Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	New	MiMo-V2.6-ProOpenXiaomi	46.3	$0.54	44	3.8 s
2	▼ 1	GLM-5.3 (max)OpenZ AI	44.8	$2.2	91	2.6 s
3	▼ 1	Kimi K3 (max)OpenKimi	43.6	$6.0	—	—
4	▼ 1	GLM 5.3 FlashOpenZ AI	41.8	$0.24	54	3.2 s
5	▼ 1	Qwen3.8 2.4T A95BOpenAlibaba	39.9	$3.0	38	3.1 s
6	▼ 1	Qwen3.8-Flash-NextOpenAlibaba	39.8	$0.23	58	2.6 s
7	▼ 1	DeepSeek V4.1 Flash (Reasoning, Max Effort)OpenDeepSeek	39.5	$0.52	220	1.2 s
8	New	MiMo-V2.6-FlashOpenXiaomi	37.9	$0.18	59	3.5 s
9	▼ 2	DeepSeek V4 Pro 0813 (Reasoning, Max Effort)OpenDeepSeek	36.0	$2.0	104	1.6 s
10	▼ 2	Kimi K3 (low)OpenKimi	34.5	$6.0	—	—
11	▼ 2	DeepSeek V4 Flash 0731 (Reasoning, Max Effort)OpenDeepSeek	34.3	$0.66	229	1.1 s
12	New	GLM-5.3 (low)OpenZ AI	34.3	$2.2	84	3.0 s
13	▼ 3	GLM-5.2 (max)OpenZ AI	33.7	$2.2	84	3.2 s
14	▼ 3	Qwen3.8 27B (xhigh)OpenAlibaba	33.7	$1.1	47	3.8 s
15	▼ 3	Motif 3OpenMotif Technologies	33.6	—	—	—
16	▼ 3	K2 Horizon 375B A23BOpenInstitute of Foundation Models	30.5	—	—	—
17	▼ 3	DeepSeek V4 Pro 0424 (Reasoning, Max Effort)OpenDeepSeek	30.4	$0.54	111	1.5 s
18	▼ 3	DeepSeek V4 Pro 0424 (Reasoning, High Effort)OpenDeepSeek	30.1	$0.54	104	1.8 s
19	▼ 3	MiniMax-M3OpenMiniMax	29.2	$0.52	175	1.1 s
20	▼ 3	Nex-N2-Pro (based on Qwen3.5-397B-A17B)OpenNex AGI	28.2	—	—	—
21	▼ 3	GLM-5 (Reasoning)OpenZ AI	27.9	$1.6	85	1.5 s
22	▼ 3	Inkling SmallOpenThinking Machines	27.8	$0.52	210	2.1 s
23	▼ 3	Qwen3.8 27B (medium)OpenAlibaba	27.6	$1.1	56	3.8 s
24	▼ 3	Kimi K2.6OpenKimi	27.0	$1.7	—	—
25	▼ 2	Qwen3.8 27B (low)OpenAlibaba	26.2	$1.1	57	3.8 s
26	▼ 2	GLM-5.1 (Reasoning)OpenZ AI	26.1	$2.0	75	1.7 s
27	▼ 2	DeepSeek V4 Flash 0420 (Reasoning, High Effort)OpenDeepSeek	26.0	$0.17	—	—
28	▼ 2	MiMo-V2.5-ProOpenXiaomi	26.0	$0.54	38	2.3 s
29	▼ 2	Kimi K2.7 CodeOpenKimi	25.8	$1.7	—	—
30	▼ 2	K2 Horizon MoVA 36B A4BOpenInstitute of Foundation Models	25.3	—	—	—
31	▼ 2	Hy3OpenTencent	25.3	$0.25	87	3.0 s
32	▼ 2	MiMo-V2.5OpenXiaomi	25.2	$0.18	46	26 s
33	▼ 2	Inkling (xhigh)OpenThinking Machines	25.0	$1.8	191	1.8 s
34	▼ 2	Ling 3.0 FlashOpenInclusionAI	24.9	$0.11	368	3.0 s
35	▼ 2	Solar Open2 250BOpenUpstage	24.7	—	—	—
36	New	DeepSeek V4.1 Flash (Non-Reasoning)OpenDeepSeek	24.7	$0.52	239	1.1 s
37	▼ 3	Ling-3.0-flash-VLOpenInclusionAI	24.6	$0.11	145	1.9 s
38	▼ 3	GLM-5.1 (Non-reasoning)OpenZ AI	24.2	$2.1	71	1.7 s
39	▼ 3	DeepSeek V4 Flash 0420 (Reasoning, Max Effort)OpenDeepSeek	24.2	$0.17	—	—
40	▼ 3	Kimi K2.6 (Non-reasoning)OpenKimi	23.6	$1.7	—	—
41	▼ 3	Kimi K2.5 (Reasoning)OpenKimi	23.5	$1.1	—	—
42	▼ 3	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	22.9	$1.1	204	1.1 s
43	▼ 3	Qwen3.5 27B (Reasoning)OpenAlibaba	22.9	$0.83	79	5.6 s
44	▼ 3	MiniMax-M2.5OpenMiniMax	22.8	$0.52	97	1.5 s
45	▼ 3	MiniMax-M2.7OpenMiniMax	22.8	$0.52	68	1.6 s
