Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	New	GLM-5.2 (max)OpenZ AI	51.1	$2.2	99	2.1 s
2	New	MiniMax-M3OpenMiniMax	44.4	$0.52	60	2.7 s
3	—	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek	44.3	$0.54	75	1.8 s
4	▼ 3	Kimi K2.6OpenKimi	42.8	$1.7	44	2.5 s
5	▼ 3	MiMo-V2.5-ProOpenXiaomi	42.2	$0.54	50	2.6 s
6	New	Kimi K2.7 CodeOpenKimi	41.9	$1.7	56	2.3 s
7	▼ 2	DeepSeek V4 Pro (Reasoning, High Effort)OpenDeepSeek	40.8	$0.54	69	1.8 s
8	▲ 3	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek	40.3	$0.18	107	1.3 s
9	▼ 5	GLM-5.1 (Reasoning)OpenZ AI	40.2	$2.2	79	1.5 s
10	▼ 2	MiMo-V2.5OpenXiaomi	40.1	$0.18	78	2.5 s
11	▼ 5	GLM-5 (Reasoning)OpenZ AI	39.5	$1.6	75	1.7 s
12	▼ 5	MiniMax-M2.7OpenMiniMax	38.1	$0.52	44	2.1 s
13	▼ 3	Kimi K2.5 (Reasoning)OpenKimi	38.1	$1.2	55	3.0 s
14	▼ 5	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	37.8	$1.2	170	1.1 s
15	▼ 3	DeepSeek V4 Flash (Reasoning, High Effort)OpenDeepSeek	37.4	$0.18	—	—
16	▼ 3	Qwen3.6 27B (Reasoning)OpenAlibaba	37.1	$1.4	55	3.8 s
17	▼ 2	GLM-5.1 (Non-reasoning)OpenZ AI	35.4	$2.2	54	1.9 s
18	▼ 1	Kimi K2.6 (Non-reasoning)OpenKimi	34.6	$1.7	45	2.9 s
19	—	GLM-4.7 (Reasoning)OpenZ AI	33.8	$1.0	115	1.0 s
20	—	Qwen3.5 27B (Reasoning)OpenAlibaba	33.8	$0.83	80	5.7 s
21	▼ 7	Qwen3.5 397B A17B (Reasoning)OpenAlibaba	33.7	$1.4	51	2.7 s
22	▼ 1	MiniMax-M2.5OpenMiniMax	33.7	$0.52	203	7.3 s
23	▼ 1	Hy3-preview (Reasoning)OpenTencent	33.6	$0.20	117	4.1 s
24	▼ 1	DeepSeek V3.2 (Reasoning)OpenDeepSeek	33.4	$0.34	—	—
25	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi	33.2	$0.15	96	2.4 s
26	—	Kimi K2 ThinkingOpenKimi	32.7	$1.1	123	1.5 s
27	—	GLM-5 (Non-reasoning)OpenZ AI	32.4	$1.6	63	2.1 s
28	▼ 4	Qwen3.5 122B A10B (Reasoning)OpenAlibaba	32.3	$1.1	134	2.5 s
29	▼ 1	Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba	32.0	$1.4	51	2.7 s
30	▼ 14	Qwen3.6 35B A3B (Reasoning)OpenAlibaba	31.6	$0.56	171	2.5 s
31	▼ 2	MiniMax-M2.1OpenMiniMax	31.4	$0.52	212	9.2 s
32	▼ 2	DeepSeek V4 Pro (Non-reasoning)OpenDeepSeek	31.2	$0.54	78	1.8 s
33	▼ 2	MiMo-V2-Flash (Reasoning)OpenXiaomi	31.2	$0.15	93	2.4 s
34	—	Ring-2.6-1TOpenInclusionAI	30.6	$0.85	132	3.4 s
35	▼ 3	Mistral Medium 3.5OpenMistral	29.9	$3.0	128	2.3 s
36	▼ 18	Step 3.7 FlashOpenStepFun	29.7	$0.44	377	1.0 s
