Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	GLM-5.2 (max)OpenZ AI · 1 more variant	51.1	$2.2	191	1.4 s
2	—	MiniMax-M3OpenMiniMax	44.4	$0.52	108	1.4 s
3	—	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	44.3	$0.54	62	1.8 s
4	—	Kimi K2.6OpenKimi · 1 more variant	44.2	$1.7	47	2.2 s
5	—	MiMo-V2.5-ProOpenXiaomi · 1 more variant	42.2	$0.54	51	3.8 s
6	—	Kimi K2.7 CodeOpenKimi	41.9	$1.7	49	3.1 s
7	—	Nex-N2-ProOpenNex AGI	41.0	$1.0	133	1.7 s
8	—	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	40.3	$0.18	102	1.4 s
9	—	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	40.2	$2.2	71	1.4 s
10	—	GLM-5 (Reasoning)OpenZ AI · 1 more variant	39.5	$1.6	52	1.8 s
11	—	MiniMax-M2.7OpenMiniMax	38.1	$0.52	47	1.9 s
12	—	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	38.1	$1.2	55	2.9 s
13	—	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	37.8	$1.2	194	1.1 s
14	—	MiMo-V2.5OpenXiaomi	37.2	$0.18	80	2.6 s
15	—	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	37.1	$1.4	58	3.8 s
16	—	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	33.8	$0.83	80	5.7 s
17	—	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	33.7	$1.0	142	0.8 s
18	—	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	33.7	$1.4	59	2.6 s
19	—	MiniMax-M2.5OpenMiniMax	33.7	$0.52	79	1.8 s
20	—	Hy3-preview (Reasoning)OpenTencent · 1 more variant	33.6	$0.20	169	3.1 s
21	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	33.2	$0.15	—	—
22	—	Kimi K2 ThinkingOpenKimi	32.7	$1.1	162	1.2 s
23	—	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	32.3	$1.1	143	2.4 s
24	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	32.0	$0.32	—	—
25	—	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	31.6	$0.56	171	2.4 s
26	—	MiniMax-M2.1OpenMiniMax	31.4	$0.52	84	1.8 s
27	—	Ring-2.6-1TOpenInclusionAI	30.6	$0.85	125	3.3 s
28	—	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	30.4	$1.9	—	—
29	—	Step 3.7 FlashOpenStepFun	30.3	$0.44	381	0.9 s
30	—	Mistral Medium 3.5OpenMistral	29.9	$3.0	135	2.1 s
31	—	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	29.4	$0.000	35	1.1 s
32	—	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	29.3	$0.69	160	2.3 s
33	—	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	28.7	$0.96	46	1.4 s
34	—	MiniMax-M2OpenMiniMax	28.3	$0.52	81	1.9 s
35	—	Ling-2.6-1TOpenInclusionAI	26.1	$0.85	—	—
36	—	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	25.7	$0.20	—	—
37	—	Step 3.5 FlashOpenStepFun	25.5	$0.15	195	1.1 s
38	—	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	25.4	$0.32	—	—
39	—	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	25.4	$0.38	146	1.1 s
40	—	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	24.7	—	—	—
41	—	Trinity Large ThinkingOpenArcee AI	24.5	$0.40	218	1.2 s
42	—	gpt-oss-120b (high)OpenOpenAI · 1 more variant	23.8	$0.26	319	0.8 s
43	—	Kimi K2 0905OpenKimi · 1 more variant	23.5	$1.1	37	2.0 s
44	—	EXAONE 4.5 33BOpenLG AI Research	23.0	—	—	—
45	—	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	22.9	$0.15	90	1.2 s
46	—	Command A+OpenCohere · 1 more variant	22.5	$0.000	164	0.4 s
47	—	DeepSeek V3.2 SpecialeOpenDeepSeek	22.2	—	—	—
48	—	Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant	22.0	$0.15	71	2.5 s
49	—	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	21.4	$0.11	54	1.6 s
50	—	Nemotron Cascade 2 30B A3BOpenNVIDIA	21.3	—	—	—
51	—	Apriel-v1.5-15B-ThinkerOpenServiceNow	21.2	$0.000	—	—
52	—	Qwen3 Coder NextOpenAlibaba	21.1	$0.56	106	1.7 s
53	—	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	21.0	$0.84	—	—