46	▼ 3	Hy3-preview (Reasoning)OpenTencent	22.7	$0.100	—	—
47	▼ 3	A.X-K2OpenSK Telecom	22.7	—	—	—
48	▼ 3	Ling-3.0-flash-FinOpenInclusionAI	22.6	$0.11	161	1.7 s
49	▼ 3	MiMo-V2-Flash (Feb 2026)OpenXiaomi	22.4	—	—	—
50	▼ 3	GLM-5.2 (Non-reasoning)OpenZ AI	22.4	$2.2	172	1.1 s
51	▼ 2	GLM-4.7 (Reasoning)OpenZ AI	22.2	$1.0	101	1.1 s
52	▼ 2	Kimi K2 ThinkingOpenKimi	22.0	$1.1	125	1.3 s
53	▼ 2	G9v3-39A5BOpenAI9Stars	21.8	$0.000	—	—
54	▼ 2	GLM-5 (Non-reasoning)OpenZ AI	21.8	$1.6	79	1.6 s
55	▼ 2	DeepSeek V3.2 (Reasoning)OpenDeepSeek	21.5	$0.32	—	—
56	▼ 2	Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba	21.4	$1.4	93	2.3 s
57	▼ 2	Qwen3.6 27B (Reasoning)OpenAlibaba	21.4	$1.4	59	3.8 s
58	▼ 2	MiniMax-M2.1OpenMiniMax	20.9	$0.52	102	1.4 s
59	▼ 2	DeepSeek V4 Pro 0424 (Non-reasoning)OpenDeepSeek	20.8	$0.54	96	1.6 s
60	▼ 2	MiMo-V2-Flash (Reasoning)OpenXiaomi	20.8	$0.15	—	—
61	▼ 2	K2 Horizon 7BOpenInstitute of Foundation Models	20.6	—	—	—
62	▼ 14	Qwen3.8 27B (Non-reasoning)OpenAlibaba	20.2	$1.1	55	3.8 s
63	▼ 3	Qwen3.6 27B (Non-reasoning)OpenAlibaba	19.8	$1.4	62	3.7 s
64	▼ 3	K-EXAONE 2.0 0803OpenLG AI Research	19.7	—	—	—
65	▼ 3	Step 3.7 FlashOpenStepFun	19.5	$0.44	191	2.5 s
66	▼ 3	Kimi K2.5 (Non-reasoning)OpenKimi	19.4	$1.2	—	—
67	▼ 3	Qwen3.5 27B (Non-reasoning)OpenAlibaba	19.4	$0.83	89	5.6 s
68	▼ 3	Qwen3.5 35B A3B (Reasoning)OpenAlibaba	19.3	$0.69	142	2.2 s
69	▼ 3	LongCat 2.0OpenLongCat	19.1	$0.52	—	—
70	▼ 3	Gemma 4 31B (Reasoning)OpenGoogle	19.0	$0.000	35	1.0 s
71	▼ 3	DeepSeek V4 Flash 0420 (Non-reasoning)OpenDeepSeek	18.9	$0.12	—	—
72	▼ 3	MiniMax-M2OpenMiniMax	18.6	$0.52	99	1.4 s
73	▼ 3	GLM-4.6 (Reasoning)OpenZ AI	18.5	$0.96	36	4.2 s
74	▼ 3	Qwen3.5 397B A17B (Reasoning)OpenAlibaba	18.4	$1.4	94	2.3 s
75	▼ 3	MiMo-V2.5-Pro (Non-reasoning)OpenXiaomi	18.3	$0.54	30	2.4 s
76	▼ 3	Qwen3.6 35B A3B (Reasoning)OpenAlibaba	18.2	$0.84	126	2.1 s
77	▼ 3	Qwen3.5 122B A10B (Non-reasoning)OpenAlibaba	17.7	$1.1	146	2.3 s
78	▼ 3	Muse Glimmer (high)OpenMeta	17.5	$0.58	122	1.3 s
79	▼ 3	GLM-4.7 (Non-reasoning)OpenZ AI	17.4	$1.0	98	1.2 s
80	▼ 3	Hy3-preview (Non-reasoning)OpenTencent	17.0	$0.100	—	—
81	▼ 3	Ling-2.6-1TOpenInclusionAI	17.0	$0.85	—	—
82	▼ 3	Gemma 4 26B A4B (Reasoning)OpenGoogle	16.7	$0.17	—	—
83	▼ 3	Ring-2.6-1TOpenInclusionAI	16.6	$0.85	126	4.0 s
84	▼ 3	Step 3.5 FlashOpenStepFun	16.6	$0.15	143	3.3 s
85	▼ 3	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek	16.6	$0.32	—	—
86	▼ 3	MiMo-V2-Flash (Non-reasoning)OpenXiaomi	16.0	—	—	—
87	▼ 3	DeepSeek V3.2 (Non-reasoning)OpenDeepSeek	16.0	$0.32	—	—
88	▼ 3	K2 Horizon 3.7BOpenInstitute of Foundation Models	15.6	—	—	—
89	▼ 3	Qwen3.5 122B A10B (Reasoning)OpenAlibaba	15.6	$1.1	135	2.4 s
90	▼ 3	Kimi K2 0905OpenKimi	15.3	$1.1	54	1.2 s
91	▼ 3	Ling 3.0 TinyOpenInclusionAI	15.3	$0.000	39	2.7 s