37	▼ 1	Kimi K2.5 (Non-reasoning)OpenKimi	29.4	$1.2	53	3.0 s
38	▼ 5	Gemma 4 31B (Reasoning)OpenGoogle	29.4	$0.000	34	1.1 s
39	▼ 2	Qwen3.5 27B (Non-reasoning)OpenAlibaba	29.3	$0.88	89	5.8 s
40	▼ 2	Command A+OpenCohere	29.3	$0.000	200	0.4 s
41	▼ 2	Qwen3.6 27B (Non-reasoning)OpenAlibaba	29.3	$1.4	59	3.8 s
42	▼ 2	Qwen3.5 35B A3B (Reasoning)OpenAlibaba	29.3	$0.69	155	2.2 s
43	▼ 2	DeepSeek V4 Flash (Non-reasoning)OpenDeepSeek	28.7	$0.18	101	1.3 s
44	▼ 2	MiniMax-M2OpenMiniMax	28.3	$0.52	112	1.8 s
45	▼ 1	Qwen3.5 122B A10B (Non-reasoning)OpenAlibaba	28.1	$1.1	160	2.5 s
46	▼ 1	MiMo-V2.5-Pro (Non-reasoning)OpenXiaomi	27.9	$1.4	54	2.7 s
47	▼ 1	GLM-4.7 (Non-reasoning)OpenZ AI	26.6	$1.0	115	0.9 s
48	▼ 1	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek	26.3	$1.9	—	—
49	▼ 1	Hy3-preview (Non-reasoning)OpenTencent	26.1	$0.20	134	4.0 s
50	▼ 1	Ling-2.6-1TOpenInclusionAI	26.1	$0.85	—	—
51	▲ 8	Gemma 4 26B A4B (Reasoning)OpenGoogle	25.7	$0.20	—	—
52	▼ 17	Step 3.5 FlashOpenStepFun	25.5	$0.15	212	1.2 s
53	▼ 2	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek	25.4	$0.31	—	—
54	▼ 11	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	25.4	$0.41	148	1.4 s
55	▼ 3	GLM-4.6 (Reasoning)OpenZ AI	25.1	$0.96	46	2.6 s
56	▼ 3	Qwen3.5 9B (Reasoning)OpenAlibaba	25.0	$0.11	63	2.0 s
57	▼ 3	Gemma 4 31B (Non-reasoning)OpenGoogle	24.8	$0.21	35	2.2 s
58	▼ 3	K-EXAONE (Reasoning)OpenLG AI Research	24.7	—	—	—
59	▼ 3	DeepSeek V3.2 (Non-reasoning)OpenDeepSeek	24.7	$0.78	—	—
60	▼ 3	Trinity Large ThinkingOpenArcee AI	24.5	$0.40	158	1.1 s
61	▼ 3	Qwen3.6 35B A3B (Non-reasoning)OpenAlibaba	24.2	$0.84	180	2.3 s
62	▼ 12	gpt-oss-120b (high)OpenOpenAI	23.8	$0.26	341	1.0 s
63	▼ 3	Kimi K2 0905OpenKimi	23.5	$1.1	27	2.4 s
64	▼ 3	Qwen3.5 35B A3B (Non-reasoning)OpenAlibaba	23.4	$0.69	170	2.3 s
65	▼ 3	MiMo-V2-Flash (Non-reasoning)OpenXiaomi	23.1	$0.15	111	3.6 s
66	▼ 3	GLM-4.6 (Non-reasoning)OpenZ AI	23.0	$1.0	48	3.6 s
67	▼ 3	EXAONE 4.5 33BOpenLG AI Research	23.0	—	—	—
68	▼ 3	GLM-4.7-Flash (Reasoning)OpenZ AI	22.9	$0.15	87	1.5 s
69	▼ 3	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba	22.3	$0.84	47	3.1 s
70	▼ 3	DeepSeek V3.2 SpecialeOpenDeepSeek	22.2	—	—	—
71	▼ 3	HyperNova 60B 2605OpenMultiverse Computing	22.1	$0.065	359	0.7 s
