Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Kimi K2.6OpenKimi · 1 more variant	53.9	$1.7	47	2.2 s
2	—	MiMo-V2.5-ProOpenXiaomi · 1 more variant	53.8	$0.54	41	3.3 s
3	—	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	51.5	$0.54	54	1.7 s
4	—	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	51.4	$2.2	72	1.5 s
5	—	GLM-5 (Reasoning)OpenZ AI · 1 more variant	49.8	$1.6	75	1.8 s
6	—	MiniMax-M2.7OpenMiniMax	49.6	$0.52	40	2.2 s
7	—	MiMo-V2.5OpenXiaomi	49.0	$0.18	76	3.6 s
8	—	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	47.7	$1.2	183	1.1 s
9	—	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	46.8	$1.2	45	3.1 s
10	—	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	46.5	$0.18	92	1.2 s
11	—	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	45.8	$1.4	55	3.9 s
12	—	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	45.0	$1.4	52	2.4 s
13	—	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	43.5	$0.56	170	2.4 s
14	—	Step 3.7 FlashOpenStepFun	42.6	$0.44	385	0.9 s
15	—	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	42.1	$1.0	103	1.3 s
16	—	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	42.1	$0.83	80	5.8 s
17	—	MiniMax-M2.5OpenMiniMax	41.9	$0.52	179	12 s
18	—	Hy3-preview (Reasoning)OpenTencent · 1 more variant	41.9	$0.20	106	4.6 s
19	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	41.7	$0.34	—	—
20	—	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	41.6	$1.1	139	2.5 s
21	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	41.5	$0.15	151	1.9 s
22	—	Kimi K2 ThinkingOpenKimi	40.9	$1.1	122	1.5 s
23	—	MiniMax-M2.1OpenMiniMax	39.4	$0.52	179	13 s
24	—	Mistral Medium 3.5OpenMistral	39.2	$3.0	59	2.3 s
25	—	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	39.2	$0.000	35	1.1 s
26	—	Ring-2.6-1TOpenInclusionAI	38.5	$0.85	120	3.3 s
27	—	Step 3.5 FlashOpenStepFun	37.8	$0.15	208	1.2 s
28	—	Command A+OpenCohere · 1 more variant	37.2	$0.000	191	0.4 s
29	—	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	37.1	$0.69	160	2.2 s
30	—	MiniMax-M2OpenMiniMax	36.1	$0.52	111	1.7 s
31	—	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	158	1.7 s
32	—	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	33.9	$1.9	—	—
33	—	Ling-2.6-1TOpenInclusionAI	33.6	$0.85	—	—
34	—	gpt-oss-120b (high)OpenOpenAI · 1 more variant	33.3	$0.26	336	0.9 s
35	—	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	32.9	$0.31	—	—
36	—	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	32.5	$0.96	42	3.0 s
37	—	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	32.4	$0.11	66	1.7 s
38	—	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	32.1	—	—	—
39	—	Trinity Large ThinkingOpenArcee AI	31.9	$0.40	212	1.3 s
40	—	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	31.2	$0.20	—	—
41	—	Kimi K2 0905OpenKimi · 1 more variant	30.9	$1.1	24	2.5 s
42	—	EXAONE 4.5 33BOpenLG AI Research	30.2	—	—	—
43	—	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	30.1	$0.15	77	2.0 s
44	—	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	29.5	$0.84	71	2.8 s
45	—	DeepSeek V3.2 SpecialeOpenDeepSeek	29.4	—	—	—
46	New	HyperNova 60B 2605OpenMultiverse Computing	29.3	$0.065	342	0.7 s
47	New	Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant	29.2	$0.15	117	2.0 s
48	▼ 2	Nemotron Cascade 2 30B A3BOpenNVIDIA	28.4	—	—	—
49	▼ 2	Qwen3 Coder NextOpenAlibaba	28.3	$0.56	81	1.7 s
50	▼ 2	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	28.1	$0.83	—	—
51	▼ 2	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	27.8	$0.26	173	0.7 s
52	▼ 2	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.6	$2.2	47	5.4 s
53	New	North Mini CodeOpenCohere	27.6	$0.000	188	0.3 s