92	▼ 3	Qwen3.6 35B A3B (Non-reasoning)OpenAlibaba	15.2	$0.84	142	2.1 s
93	▼ 3	Qwen3.5 35B A3B (Non-reasoning)OpenAlibaba	15.1	$0.69	165	2.1 s
94	▼ 3	GLM-4.6 (Non-reasoning)OpenZ AI	14.9	$0.98	36	4.5 s
95	▼ 3	GLM-4.7-Flash (Reasoning)OpenZ AI	14.9	$0.15	74	1.5 s
96	▼ 3	Granite 4.2 30BOpenIBM	14.8	$0.28	77	0.9 s
97	▼ 3	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek	14.8	$1.9	—	—
98	▼ 3	DeepSeek V3.2 SpecialeOpenDeepSeek	14.5	—	—	—
99	▼ 3	K-EXAONE (Reasoning)OpenLG AI Research	14.4	—	—	—
100	▼ 3	Mistral Medium 3.5OpenMistral	14.2	$3.0	163	2.2 s
101	▼ 3	Gemma 4 12B (Reasoning)OpenGoogle	14.2	$0.15	114	2.5 s
102	▼ 3	DeepSeek V3.1 Terminus (Non-reasoning)OpenDeepSeek	13.9	$0.45	—	—
103	▼ 3	Gemma 4 31B (Non-reasoning)OpenGoogle	13.9	$0.21	54	2.1 s
104	▼ 3	DeepSeek V3.2 Exp (Non-reasoning)OpenDeepSeek	13.9	$0.32	—	—
105	▼ 3	Apriel-v1.5-15B-ThinkerOpenServiceNow	13.8	$0.000	—	—
106	▼ 3	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek	13.7	$0.85	—	—
107	▼ 3	Qwen3.5 9B (Reasoning)OpenAlibaba	13.7	$0.15	43	2.2 s
108	▼ 3	DeepSeek V3.1 (Reasoning)OpenDeepSeek	13.5	$0.87	—	—
109	▼ 3	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	13.4	$1.3	57	3.1 s
110	▼ 3	Apriel-v1.6-15B-ThinkerOpenServiceNow	13.4	$0.000	—	—
111	▼ 3	Qwen3.5 9B (Non-reasoning)OpenAlibaba	13.3	$0.19	86	0.8 s
112	▼ 3	EXAONE 4.5 33BOpenLG AI Research	13.2	—	—	—
113	▼ 3	Command A+OpenCohere	13.1	$0.000	209	0.4 s
114	▼ 3	Gemma 4 26B A4B (Non-reasoning)OpenGoogle	13.1	$0.20	106	1.0 s
115	▼ 3	Qwen3.5 4B (Reasoning)OpenAlibaba	13.1	$0.060	24	0.8 s
116	▼ 3	DeepSeek R1 0528 (May '25)OpenDeepSeek	13.1	$1.8	—	—
117	▼ 3	Nemotron 3.5 LightningOpenNVIDIA	12.9	$0.11	290	0.6 s
118	▼ 3	Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	12.8	$0.45	167	1.4 s
119	▼ 3	GLM-4.5 (Reasoning)OpenZ AI	12.8	—	—	—
120	▼ 3	Kimi K2OpenKimi	12.7	$1.0	53	1.5 s
121	▼ 3	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba	12.7	$0.75	60	2.8 s
122	▼ 3	MiniCPM5-2BOpenOpenBMB	12.5	—	—	—
123	▼ 3	Seed-OSS-36B-InstructOpenByteDance Seed	12.1	$0.30	41	2.8 s
124	▼ 3	Qwen3 235B A22B 2507 InstructOpenAlibaba	12.0	$0.40	60	2.4 s
125	▼ 3	Qwen3 Coder 480B A35B InstructOpenAlibaba	11.9	$3.0	51	3.1 s
126	▼ 3	Qwen3 VL 32B (Reasoning)OpenAlibaba	11.9	$0.28	90	2.7 s
127	▼ 3	HyperNova 60B 2605 (high, based on gpt-oss-120b)OpenMultiverse Computing	11.7	—	—	—
128	▼ 3	MiniMax M1 80kOpenMiniMax	11.7	$0.96	—	—
129	▼ 3	Nemotron Cascade 2 30B A3BOpenNVIDIA	11.7	—	—	—
130	▼ 3	gpt-oss-120b (high)OpenOpenAI	11.6	$0.26	231	0.9 s
131	▼ 3	K2 Think V2OpenInstitute of Foundation Models	11.5	—	—	—
132	▼ 3	LongCat Flash LiteOpenLongCat	11.5	—	—	—
133	▼ 3	DeepSeek R1 (Jan '25)OpenDeepSeek	11.4	$2.5	—	—
134	▼ 3	HyperCLOVA X SEED Think (32B)OpenNaver	11.4	—	—	—