72	▼ 3	Gemma 4 12B (Reasoning)OpenGoogle	22.0	$0.15	126	2.4 s
73	▼ 3	DeepSeek V3.1 Terminus (Non-reasoning)OpenDeepSeek	21.4	$0.45	—	—
74	▼ 3	DeepSeek V3.2 Exp (Non-reasoning)OpenDeepSeek	21.3	$0.31	—	—
75	▼ 3	Nemotron Cascade 2 30B A3BOpenNVIDIA	21.3	—	—	—
76	▼ 3	Qwen3 Coder NextOpenAlibaba	21.2	$0.56	71	2.0 s
77	▼ 3	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek	21.0	$0.83	—	—
78	▼ 3	Mistral Small 4 (Reasoning)OpenMistral	20.8	$0.26	169	0.8 s
79	▼ 3	DeepSeek V3.1 (Reasoning)OpenDeepSeek	20.7	$0.87	—	—
80	▼ 3	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	20.6	$2.2	56	3.1 s
81	▼ 3	North Mini CodeOpenCohere	20.6	$0.000	152	0.3 s
82	▼ 3	Qwen3.5 9B (Non-reasoning)OpenAlibaba	20.3	—	—	—
83	▼ 3	Gemma 4 26B A4B (Non-reasoning)OpenGoogle	20.1	$0.20	40	1.9 s
84	▼ 3	Qwen3.5 4B (Reasoning)OpenAlibaba	20.1	$0.060	28	0.9 s
85	▼ 3	DeepSeek R1 0528 (May '25)OpenDeepSeek	20.1	$2.1	—	—
86	▼ 3	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	19.8	$1.9	173	2.2 s
87	▼ 3	GLM-4.5 (Reasoning)OpenZ AI	19.5	$1.0	51	3.4 s
88	▼ 3	Kimi K2OpenKimi	19.4	$1.0	27	2.4 s
89	▼ 3	Ling 2.6 FlashOpenInclusionAI	19.3	$0.15	—	—
90	▼ 3	Seed-OSS-36B-InstructOpenByteDance Seed	18.3	$0.30	35	3.1 s
91	▼ 3	Qwen3 235B A22B 2507 InstructOpenAlibaba	18.2	$0.36	57	2.3 s
92	▼ 3	Qwen3 Coder 480B A35B InstructOpenAlibaba	18.0	$0.68	59	3.0 s
93	▼ 3	Qwen3 VL 32B (Reasoning)OpenAlibaba	17.9	$2.6	90	2.8 s
94	▼ 2	gpt-oss-120b (low)OpenOpenAI	17.7	$0.26	356	0.9 s
95	▼ 2	MiniMax M1 80kOpenMiniMax	17.7	$0.96	—	—
96	▼ 2	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA	17.5	$0.096	75	3.7 s
97	▼ 2	LongCat Flash LiteOpenLongCat	17.2	$0.000	—	—
98	▼ 2	GLM-4.6V (Reasoning)OpenZ AI	16.8	$0.45	86	3.9 s
99	▼ 2	K-EXAONE (Non-reasoning)OpenLG AI Research	16.7	—	—	—
100	▼ 2	GLM-4.5-AirOpenZ AI	16.5	$0.37	79	2.8 s
101	▼ 2	Mistral Large 3OpenMistral	16.2	$0.75	50	1.2 s
102	▼ 2	Ring-1TOpenInclusionAI	16.2	—	—	—
103	▼ 2	Qwen3.5 4B (Non-reasoning)OpenAlibaba	16.0	$0.060	31	0.9 s
104	▼ 2	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba	15.8	$0.67	143	2.5 s
105	▼ 2	DeepSeek V3 0324OpenDeepSeek	15.7	$1.2	—	—
106	▼ 2	INTELLECT-3OpenPrime Intellect	15.6	—	—	—
107	▼ 2	GLM-4.7-Flash (Non-reasoning)OpenZ AI	15.5	$0.15	144	1.5 s