54	▼ 3	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	27.1	$0.060	195	0.5 s
55	▼ 3	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	27.1	$2.1	—	—
56	▼ 3	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.7	$1.9	167	2.2 s
57	▼ 3	GLM-4.5 (Reasoning)OpenZ AI	26.4	$1.0	49	3.5 s
58	▼ 3	Ling 2.6 FlashOpenInclusionAI	26.2	$0.15	—	—
59	▼ 3	Seed-OSS-36B-InstructOpenByteDance Seed	25.2	$0.30	31	3.2 s
60	▼ 3	Qwen3 235B A22B 2507 InstructOpenAlibaba	25.0	$0.36	57	2.3 s
61	▼ 3	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.8	$0.68	62	3.0 s
62	▼ 3	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.7	$2.6	90	2.6 s
63	▼ 3	gpt-oss-20B (high)OpenOpenAI · 1 more variant	24.5	$0.088	221	0.8 s
64	▼ 3	MiniMax M1 80kOpenMiniMax	24.4	$0.96	—	—
65	▼ 3	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	24.3	$0.096	137	1.6 s
66	▼ 3	LongCat Flash LiteOpenLongCat	23.9	$0.000	—	—
67	▼ 3	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	23.4	$0.45	86	4.1 s
68	▼ 3	GLM-4.5-AirOpenZ AI	23.2	$0.37	78	3.0 s
69	▼ 3	Mistral Large 3OpenMistral	22.8	$0.75	50	1.1 s
70	▼ 3	Ring-1TOpenInclusionAI	22.8	—	—	—
71	▼ 3	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	22.4	$0.67	146	2.4 s
72	▼ 3	DeepSeek V3 0324OpenDeepSeek · 1 more variant	22.3	$1.2	—	—
73	▼ 3	INTELLECT-3OpenPrime Intellect	22.2	—	—	—
74	▼ 3	Devstral 2OpenMistral	22.0	$0.000	43	1.4 s
75	▼ 3	Solar Open 100B (Reasoning)OpenUpstage	21.7	—	—	—
76	▼ 3	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	21.4	$0.13	300	1.1 s
77	▼ 3	MiniMax M1 40kOpenMiniMax	20.9	—	—	—
78	▼ 3	Qwen3 VL 235B A22B InstructOpenAlibaba	20.8	$0.70	49	2.8 s
79	▼ 3	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	148	2.3 s
80	▼ 3	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.35	100	2.7 s
81	▼ 3	QwQ 32BOpenAlibaba	19.7	$0.75	30	2.1 s
82	▼ 3	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.7	$0.34	111	2.3 s
83	▼ 3	Devstral Small 2OpenMistral	19.5	$0.000	36	1.2 s
84	▼ 3	Ling-1TOpenInclusionAI	19.0	—	—	—
85	▼ 3	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	18.8	—	—	—
86	▼ 3	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	18.7	$0.18	49	1.3 s
87	▼ 3	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	18.5	—	—	—
88	▼ 3	Llama 4 MaverickOpenMeta	18.4	$0.48	99	1.0 s
89	▼ 3	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	18.2	—	—	—
90	▼ 3	MiniCPM5-1B (Reasoning)OpenOpenBMB · 1 more variant	18.2	—	—	—
91	▼ 3	Magistral Small 1.2OpenMistral	18.2	$0.75	108	0.8 s
92	▼ 3	Sarvam 105B (high)OpenSarvam	18.2	$0.074	98	2.1 s
93	▼ 3	Devstral Small (May '25)OpenMistral · 1 more variant	18.0	—	—	—
94	▼ 3	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	30	2.4 s
95	▼ 3	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	73	2.7 s
96	▼ 3	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	—	—	—
97	▼ 3	Magistral Small 1OpenMistral	16.8	—	—	—
98	▼ 3	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	16.7	—	—	—
99	▼ 3	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.7	$0.66	114	2.4 s
100	▼ 3	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	16.5	$0.28	66	2.7 s
101	▼ 3	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	—	—	—
102	▼ 3	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	16.3	$0.040	15	5.2 s
103	▼ 3	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	16.2	$0.73	60	2.7 s
104	▼ 3	Nanbeige4.1-3BOpenNanbeige	16.1	—	—	—
105	▼ 3	Qwen3 VL 30B A3B InstructOpenAlibaba	16.0	$0.30	111	2.2 s
106	▼ 3	Ministral 3 14BOpenMistral	16.0	$0.20	88	0.8 s
107	▼ 3	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	41	1.7 s
108	▼ 3	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	—	—	—