135	▼ 3	Mistral Small 4 (Reasoning)OpenMistral	11.3	$0.26	177	0.8 s
136	▼ 3	GLM-4.6V (Reasoning)OpenZ AI	11.2	$0.45	81	3.3 s
137	▼ 3	K-EXAONE (Non-reasoning)OpenLG AI Research	11.2	—	—	—
138	▼ 3	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	11.2	$0.41	195	2.3 s
139	▼ 3	GLM-4.5-AirOpenZ AI	11.1	$0.37	74	2.4 s
140	▼ 3	Granite 4.2 8BOpenIBM	11.1	$0.11	76	0.9 s
141	▼ 3	Ring-1TOpenInclusionAI	10.9	—	—	—
142	▼ 3	G9v3-3BOpenAI9Stars	10.8	$0.000	—	—
143	▼ 3	Trinity Large ThinkingOpenArcee AI	10.8	$0.39	311	1.3 s
144	▼ 3	Qwen3.5 4B (Non-reasoning)OpenAlibaba	10.8	$0.060	23	0.8 s
145	New	INTELLECT-3 (based on GLM-4.5-Air)OpenPrime Intellect	10.6	—	—	—
146	▼ 3	GLM-4.7-Flash (Non-reasoning)OpenZ AI	10.6	$0.15	103	1.4 s
147	▼ 3	Solar Open 100B (Reasoning)OpenUpstage	10.4	—	—	—
148	▼ 3	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	10.3	$0.42	264	0.5 s
149	▼ 3	gpt-oss-120b (low)OpenOpenAI	10.2	$0.25	236	0.9 s
150	▼ 3	Llama 4 MaverickOpenMeta	10.0	$0.42	110	0.9 s
151	▼ 3	MiniMax M1 40kOpenMiniMax	10.0	—	—	—
152	▼ 3	gpt-oss-20b (low)OpenOpenAI	10.0	$0.11	233	1.0 s
153	▼ 3	Qwen3 VL 235B A22B InstructOpenAlibaba	9.9	$0.70	53	2.7 s
154	▼ 3	North Mini CodeOpenCohere	9.9	$0.000	83	0.4 s
155	▼ 3	K2-V2 (high)OpenInstitute of Foundation Models	9.9	—	—	—
156	▼ 3	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba	9.8	$0.75	143	2.4 s
157	▼ 3	DeepSeek V3 0324OpenDeepSeek	9.7	$0.93	—	—
158	▼ 3	Ling 2.6 FlashOpenInclusionAI	9.7	—	—	—
159	▼ 3	Qwen3 Next 80B A3B InstructOpenAlibaba	9.6	$0.41	183	2.2 s
160	▼ 3	Tri-21B-think PreviewOpenTrillion Labs	9.6	—	—	—
161	▼ 3	Qwen3 Coder 30B A3B InstructOpenAlibaba	9.6	$0.90	92	2.6 s
162	▼ 3	DiffusionGemma 26B A4BOpenGoogle	9.5	—	—	—
163	▼ 3	Qwen3 235B A22B (Reasoning)OpenAlibaba	9.5	$2.6	60	2.8 s
164	▼ 3	QwQ 32BOpenAlibaba	9.5	$0.75	—	—
165	▼ 3	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	9.5	$0.75	112	2.2 s
166	▼ 3	Gemma 4 12B (Non-reasoning)OpenGoogle	9.4	$0.15	124	2.4 s
167	▼ 3	Mistral Large 3OpenMistral	9.3	$0.75	78	1.0 s
168	▼ 3	Qwen3 Coder NextOpenAlibaba	9.2	$0.56	128	1.2 s
169	▼ 3	Ling-1TOpenInclusionAI	9.2	—	—	—
170	▼ 3	Granite 4.2 3BOpenIBM	9.1	$0.053	217	0.5 s
171	▼ 3	K2-V2 (medium)OpenInstitute of Foundation Models	9.0	—	—	—
172	▼ 3	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA	9.0	—	—	—
173	▼ 3	Mistral Small 4 (Non-reasoning)OpenMistral	9.0	$0.26	159	0.7 s
174	▼ 3	Tri-21B-ThinkOpenTrillion Labs	9.0	—	—	—
175	▼ 3	gpt-oss-20b (high)OpenOpenAI	9.0	$0.098	169	0.8 s
176	▼ 3	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA	8.9	—	—	—
177	▼ 3	Gemma 4 E4B (Reasoning)OpenGoogle	8.9	$0.040	59	0.8 s
178	▼ 3	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA	8.9	$0.088	185	1.0 s
179	▼ 3	Qwen3 4B 2507 (Reasoning)OpenAlibaba	8.8	—	—	—