54	—	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	20.6	$2.6	56	3.0 s
55	—	North Mini CodeOpenCohere	20.6	$0.000	105	0.3 s
56	—	Apriel-v1.6-15B-ThinkerOpenServiceNow	20.5	$0.000	—	—
57	—	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	20.1	$0.060	24	0.7 s
58	—	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	20.1	$2.1	—	—
59	—	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	19.6	$2.6	58	2.9 s
60	—	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	19.6	$0.26	166	0.7 s
61	—	GLM-4.5 (Reasoning)OpenZ AI	19.5	$1.0	—	—
62	—	Devstral 2OpenMistral	19.2	$0.000	60	1.3 s
63	—	Seed-OSS-36B-InstructOpenByteDance Seed	18.3	$0.30	36	3.0 s
64	—	Qwen3 235B A22B 2507 InstructOpenAlibaba	18.2	$1.2	57	2.1 s
65	—	Qwen3 Coder 480B A35B InstructOpenAlibaba	18.0	$3.0	58	3.1 s
66	—	Qwen3 VL 32B (Reasoning)OpenAlibaba	17.9	$2.6	90	2.7 s
67	—	HyperNova 60B 2605OpenMultiverse Computing	17.8	$0.065	354	1.0 s
68	—	MiniMax M1 80kOpenMiniMax	17.7	$0.96	—	—
69	—	Devstral Small 2OpenMistral	17.4	$0.000	73	1.2 s
70	—	K2 Think V2OpenMBZUAI Institute of Foundation Models	17.3	—	—	—
71	—	LongCat Flash LiteOpenLongCat	17.2	—	—	—
72	—	HyperCLOVA X SEED Think (32B)OpenNaver	17.0	—	—	—
73	—	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	16.8	$0.45	59	4.3 s
74	—	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	16.7	$1.9	171	2.3 s
75	—	GLM-4.5-AirOpenZ AI	16.5	$0.37	74	2.7 s
76	—	Ring-1TOpenInclusionAI	16.2	—	—	—
77	—	Mistral Large 3OpenMistral	15.9	$0.75	47	1.2 s
78	—	INTELLECT-3OpenPrime Intellect	15.6	—	—	—
79	—	DeepSeek V3 0324OpenDeepSeek · 1 more variant	15.4	$1.2	—	—
80	—	Solar Open 100B (Reasoning)OpenUpstage	15.1	—	—	—
81	—	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	14.9	$0.13	313	1.0 s
82	—	gpt-oss-20b (high)OpenOpenAI · 1 more variant	14.9	$0.088	218	0.8 s
83	—	Mistral Small 3.1OpenMistral	14.7	$0.15	150	0.7 s
84	—	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	14.4	$0.75	119	2.5 s
85	—	MiniMax M1 40kOpenMiniMax	14.4	—	—	—
86	—	Qwen3 VL 235B A22B InstructOpenAlibaba	14.3	$1.2	51	2.8 s
87	—	Llama 4 MaverickOpenMeta	14.3	$0.48	118	1.0 s
88	—	K2-V2 (high)OpenMBZUAI Institute of Foundation Models · 2 more variants	14.2	—	—	—
89	—	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	14.2	$0.088	107	1.4 s
90	—	Ling 2.6 FlashOpenInclusionAI	14.1	$0.15	172	1.2 s
91	—	Qwen3 Next 80B A3B InstructOpenAlibaba	13.7	$0.88	181	2.3 s
92	—	Tri-21B-think PreviewOpenTrillion Labs	13.6	—	—	—
93	—	Qwen3 Coder 30B A3B InstructOpenAlibaba	13.6	$0.90	102	2.6 s
94	—	DiffusionGemma 26B A4BOpenGoogle	13.5	—	—	—
95	—	QwQ 32BOpenAlibaba	13.4	$0.75	32	2.1 s
96	—	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	13.3	$0.75	112	2.3 s
97	—	Ling-1TOpenInclusionAI	12.8	—	—	—
98	—	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	12.5	—	—	—
99	—	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	12.4	$0.40	50	1.2 s
100	—	Tri-21B-ThinkOpenTrillion Labs	12.4	—	—	—
101	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	12.2	—	—	—
102	—	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	12.0	—	—	—
103	—	MiniCPM5-1B (Reasoning)OpenOpenBMB · 1 more variant	12.0	—	—	—
104	—	Sarvam 105B (high)OpenSarvam	11.9	$0.074	132	2.0 s
105	—	Devstral Small (May '25)OpenMistral · 1 more variant	11.8	—	—	—
106	—	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	11.5	$2.6	92	2.6 s
107	—	Magistral Small 1.2OpenMistral	11.3	$0.75	81	0.9 s
108	—	Nanbeige4.1-3BOpenNanbeige	11.1	—	—	—