109	▼ 3	Falcon-H1R-7BOpenTII UAE	15.8	—	—	—
110	▼ 3	Ling-flash-2.0OpenInclusionAI	15.7	$0.25	70	2.4 s
111	▼ 3	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	85	2.2 s
112	▼ 3	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.37	—	—
113	▼ 3	Step3 VL 10BOpenStepFun	15.5	—	—	—
114	▼ 3	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	15.2	—	—	—
115	▼ 3	QwQ 32B-PreviewOpenAlibaba	15.2	—	—	—
116	▼ 3	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	15.1	$0.90	37	2.1 s
117	▼ 3	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	15.1	$3.0	51	1.1 s
118	▼ 3	Mistral Small 3.2OpenMistral	15.1	$0.13	130	0.7 s
119	▼ 3	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	51	2.5 s
120	▼ 3	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.21	157	1.9 s
121	▼ 3	ERNIE 4.5 300B A47BOpenBaidu	15.0	$0.49	—	—
122	▼ 3	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	14.9	$0.30	271	0.5 s
123	▼ 3	Ministral 3 8BOpenMistral	14.8	$0.15	85	0.6 s
124	▼ 3	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	14.8	$0.070	122	0.6 s
125	▼ 3	Granite 4.1 30BOpenIBM	14.7	—	—	—
126	▼ 3	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
127	▼ 3	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.61	84	1.8 s
128	▼ 3	Mistral Small 3.1OpenMistral	14.5	$0.14	157	0.7 s
129	▼ 3	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
130	▼ 3	Kimi Linear 48B A3B InstructOpenKimi	14.4	—	—	—
131	▼ 3	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	122	2.4 s
132	New	LFM2.5-8B-A1BOpenLiquid AI	14.2	$0.000	213	12 s
133	▼ 4	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	—	—
134	▼ 4	Pixtral LargeOpenMistral	14.0	$3.0	53	1.1 s
135	▼ 4	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
136	▼ 4	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	—	—	—
137	▼ 4	Llama 4 ScoutOpenMeta	13.5	$0.29	87	0.9 s
138	▼ 4	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	296	4.2 s
139	▼ 4	Qwen2.5 Instruct 32BOpenAlibaba	13.2	—	—	—
140	▼ 4	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	13.2	$0.37	39	3.8 s
141	▼ 4	Qwen3 4B 2507 InstructOpenAlibaba	12.9	—	—	—
142	▼ 4	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	—	—	—
143	▼ 4	Mistral Small 3OpenMistral	12.7	$0.10	151	0.7 s
144	▼ 4	MiniCPM-V 4.6 1.3BOpenOpenBMB	12.7	—	—	—
145	▼ 4	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	12.5	—	—	—
146	▼ 4	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	38	1.9 s
147	▼ 4	Granite 4.1 8BOpenIBM	12.4	$0.063	121	0.8 s
148	▼ 4	Sarvam 30B (high)OpenSarvam	12.3	$0.047	166	1.9 s
149	▼ 4	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	—	—	—
150	▼ 4	R1 1776OpenPerplexity	12.0	—	—	—
151	▼ 4	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$1.4	58	1.2 s
151	▼ 4	Solar MiniOpenUpstage	11.9	$0.15	—	—
153	▼ 4	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	154	0.9 s
154	▼ 4	Grok-1OpenxAI	11.7	—	—	—
155	▼ 4	Qwen2 Instruct 72BOpenAlibaba	11.7	—	—	—
156	▼ 4	Ministral 3 3BOpenMistral	11.2	$0.10	163	0.5 s
157	▼ 4	Jamba 1.7 LargeOpenAI21 Labs	10.9	$3.5	61	1.7 s
158	▼ 4	Granite 4.0 H SmallOpenIBM	10.8	$0.11	560	10 s
159	▼ 4	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
160	▼ 4	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	94	1.9 s
161	▼ 4	DeepSeek-Coder-V2OpenDeepSeek	10.6	—	—	—
162	▼ 4	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	59	1.6 s
163	▼ 4	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	10.5	$0.020	19	0.7 s
164	▼ 4	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	123	0.6 s
165	▼ 4	Phi-4OpenMicrosoft	10.4	$0.22	37	2.1 s
166	▼ 4	Gemma 3 27B InstructOpenGoogle	10.3	$0.14	—	—
167	▼ 4	Mistral Small (Sep '24)OpenMistral	10.2	$0.30	157	0.8 s