180	▼ 3	MiniCPM5-1B (Reasoning)OpenOpenBMB	8.8	—	—	—
181	▼ 3	Sarvam 105B (high)OpenSarvam	8.8	$0.074	—	—
182	▼ 3	Devstral Small (May '25)OpenMistral	8.7	—	—	—
183	▼ 3	MiniCPM5-1B (Non-reasoning)OpenOpenBMB	8.7	—	—	—
184	▼ 3	Devstral 2OpenMistral	8.6	—	—	—
185	▼ 3	Magistral Small 1.2OpenMistral	8.6	$0.75	—	—
186	▼ 3	Qwen3 32B (Reasoning)OpenAlibaba	8.6	$0.28	106	2.5 s
187	▼ 3	DeepSeek V3 (Dec '24)OpenDeepSeek	8.5	$0.46	—	—
188	▼ 3	Nanbeige4.1-3BOpenNanbeige	8.4	—	—	—
189	▼ 3	LFM2.5-2.6BOpenLiquid AI	8.4	$0.000	—	—
190	▼ 3	Qwen3 VL 32B InstructOpenAlibaba	8.4	$0.28	72	2.6 s
191	▼ 3	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	8.4	—	—	—
192	▼ 3	GLM-4.6V (Non-reasoning)OpenZ AI	8.4	$0.45	76	3.3 s
193	▼ 3	Qwen3 235B A22B (Non-reasoning)OpenAlibaba	8.3	$1.2	60	2.7 s
194	▼ 3	Mistral Small 3.2OpenMistral	8.2	$0.11	—	—
195	▼ 3	Magistral Small 1OpenMistral	8.2	—	—	—
196	▼ 3	EXAONE 4.0 32B (Reasoning)OpenLG AI Research	8.2	—	—	—
197	▼ 3	Qwen3 VL 8B (Reasoning)OpenAlibaba	8.2	$0.66	112	2.4 s
198	▼ 3	Qwen3 14B (Reasoning)OpenAlibaba	8.2	$1.3	63	2.8 s
199	▼ 3	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	8.1	—	—	—
200	▼ 3	Llama 4 ScoutOpenMeta	8.1	$0.31	107	0.8 s
201	▼ 3	Qwen3 VL 30B A3B InstructOpenAlibaba	7.9	$0.35	111	2.2 s
202	▼ 3	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research	7.9	—	—	—
203	▼ 3	DeepSeek R1 Distill Llama 70BOpenDeepSeek	7.9	$0.80	—	—
204	▼ 3	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	7.8	—	—	—
205	▼ 3	Falcon-H1R-7BOpenTII UAE	7.8	—	—	—
206	▼ 3	Ling-flash-2.0OpenInclusionAI	7.8	$0.25	6	2.5 s
207	▼ 3	Gemma 4 E2B (Reasoning)OpenGoogle	7.8	—	—	—
208	▼ 3	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	7.8	$0.43	101	2.0 s
209	▼ 3	Qwen2.5 Instruct 72BOpenAlibaba	7.7	$0.48	—	—
210	▼ 3	Step3 VL 10BOpenStepFun	7.7	—	—	—
211	▼ 3	Llama 3.3 Instruct 70BOpenMeta	7.7	$0.71	87	1.7 s
212	▼ 3	Qwen3 30B A3B (Reasoning)OpenAlibaba	7.6	$0.75	108	2.2 s
213	▼ 3	Devstral Small (Jul '25)OpenMistral	7.6	—	—	—
214	▼ 3	QwQ 32B-PreviewOpenAlibaba	7.6	—	—	—
215	▼ 3	GLM-4.5V (Reasoning)OpenZ AI	7.6	$0.90	46	2.7 s
216	▼ 3	Mistral Large 2 (Nov '24)OpenMistral	7.6	—	—	—
217	▼ 3	Devstral Small 2OpenMistral	7.5	—	—	—
218	▼ 3	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	7.5	—	—	—
219	▼ 3	Qwen3 30B A3B 2507 InstructOpenAlibaba	7.5	$0.35	145	1.9 s
220	▼ 3	ERNIE 4.5 300B A47BOpenBaidu	7.5	$0.49	—	—
221	▼ 3	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research	7.5	$1.5	43	2.3 s
222	▼ 3	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA	7.5	—	—	—
223	▼ 3	Gemma 4 E4B (Non-reasoning)OpenGoogle	7.5	$0.040	60	0.8 s
224	▼ 3	Granite 4.1 30BOpenIBM	7.4	—	—	—
225	▼ 3	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA	7.4	$0.070	116	4.3 s