108	▼ 2	Devstral 2OpenMistral	15.5	$0.000	44	1.4 s
109	▼ 2	Solar Open 100B (Reasoning)OpenUpstage	15.1	—	—	—
110	▼ 2	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	14.9	$0.13	278	1.0 s
111	▼ 20	gpt-oss-20B (high)OpenOpenAI	14.9	$0.088	215	0.8 s
112	▼ 3	MiniMax M1 40kOpenMiniMax	14.4	—	—	—
113	▼ 3	gpt-oss-20B (low)OpenOpenAI	14.3	$0.095	224	0.8 s
114	▼ 3	Qwen3 VL 235B A22B InstructOpenAlibaba	14.3	$0.70	51	2.7 s
115	▲ 10	Llama 4 MaverickOpenMeta	14.3	$0.48	93	1.0 s
116	▼ 4	Qwen3 Next 80B A3B InstructOpenAlibaba	13.7	$0.88	176	2.2 s
117	▼ 4	Qwen3 Coder 30B A3B InstructOpenAlibaba	13.6	$0.35	100	2.7 s
118	▼ 4	Qwen3 235B A22B (Reasoning)OpenAlibaba	13.4	$2.6	57	2.9 s
119	▼ 4	QwQ 32BOpenAlibaba	13.4	$0.75	30	2.1 s
120	▼ 4	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	13.3	$0.34	111	2.3 s
121	▼ 4	Gemma 4 12B (Non-reasoning)OpenGoogle	13.2	—	—	—
122	▼ 4	Devstral Small 2OpenMistral	13.1	$0.000	45	1.2 s
123	▼ 4	Ling-1TOpenInclusionAI	12.8	—	—	—
124	▼ 4	DeepSeek R1 (Jan '25)OpenDeepSeek	12.6	$2.4	—	—
125	▼ 4	Gemma 4 E4B (Reasoning)OpenGoogle	12.5	—	—	—
126	▼ 4	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA	12.4	$0.18	48	1.3 s
127	▼ 4	Mistral Small 4 (Non-reasoning)OpenMistral	12.4	$0.26	149	0.8 s
128	▼ 4	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA	12.2	—	—	—
129	▼ 3	Qwen3 4B 2507 (Reasoning)OpenAlibaba	12.0	—	—	—
130	▼ 3	MiniCPM5-1B (Reasoning)OpenOpenBMB	12.0	—	—	—
131	▼ 3	Magistral Small 1.2OpenMistral	11.9	$0.75	105	0.9 s
132	▼ 3	Sarvam 105B (high)OpenSarvam	11.9	$0.074	103	2.1 s
133	▼ 3	Devstral Small (May '25)OpenMistral	11.8	—	—	—
134	▼ 3	MiniCPM5-1B (Non-reasoning)OpenOpenBMB	11.7	—	—	—
135	▼ 2	Qwen3 VL 32B InstructOpenAlibaba	11.1	$1.2	67	2.7 s
136	▼ 2	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	11.0	—	—	—
137	▼ 2	GLM-4.6V (Non-reasoning)OpenZ AI	11.0	$0.45	80	4.3 s
138	▼ 2	Qwen3 235B A22B (Non-reasoning)OpenAlibaba	10.9	$0.79	58	2.8 s
139	▼ 2	Magistral Small 1OpenMistral	10.7	—	—	—
140	▼ 2	EXAONE 4.0 32B (Reasoning)OpenLG AI Research	10.6	—	—	—
141	▼ 2	Qwen3 VL 8B (Reasoning)OpenAlibaba	10.6	$0.66	110	2.5 s
142	▼ 2	Qwen3 32B (Reasoning)OpenAlibaba	10.5	$0.28	61	2.7 s
143	▼ 2	DeepSeek V3 (Dec '24)OpenDeepSeek	10.4	$0.52	—	—