168	▼ 4	Phi-3 Mini Instruct 3.8BOpenMicrosoft	10.1	—	—	—
169	▼ 4	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
170	▼ 4	Phi-4 Multimodal InstructOpenMicrosoft	10.0	$0.000	16	1.8 s
171	▼ 4	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	—	—	—
172	▼ 4	Mixtral 8x22B InstructOpenMistral	9.8	—	—	—
173	New	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
174	▼ 5	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.15	51	1.1 s
175	▼ 5	Jamba Reasoning 3BOpenAI21 Labs	9.6	—	—	—
176	▼ 5	Qwen3 VL 4B InstructOpenAlibaba	9.6	—	—	—
177	▼ 5	Qwen1.5 Chat 110BOpenAlibaba	9.5	—	—	—
178	▼ 5	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
179	▼ 5	Ling-mini-2.0OpenInclusionAI	9.2	—	—	—
180	▼ 5	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	—	—	—
181	▼ 5	DeepSeek-V2-ChatOpenDeepSeek	9.1	—	—	—
182	▼ 5	Llama 3 Instruct 70BOpenMeta	8.9	$1.2	—	—
183	▼ 5	Arctic InstructOpenSnowflake	8.8	—	—	—
183	▼ 5	Qwen Chat 72BOpenAlibaba	8.8	—	—	—
185	▼ 5	Gemma 3 12B InstructOpenGoogle	8.8	$0.14	—	—
186	▼ 5	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.25	48	0.7 s
187	▼ 5	Granite 4.1 3BOpenIBM	8.5	—	—	—
188	▼ 5	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	—	—	—
189	▼ 5	Sarvam M (Reasoning)OpenSarvam	8.4	$0.000	—	—
190	▼ 5	Phi-4 Mini InstructOpenMicrosoft	8.4	$0.000	24	1.9 s
191	▼ 5	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	—	—	—
191	▼ 5	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
193	▼ 5	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
194	▼ 5	Command-R+ (Apr '24)OpenCohere · 1 more variant	8.3	$6.0	—	—
195	▼ 5	OpenChat 3.5 (1210)OpenOpenChat	8.3	—	—	—
196	▼ 5	DBRX InstructOpenDatabricks	8.3	—	—	—
197	▼ 5	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	8.3	—	—	—
198	▼ 5	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
199	▼ 5	Jamba 1.7 MiniOpenAI21 Labs	8.1	—	—	—
200	▼ 5	LFM2 2.6BOpenLiquid AI	8.0	$0.000	325	6.5 s
201	▼ 5	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	446	10 s
202	▼ 5	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
203	▼ 5	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
204	▼ 5	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	8.0	$0.40	—	—
205	▼ 5	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	184	1.1 s
206	▼ 5	Mixtral 8x7B InstructOpenMistral	7.7	$0.51	—	—
207	▼ 5	Gemma 3 270MOpenGoogle	7.7	—	—	—
208	▼ 5	Apertus 70B InstructOpenSwiss AI Initiative	7.7	$1.3	—	—
209	▼ 5	Granite 4.0 MicroOpenIBM	7.7	—	—	—
210	▼ 5	Llama 65BOpenMeta	7.4	—	—	—
210	▼ 5	Mistral 7B InstructOpenMistral	7.4	$0.21	88	0.7 s
210	▼ 5	Qwen Chat 14BOpenAlibaba	7.4	—	—	—
213	▼ 5	Granite 4.0 1BOpenIBM	7.3	—	—	—
214	▼ 5	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
215	▼ 5	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	349	27 s
216	▼ 5	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	6.5	$0.40	—	—
217	▼ 5	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
218	▼ 5	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	45	1.3 s
219	▼ 5	LFM2 1.2BOpenLiquid AI	6.3	$0.000	421	5.2 s
220	▼ 5	Gemma 3 4B InstructOpenGoogle	6.3	$0.050	—	—
221	▼ 5	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	85	0.9 s
222	▼ 5	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	426	10 s
223	▼ 5	Granite 4.0 350MOpenIBM	6.1	—	—	—
224	▼ 5	Apertus 8B InstructOpenSwiss AI Initiative	5.9	$0.13	—	—
225	▼ 5	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	—	—
226	▼ 5	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
227	▼ 5	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
228	▼ 5	Tiny Aya GlobalOpenCohere	4.7	$0.000	—	—

178 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