226	▼ 3	Hermes 4 - Llama-3.1 405B (Non-reasoning)OpenNous Research	7.4	$1.5	43	2.3 s
227	▼ 3	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	7.4	—	—	—
228	▼ 3	Llama Nemotron Super 49B v1.5 (Non-reasoning)OpenNVIDIA	7.4	—	—	—
229	▼ 3	Qwen3 32B (Non-reasoning)OpenAlibaba	7.3	$0.28	105	2.5 s
230	▼ 3	K2-V2 (low)OpenInstitute of Foundation Models	7.3	—	—	—
231	▼ 3	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	7.3	—	—	—
232	▼ 3	Kimi Linear 48B A3B InstructOpenKimi	7.3	—	—	—
233	▼ 3	Llama 3.1 Instruct 405BOpenMeta	7.3	—	—	—
234	▼ 3	Qwen3 8B (Reasoning)OpenAlibaba	7.3	$0.66	41	3.9 s
235	▼ 3	Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)OpenNVIDIA	7.3	—	—	—
236	▼ 3	Qwen3 VL 8B InstructOpenAlibaba	7.3	$0.31	115	2.3 s
237	▼ 3	Qwen3 4B (Reasoning)OpenAlibaba	7.2	—	—	—
238	▼ 3	LFM2.5-8B-A1BOpenLiquid AI	7.2	—	—	—
239	▼ 3	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	7.2	—	—	—
240	▼ 3	Ring-flash-2.0OpenInclusionAI	7.2	$0.25	—	—
241	▼ 3	Pixtral LargeOpenMistral	7.1	—	—	—
242	▼ 3	Olmo 3.1 32B ThinkOpenAllen Institute for AI	7.1	$0.000	—	—
243	▼ 3	Mistral Small 3.1OpenMistral	7.1	$0.13	—	—
244	▼ 3	Grok 2 (Dec '24)OpenSpaceXAI	7.1	—	—	—
245	▼ 3	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.0	—	—	—
246	▼ 3	Command AOpenCohere	7.0	$4.4	59	1.7 s
247	▼ 3	Qwen3.5 2B (Reasoning)OpenAlibaba	6.9	—	—	—
248	▼ 3	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	6.9	—	—	—
249	▼ 3	Llama 3.1 Instruct 8BOpenMeta	6.9	$0.028	136	0.9 s
250	▼ 3	Qwen2.5 Instruct 32BOpenAlibaba	6.9	—	—	—
251	▼ 3	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)OpenNVIDIA	6.8	$0.088	239	0.9 s
252	▼ 3	NVIDIA Nemotron Nano 9B V2 (Non-reasoning)OpenNVIDIA	6.8	$0.086	163	1.9 s
253	▼ 3	Mistral Large 2 (Jul '24)OpenMistral	6.8	$3.0	—	—
254	▼ 3	Qwen3 4B 2507 InstructOpenAlibaba	6.7	—	—	—
255	▼ 3	Qwen2.5 Coder Instruct 32BOpenAlibaba	6.7	—	—	—
256	▼ 3	Qwen3 14B (Non-reasoning)OpenAlibaba	6.7	$0.61	62	2.7 s
257	▼ 3	GLM-4.5V (Non-reasoning)OpenZ AI	6.7	$0.90	46	2.7 s
258	▼ 3	Mistral Small 3OpenMistral	6.7	$0.058	—	—
259	▼ 3	Hermes 4 - Llama-3.1 70B (Non-reasoning)OpenNous Research	6.7	—	—	—
260	▼ 3	Qwen3 30B A3B (Non-reasoning)OpenAlibaba	6.6	$0.35	105	2.3 s
261	▼ 3	DeepSeek-V2.5 (Dec '24)OpenDeepSeek	6.6	—	—	—
262	▼ 3	Qwen3 4B (Non-reasoning)OpenAlibaba	6.6	—	—	—
263	▼ 3	Llama 3.1 Instruct 70BOpenMeta	6.6	$0.56	52	1.7 s
264	▼ 3	Granite 4.1 8BOpenIBM	6.6	$0.063	126	0.8 s
265	▼ 3	Sarvam 30B (high)OpenSarvam	6.6	$0.047	—	—
266	▼ 3	DeepSeek-V2.5OpenDeepSeek	6.6	—	—	—
267	▼ 3	Olmo 3.1 32B InstructOpenAllen Institute for AI	6.5	—	—	—
268	▼ 3	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.5	—	—	—
269	▼ 3	Gemma 4 E2B (Non-reasoning)OpenGoogle	6.5	—	—	—
270	▼ 3	Olmo 3 32B ThinkOpenAllen Institute for AI	6.5	—	—	—