144	▼ 2	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	10.4	—	—	—
145	▼ 2	Qwen3.5 2B (Reasoning)OpenAlibaba	10.2	$0.040	27	0.8 s
146	▼ 2	Qwen3 14B (Reasoning)OpenAlibaba	10.1	$0.73	63	2.7 s
147	▼ 2	Nanbeige4.1-3BOpenNanbeige	10.1	—	—	—
148	▲ 38	Llama 4 ScoutOpenMeta	10.0	$0.29	109	0.9 s
149	▼ 3	Qwen3 VL 30B A3B InstructOpenAlibaba	10.0	$0.30	112	2.3 s
150	▼ 3	Ministral 3 14BOpenMistral	10.0	$0.20	90	0.8 s
151	▼ 3	DeepSeek R1 Distill Llama 70BOpenDeepSeek	9.9	$0.79	52	0.6 s
152	▼ 3	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	9.8	—	—	—
153	▼ 3	Falcon-H1R-7BOpenTII UAE	9.8	—	—	—
154	▼ 3	Ling-flash-2.0OpenInclusionAI	9.7	$0.25	59	2.3 s
155	▼ 3	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	9.6	$0.43	86	2.1 s
156	▼ 3	Qwen2.5 Instruct 72BOpenAlibaba	9.6	$0.37	—	—
157	▼ 3	Step3 VL 10BOpenStepFun	9.5	—	—	—
158	▼ 3	Qwen3 30B A3B (Reasoning)OpenAlibaba	9.3	$0.18	109	2.2 s
159	▼ 3	Devstral Small (Jul '25)OpenMistral	9.3	$0.15	44	1.1 s
160	▼ 3	Gemma 4 E2B (Reasoning)OpenGoogle	9.3	—	—	—
161	▼ 3	QwQ 32B-PreviewOpenAlibaba	9.2	—	—	—
162	▼ 3	GLM-4.5V (Reasoning)OpenZ AI	9.1	$0.90	24	2.3 s
163	▼ 3	Mistral Large 2 (Nov '24)OpenMistral	9.1	$3.0	53	1.2 s
164	▼ 3	Mistral Small 3.2OpenMistral	9.1	$0.13	138	0.7 s
165	▼ 3	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	9.1	$0.90	51	2.4 s
166	▼ 3	Qwen3 30B A3B 2507 InstructOpenAlibaba	9.1	$0.21	145	2.0 s
167	▼ 3	ERNIE 4.5 300B A47BOpenBaidu	9.0	$0.49	—	—
168	▼ 3	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA	9.0	$0.30	283	0.4 s
169	▼ 3	Ministral 3 8BOpenMistral	8.9	$0.15	96	0.7 s
170	▼ 3	Gemma 4 E4B (Non-reasoning)OpenGoogle	8.9	—	—	—
171	▼ 2	Granite 4.1 30BOpenIBM	8.9	—	—	—
172	▼ 4	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA	8.8	$0.070	78	7.4 s
173	▼ 3	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	8.8	—	—	—
174	▼ 3	Qwen3.5 2B (Non-reasoning)OpenAlibaba	8.8	$0.040	29	0.8 s
175	▼ 3	Llama Nemotron Super 49B v1.5 (Non-reasoning)OpenNVIDIA	8.7	$0.18	49	1.3 s
176	▼ 3	Qwen3 32B (Non-reasoning)OpenAlibaba	8.6	$0.26	61	2.6 s
177	▼ 3	Llama 3.3 Instruct 70BOpenMeta	8.6	$0.61	92	1.6 s
178	▼ 3	Mistral Small 3.1OpenMistral	8.6	$0.14	153	0.8 s
179	▼ 3	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	8.5	—	—	—
