B-ThinkingOpenLiquid AI	5.2	—	—	—
333	▼ 1	Jamba 1.7 MiniOpenAI21 Labs	5.2	—	—	—
334	▼ 1	LFM2 2.6BOpenLiquid AI	5.2	—	—	—
335	▼ 1	LFM2.5-1.2B-InstructOpenLiquid AI	5.2	—	—	—
336	▼ 1	Jamba 1.5 MiniOpenAI21 Labs	5.2	$0.25	—	—
337	▼ 1	Granite 4.0 H 1BOpenIBM	5.2	—	—	—
338	▼ 1	Qwen3 1.7B (Reasoning)OpenAlibaba	5.2	—	—	—
339	▼ 1	Jamba 1.6 MiniOpenAI21 Labs	5.2	—	—	—
340	▼ 1	Mixtral 8x7B InstructOpenMistral	5.1	$0.51	—	—
341	▼ 1	Gemma 3 270MOpenGoogle	5.1	—	—	—
342	▼ 1	Apertus 70B InstructOpenSwiss AI Initiative	5.1	$1.3	—	—
343	▼ 1	Granite 4.0 MicroOpenIBM	5.1	—	—	—
344	▼ 1	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	5.1	—	—	—
345	▼ 1	Command-R (Mar '24)OpenCohere	5.0	—	—	—
345	▼ 1	Llama 65BOpenMeta	5.0	—	—	—
345	▼ 1	Mistral 7B InstructOpenMistral	5.0	$0.16	—	—
345	▼ 1	Qwen Chat 14BOpenAlibaba	5.0	—	—	—
349	▼ 1	Granite 4.0 1BOpenIBM	5.0	—	—	—
350	▼ 1	Molmo2-8BOpenAllen Institute for AI	5.0	—	—	—
351	▼ 1	LFM2 8B A1BOpenLiquid AI	4.9	—	—	—
352	▼ 1	Granite 3.3 8B (Non-reasoning)OpenIBM	4.9	$0.085	—	—
353	▼ 1	Qwen3 1.7B (Non-reasoning)OpenAlibaba	4.9	—	—	—
354	▼ 1	Gemma 3 27B InstructOpenGoogle	4.9	$0.000	—	—
355	▼ 1	Ministral 3 3BOpenMistral	4.8	$0.10	233	0.7 s
356	▼ 1	Apertus 8B InstructOpenSwiss AI Initiative	4.8	$0.13	—	—
356	▼ 1	Gemma 3 1B InstructOpenGoogle	4.8	$0.000	—	—
356	▼ 1	Gemma 3 4B InstructOpenGoogle	4.8	$0.000	—	—
356	▼ 1	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
356	▼ 1	Gemma 3n E4B InstructOpenGoogle	4.8	—	—	—
356	▼ 1	Granite 4.0 350MOpenIBM	4.8	—	—	—
356	▼ 1	Granite 4.0 H 350MOpenIBM	4.8	—	—	—
356	▼ 1	LFM2 1.2BOpenLiquid AI	4.8	—	—	—
356	▼ 1	LFM2.5-VL-1.6BOpenLiquid AI	4.8	—	—	—
356	▼ 1	Llama 3 Instruct 8BOpenMeta	4.8	$0.070	—	—
356	▼ 1	Llama 3.2 Instruct 1BOpenMeta	4.8	—	—	—
356	▼ 1	Qwen3 0.6B (Non-reasoning)OpenAlibaba	4.8	—	—	—
356	▼ 1	Qwen3 0.6B (Reasoning)OpenAlibaba	4.8	—	—	—
356	▼ 1	Tiny Aya GlobalOpenCohere	4.8	$0.000	—	—
370	▼ 143	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	4.8	—	—	—
371	▼ 2	Gemma 3 12B InstructOpenGoogle	3.8	$0.000	—	—
372	▼ 2	K2 Horizon 0.9BOpenInstitute of Foundation Models	3.0	—	—	—

322 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