271	▼ 3	R1 1776OpenPerplexity	6.4	—	—	—
272	▼ 3	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.4	—	—	—
272	▼ 3	Solar MiniOpenUpstage	6.4	$0.15	—	—
274	▼ 3	Grok-1OpenSpaceXAI	6.3	—	—	—
275	▼ 3	Qwen2 Instruct 72BOpenAlibaba	6.3	—	—	—
276	▼ 3	Phi-4 Mini InstructOpenMicrosoft	6.3	$0.000	45	0.8 s
277	▼ 3	EXAONE 4.0 32B (Non-reasoning)OpenLG AI Research	6.3	—	—	—
278	▼ 3	Qwen3.5 2B (Non-reasoning)OpenAlibaba	6.2	—	—	—
279	▼ 3	Qwen3.5 0.8B (Reasoning)OpenAlibaba	6.1	—	—	—
280	▼ 3	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	6.1	—	—	—
281	▼ 3	Jamba 1.7 LargeOpenAI21 Labs	6.1	—	—	—
282	▼ 3	Granite 4.0 H SmallOpenIBM	6.0	$0.11	15	36 s
283	▼ 3	Ministral 3 14BOpenMistral	6.0	$0.20	87	0.9 s
284	▼ 3	Jamba 1.5 LargeOpenAI21 Labs	6.0	$3.5	—	—
285	▼ 3	Qwen3 Omni 30B A3B InstructOpenAlibaba	6.0	$0.43	96	1.9 s
286	▼ 3	Hermes 3 - Llama-3.1 70BOpenNous Research	6.0	$0.70	30	2.2 s
287	▼ 3	Qwen3 8B (Non-reasoning)OpenAlibaba	6.0	$0.31	41	3.8 s
288	▼ 3	DeepSeek-Coder-V2OpenDeepSeek	6.0	—	—	—
289	▼ 3	OLMo 2 32BOpenAllen Institute for AI	6.0	—	—	—
290	▼ 3	Jamba 1.6 LargeOpenAI21 Labs	6.0	—	—	—
291	▼ 3	LFM2 24B A2BOpenLiquid AI	5.9	—	—	—
292	▼ 3	Phi-4OpenMicrosoft	5.9	$0.22	40	2.5 s
293	▼ 3	Granite 4.1 3BOpenIBM	5.9	—	—	—
294	▼ 3	Mistral Small (Sep '24)OpenMistral	5.8	—	—	—
295	▼ 3	Phi-3 Mini Instruct 3.8BOpenMicrosoft	5.8	—	—	—
296	▼ 3	NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)OpenNVIDIA	5.8	$0.30	201	1.1 s
297	▼ 3	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	5.8	—	—	—
298	▼ 3	Phi-4 Multimodal InstructOpenMicrosoft	5.8	$0.000	17	0.8 s
299	▼ 3	Qwen2.5 Coder Instruct 7BOpenAlibaba	5.8	—	—	—
300	▼ 3	Mixtral 8x22B InstructOpenMistral	5.7	—	—	—
301	▼ 3	Llama 2 Chat 7BOpenMeta	5.7	$0.10	—	—
302	▼ 3	Llama 3.2 Instruct 3BOpenMeta	5.7	—	—	—
303	▼ 3	MiniCPM-V 4.6 1.3BOpenOpenBMB	5.7	—	—	—
304	▼ 3	Jamba Reasoning 3BOpenAI21 Labs	5.7	—	—	—
305	▼ 3	Qwen3 VL 4B InstructOpenAlibaba	5.7	—	—	—
306	▼ 3	Qwen1.5 Chat 110BOpenAlibaba	5.7	—	—	—
307	▼ 3	Reka Flash 3OpenReka AI	5.6	$0.35	—	—
308	▼ 3	Olmo 3 7B ThinkOpenAllen Institute for AI	5.6	—	—	—
309	▼ 3	OLMo 2 7BOpenAllen Institute for AI	5.6	—	—	—
310	▼ 3	Molmo 7B-DOpenAllen Institute for AI	5.6	—	—	—
311	▼ 3	Ling-mini-2.0OpenInclusionAI	5.5	—	—	—
312	▼ 3	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	5.5	—	—	—
313	▼ 3	DeepSeek-V2-ChatOpenDeepSeek	5.5	—	—	—
314	▼ 3	Ministral 3 8BOpenMistral	5.5	$0.15	106	0.7 s
315	▼ 3	Llama 3 Instruct 70BOpenMeta	5.5	$1.2	—	—
316	▼ 3	Arctic InstructOpenSnowflake	5.4	—	—	—
316	▼ 3	Qwen Chat 72BOpenAlibaba	5.4	—	—	—
318	▼ 3	Llama 3.2 Instruct 11B (Vision)OpenMeta	5.4	$0.35	16	2.3 s
319	▼ 3	Qwen3.5 0.8B (Non-reasoning)OpenAlibaba	5.4	—	—	—