180	▼ 3	Kimi Linear 48B A3B InstructOpenKimi	8.5	—	—	—
181	▼ 49	Llama 3.1 Instruct 405BOpenMeta	8.5	$3.7	32	2.3 s
182	▼ 4	Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)OpenNVIDIA	8.5	—	—	—
183	▼ 4	Qwen3 VL 8B InstructOpenAlibaba	8.4	$0.31	121	2.3 s
184	▼ 4	Qwen3 4B (Reasoning)OpenAlibaba	8.4	$0.40	—	—
185	▼ 4	LFM2.5-8B-A1BOpenLiquid AI	8.3	$0.000	234	2.6 s
186	▼ 4	Ring-flash-2.0OpenInclusionAI	8.2	$0.25	—	—
187	▼ 4	Pixtral LargeOpenMistral	8.1	$3.0	49	1.2 s
188	▼ 4	Grok 2 (Dec '24)OpenxAI	8.0	—	—	—
189	▼ 4	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.9	—	—	—
190	▼ 3	Command AOpenCohere	7.7	$4.4	71	1.6 s
191	▼ 3	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	7.6	$1.2	274	4.8 s
192	▼ 3	Qwen2.5 Instruct 32BOpenAlibaba	7.5	—	—	—
193	▼ 3	Qwen3 8B (Reasoning)OpenAlibaba	7.4	$0.37	38	3.7 s
194	▼ 3	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)OpenNVIDIA	7.4	$0.088	79	0.4 s
195	▼ 3	NVIDIA Nemotron Nano 9B V2 (Non-reasoning)OpenNVIDIA	7.4	$0.086	142	1.9 s
196	▼ 3	Mistral Large 2 (Jul '24)OpenMistral	7.3	$3.0	—	—
197	▼ 3	Qwen3 4B 2507 InstructOpenAlibaba	7.1	—	—	—
198	▼ 3	Qwen2.5 Coder Instruct 32BOpenAlibaba	7.1	—	—	—
199	▼ 3	Qwen3 14B (Non-reasoning)OpenAlibaba	7.0	$0.38	62	2.8 s
200	▼ 3	GLM-4.5V (Non-reasoning)OpenZ AI	7.0	$0.90	32	32 s
201	▼ 3	Mistral Small 3OpenMistral	6.9	$0.10	150	0.8 s
202	▼ 2	Qwen3 30B A3B (Non-reasoning)OpenAlibaba	6.8	$0.13	107	2.3 s
203	▼ 2	DeepSeek-V2.5 (Dec '24)OpenDeepSeek	6.8	—	—	—
204	▼ 2	Qwen3 4B (Non-reasoning)OpenAlibaba	6.8	$0.19	—	—
205	▼ 2	Llama 3.1 Instruct 70BOpenMeta	6.8	$0.56	31	1.8 s
206	▼ 2	Granite 4.1 8BOpenIBM	6.7	$0.063	123	0.8 s
207	▼ 2	Sarvam 30B (high)OpenSarvam	6.6	$0.047	161	1.9 s
208	▼ 2	DeepSeek-V2.5OpenDeepSeek	6.6	—	—	—
209	▼ 2	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.4	—	—	—
210	▼ 2	Gemma 4 E2B (Non-reasoning)OpenGoogle	6.4	—	—	—
211	▼ 2	R1 1776OpenPerplexity	6.3	—	—	—
212	▼ 2	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.2	$1.4	57	1.2 s
212	▼ 2	Solar MiniOpenUpstage	6.2	$0.15	—	—
214	▼ 2	Llama 3.1 Instruct 8BOpenMeta	6.1	$0.10	154	0.9 s
215	▼ 2	Grok-1OpenxAI	6.0	—	—	—
216	▼ 2	Qwen2 Instruct 72BOpenAlibaba	6.0	—	—	—
217	▼ 2	EXAONE 4.0 32B (Non-reasoning)OpenLG AI Research	6.0	—	—	—