320	▼ 3	DeepSeek Coder V2 Lite InstructOpenDeepSeek	5.3	—	—	—
321	New	Sarvam M (Reasoning, based on Mistral Small 3.1)OpenSarvam	5.3	$0.000	—	—
322	▼ 3	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	5.3	—	—	—
322	▼ 3	Llama 2 Chat 70BOpenMeta	5.3	—	—	—
324	▼ 3	Llama 2 Chat 13BOpenMeta	5.3	—	—	—
325	▼ 3	Command-R+ (Apr '24)OpenCohere	5.3	—	—	—
326	▼ 3	OpenChat 3.5 (1210)OpenOpenChat	5.3	—	—	—
327	▼ 3	DBRX InstructOpenDatabricks	5.3	—	—	—
328	▼ 3	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research	5.3	—	—	—
329	▼ 3	Olmo 3 7B InstructOpenAllen Institute for AI	5.2	$0.13	—	—
330	▼ 3	Exaone 4.0 1.2B (Non-reasoning)OpenLG AI Research	5.2	—	—	—
331	▼ 3	LFM2.5-1.2B-ThinkingOpenLiquid AI	5.2	—	—	—
332	▼ 3	Jamba 1.7 MiniOpenAI21 Labs	5.2	—	—	—
333	▼ 3	LFM2 2.6BOpenLiquid AI	5.2	—	—	—
334	▼ 3	LFM2.5-1.2B-InstructOpenLiquid AI	5.2	—	—	—
335	▼ 3	Jamba 1.5 MiniOpenAI21 Labs	5.2	$0.25	—	—
336	▼ 3	Granite 4.0 H 1BOpenIBM	5.2	—	—	—
337	▼ 3	Qwen3 1.7B (Reasoning)OpenAlibaba	5.2	—	—	—
338	▼ 3	Jamba 1.6 MiniOpenAI21 Labs	5.2	—	—	—
339	▼ 3	Mixtral 8x7B InstructOpenMistral	5.1	$0.51	—	—
340	▼ 3	Gemma 3 270MOpenGoogle	5.1	—	—	—
341	▼ 3	Apertus 70B InstructOpenSwiss AI Initiative	5.1	$1.3	—	—
342	▼ 3	Granite 4.0 MicroOpenIBM	5.1	—	—	—
343	▼ 3	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	5.1	—	—	—
344	▼ 3	Command-R (Mar '24)OpenCohere	5.0	—	—	—
344	▼ 3	Llama 65BOpenMeta	5.0	—	—	—
344	▼ 3	Mistral 7B InstructOpenMistral	5.0	$0.16	—	—
344	▼ 3	Qwen Chat 14BOpenAlibaba	5.0	—	—	—
348	▼ 3	Granite 4.0 1BOpenIBM	5.0	—	—	—
349	▼ 3	Molmo2-8BOpenAllen Institute for AI	5.0	—	—	—
350	▼ 3	LFM2 8B A1BOpenLiquid AI	4.9	—	—	—
351	▼ 3	Granite 3.3 8B (Non-reasoning)OpenIBM	4.9	$0.085	14	28 s
352	▼ 3	Qwen3 1.7B (Non-reasoning)OpenAlibaba	4.9	—	—	—
353	▼ 3	Gemma 3 27B InstructOpenGoogle	4.9	$0.000	—	—
354	▼ 3	Ministral 3 3BOpenMistral	4.8	$0.10	210	0.7 s
355	▼ 3	Apertus 8B InstructOpenSwiss AI Initiative	4.8	$0.13	—	—
355	▼ 3	Gemma 3 1B InstructOpenGoogle	4.8	$0.000	—	—
355	▼ 3	Gemma 3 4B InstructOpenGoogle	4.8	$0.000	—	—
355	▼ 3	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
355	▼ 3	Gemma 3n E4B InstructOpenGoogle	4.8	—	—	—
355	▼ 3	Granite 4.0 350MOpenIBM	4.8	—	—	—
355	▼ 3	Granite 4.0 H 350MOpenIBM	4.8	—	—	—
355	▼ 3	LFM2 1.2BOpenLiquid AI	4.8	—	—	—
355	▼ 3	LFM2.5-VL-1.6BOpenLiquid AI	4.8	—	—	—
355	▼ 3	Llama 3 Instruct 8BOpenMeta	4.8	$0.070	—	—
355	▼ 3	Llama 3.2 Instruct 1BOpenMeta	4.8	—	—	—
355	▼ 3	Qwen3 0.6B (Non-reasoning)OpenAlibaba	4.8	—	—	—
355	▼ 3	Qwen3 0.6B (Reasoning)OpenAlibaba	4.8	—	—	—
355	▼ 3	Tiny Aya GlobalOpenCohere	4.8	$0.000	—	—
369	▼ 3	Gemma 3 12B InstructOpenGoogle	3.8	$0.000	—	—
370	▼ 3	K2 Horizon 0.9BOpenInstitute of Foundation Models	3.0	—	—	—

320 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