218	▼ 2	Ministral 3 3BOpenMistral	5.6	$0.10	166	0.6 s
219	▼ 2	Jamba 1.7 LargeOpenAI21 Labs	5.3	$3.5	59	1.6 s
220	▼ 2	Granite 4.0 H SmallOpenIBM	5.2	$0.11	356	10 s
221	▼ 2	Jamba 1.5 LargeOpenAI21 Labs	5.1	$3.5	—	—
222	▼ 2	Qwen3 Omni 30B A3B InstructOpenAlibaba	5.1	$0.43	95	2.0 s
223	▼ 2	Qwen3 8B (Non-reasoning)OpenAlibaba	5.1	$0.19	39	3.7 s
224	▼ 2	DeepSeek-Coder-V2OpenDeepSeek	5.1	—	—	—
225	▼ 2	Jamba 1.6 LargeOpenAI21 Labs	5.0	$3.5	60	1.6 s
226	▼ 2	Qwen3.5 0.8B (Reasoning)OpenAlibaba	5.0	$0.020	32	0.8 s
227	▼ 2	LFM2 24B A2BOpenLiquid AI	4.9	$0.053	126	0.6 s
228	▼ 2	Phi-4OpenMicrosoft	4.9	$0.22	40	2.0 s
229	▼ 2	Gemma 3 27B InstructOpenGoogle	4.8	$0.14	—	—
230	▼ 2	Mistral Small (Sep '24)OpenMistral	4.7	$0.30	155	0.8 s
231	▼ 2	Phi-3 Mini Instruct 3.8BOpenMicrosoft	4.6	—	—	—
232	▼ 2	NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)OpenNVIDIA	4.6	$0.30	211	0.8 s
233	▼ 2	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	4.6	—	—	—
234	▼ 2	Phi-4 Multimodal InstructOpenMicrosoft	4.5	$0.000	16	1.8 s
235	▼ 2	Qwen2.5 Coder Instruct 7BOpenAlibaba	4.5	—	—	—
236	▼ 2	Qwen3.5 0.8B (Non-reasoning)OpenAlibaba	4.4	$0.020	32	0.8 s
237	▼ 2	Mixtral 8x22B InstructOpenMistral	4.4	—	—	—
238	▼ 2	Llama 2 Chat 7BOpenMeta	4.3	$0.10	—	—
239	▼ 2	Llama 3.2 Instruct 3BOpenMeta	4.2	$0.15	51	1.1 s
240	▼ 41	MiniCPM-V 4.6 1.3BOpenOpenBMB	4.2	—	—	—
241	▼ 3	Jamba Reasoning 3BOpenAI21 Labs	4.1	—	—	—
242	▼ 3	Qwen3 VL 4B InstructOpenAlibaba	4.1	—	—	—
243	▼ 3	Qwen1.5 Chat 110BOpenAlibaba	4.1	—	—	—
244	▼ 3	Reka Flash 3OpenReka AI	4.1	$0.35	—	—
245	▼ 3	Ling-mini-2.0OpenInclusionAI	3.8	—	—	—
246	▼ 3	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	3.7	—	—	—
247	▼ 3	DeepSeek-V2-ChatOpenDeepSeek	3.6	—	—	—
248	▼ 3	Llama 3 Instruct 70BOpenMeta	3.5	$1.2	—	—
249	▼ 3	Arctic InstructOpenSnowflake	3.4	—	—	—
249	▼ 3	Qwen Chat 72BOpenAlibaba	3.4	—	—	—
251	▼ 3	Gemma 3 12B InstructOpenGoogle	3.4	$0.14	—	—
252	▼ 3	Llama 3.2 Instruct 11B (Vision)OpenMeta	3.3	$0.25	51	0.7 s
253	▼ 3	Granite 4.1 3BOpenIBM	3.2	—	—	—
254	▼ 3	DeepSeek Coder V2 Lite InstructOpenDeepSeek	3.1	—	—	—
255	▼ 3	Sarvam M (Reasoning)OpenSarvam	3.0	$0.000	—	—
256	▼ 3	Phi-4 Mini InstructOpenMicrosoft	3.0	$0.000	45	0.9 s
257	▼ 3	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	3.0	—	—	—
257	▼ 3	Llama 2 Chat 70BOpenMeta	3.0	—	—	—
259	▼ 3	Llama 2 Chat 13BOpenMeta	3.0	—	—	—
260	▼ 3	Command-R+ (Apr '24)OpenCohere	3.0	$6.0	—	—
261	▼ 3	OpenChat 3.5 (1210)OpenOpenChat	3.0	—	—	—
262	▼ 3	DBRX InstructOpenDatabricks	3.0	—	—	—
263	▼ 3	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research	2.9	—	—	—
264	▼ 3	Exaone 4.0 1.2B (Non-reasoning)OpenLG AI Research	2.8	—	—	—
265	▼ 3	LFM2.5-1.2B-ThinkingOpenLiquid AI	2.7	—	—	—
266	▼ 3	Jamba 1.7 MiniOpenAI21 Labs	2.7	—	—	—
267	▼ 3	LFM2 2.6BOpenLiquid AI	2.7	$0.000	338	1.3 s
268	▼ 3	LFM2.5-1.2B-InstructOpenLiquid AI	2.7	$0.000	448	1.3 s
269	▼ 3	Jamba 1.5 MiniOpenAI21 Labs	2.7	$0.25	—	—
270	▼ 3	Granite 4.0 H 1BOpenIBM	2.7	—	—	—
271	▼ 3	Qwen3 1.7B (Reasoning)OpenAlibaba	2.6	$0.40	—	—
272	▼ 3	Jamba 1.6 MiniOpenAI21 Labs	2.6	$0.25	182	1.0 s
273	▼ 3	Mixtral 8x7B InstructOpenMistral	2.4	$0.51	—	—
274	▼ 3	Gemma 3 270MOpenGoogle	2.4	—	—	—
275	▼ 3	Apertus 70B InstructOpenSwiss AI Initiative	2.4	$1.3	—	—
276	▼ 3	Granite 4.0 MicroOpenIBM	2.4	—	—	—
277	▼ 3	Command-R (Mar '24)OpenCohere	2.1	$0.75	—	—
277	▼ 3	Llama 65BOpenMeta	2.1	—	—	—
277	▼ 3	Mistral 7B InstructOpenMistral	2.1	$0.21	96	0.7 s
277	▼ 3	Qwen Chat 14BOpenAlibaba	2.1	—	—	—
281	▼ 3	Granite 4.0 1BOpenIBM	2.1	—	—	—
282	▼ 3	LFM2 8B A1BOpenLiquid AI	1.8	$0.000	—	—
283	▼ 3	Granite 3.3 8B (Non-reasoning)OpenIBM	1.8	$0.085	348	28 s
284	▼ 3	Qwen3 1.7B (Non-reasoning)OpenAlibaba	1.5	$0.19	—	—
285	▼ 3	Qwen3 0.6B (Reasoning)OpenAlibaba	1.3	$0.40	—	—
286	▼ 3	Llama 3 Instruct 8BOpenMeta	1.2	$0.070	—	—
287	▼ 3	Gemma 3n E4B InstructOpenGoogle	1.2	$0.025	52	1.3 s
288	▼ 3	LFM2 1.2BOpenLiquid AI	1.1	$0.000	430	1.3 s
289	▼ 3	Gemma 3 4B InstructOpenGoogle	1.1	$0.050	—	—
290	▼ 3	Llama 3.2 Instruct 1BOpenMeta	1.1	$0.050	84	0.9 s
291	▼ 3	LFM2.5-VL-1.6BOpenLiquid AI	1.0	$0.000	467	1.6 s
292	▼ 2	Apertus 8B InstructOpenSwiss AI Initiative	1.0	$0.13	—	—
292	—	Gemma 3 1B InstructOpenGoogle	1.0	$0.000	—	—
292	▲ 2	Gemma 3n E2B InstructOpenGoogle	1.0	$0.000	—	—
292	▼ 3	Granite 4.0 350MOpenIBM	1.0	—	—	—
292	▲ 1	Granite 4.0 H 350MOpenIBM	1.0	—	—	—
292	▼ 1	Qwen3 0.6B (Non-reasoning)OpenAlibaba	1.0	$0.19	—	—
292	▲ 3	Tiny Aya GlobalOpenCohere	1.0	$0.000	—	—

248 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