109	—	Qwen3 VL 32B InstructOpenAlibaba	11.1	$1.2	72	2.7 s
110	—	Ministral 3 14BOpenMistral	11.1	$0.20	81	0.9 s
111	—	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	11.0	—	—	—
112	—	Magistral Small 1OpenMistral	10.7	—	—	—
113	—	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	10.6	—	—	—
114	—	Qwen3 VL 8B (Reasoning)OpenAlibaba	10.6	$0.66	111	2.4 s
115	—	Mistral Small 3.2OpenMistral	10.6	$0.15	153	0.6 s
116	—	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	10.4	$1.3	62	2.7 s
117	—	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	10.4	—	—	—
118	—	Llama 4 ScoutOpenMeta	10.0	$0.29	115	0.9 s
119	—	Qwen3 VL 30B A3B InstructOpenAlibaba	10.0	$0.35	113	2.2 s
120	—	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research · 1 more variant	10.0	$0.20	92	1.4 s
121	—	DeepSeek R1 Distill Llama 70BOpenDeepSeek	9.9	$0.79	30	0.6 s
122	—	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	9.8	—	—	—
123	—	Falcon-H1R-7BOpenTII UAE	9.8	—	—	—
124	—	Ling-flash-2.0OpenInclusionAI	9.7	$0.25	73	2.2 s
125	—	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	9.6	$0.43	101	2.0 s
126	—	Qwen2.5 Instruct 72BOpenAlibaba	9.6	$0.48	—	—
127	—	Step3 VL 10BOpenStepFun	9.5	—	—	—
128	—	Llama 3.3 Instruct 70BOpenMeta	9.4	$0.61	90	1.6 s
129	—	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	9.3	—	—	—
130	—	QwQ 32B-PreviewOpenAlibaba	9.2	—	—	—
131	—	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	9.1	$0.90	26	6.3 s
132	—	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	9.1	$3.0	—	—
133	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	9.1	$0.90	51	2.4 s
134	—	Qwen3 30B A3B 2507 InstructOpenAlibaba	9.1	$0.35	141	2.0 s
135	—	ERNIE 4.5 300B A47BOpenBaidu	9.0	$0.49	—	—
136	—	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research · 1 more variant	9.0	$1.5	41	2.4 s
137	—	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	9.0	$0.30	285	0.4 s
138	—	Ministral 3 8BOpenMistral	9.0	$0.15	84	0.8 s
139	—	Granite 4.1 30BOpenIBM	8.9	—	—	—
140	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	8.8	$0.070	86	6.4 s
141	—	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	8.7	—	—	—
142	—	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	8.5	—	—	—
143	—	Kimi Linear 48B A3B InstructOpenKimi	8.5	—	—	—
144	—	Llama 3.1 Instruct 405BOpenMeta	8.5	$3.7	75	2.4 s
145	—	Qwen3 VL 8B InstructOpenAlibaba	8.4	$0.31	122	2.3 s
146	—	LFM2.5-8B-A1BOpenLiquid AI	8.3	$0.000	338	5.2 s
147	—	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	8.3	$0.66	39	3.9 s
148	—	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	8.3	—	—	—
149	—	Ring-flash-2.0OpenInclusionAI	8.2	$0.25	—	—
150	—	Pixtral LargeOpenMistral	8.1	$3.0	—	—
151	—	Olmo 3.1 32B ThinkOpenAllen Institute for AI	8.1	$0.000	—	—
152	—	Grok 2 (Dec '24)OpenSpaceXAI	8.0	—	—	—
153	—	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.9	—	—	—
154	—	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	7.6	—	—	—
155	—	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	7.6	$1.2	300	5.5 s
156	—	Llama 3.1 Instruct 8BOpenMeta	7.6	$0.080	155	0.9 s
157	—	Qwen2.5 Instruct 32BOpenAlibaba	7.5	—	—	—
158	—	Gemma 3 27B InstructOpenGoogle	7.4	$0.000	—	—
159	—	Qwen3 4B 2507 InstructOpenAlibaba	7.1	—	—	—
160	—	Qwen2.5 Coder Instruct 32BOpenAlibaba	7.1	—	—	—
161	—	Mistral Small 3OpenMistral	6.9	$0.15	151	0.7 s
162	—	Ministral 3 3BOpenMistral	6.8	$0.10	163	0.6 s
163	—	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	6.8	—	—	—
164	—	Llama 3.1 Instruct 70BOpenMeta	6.8	$0.56	33	1.8 s
165	—	Granite 4.1 8BOpenIBM	6.7	$0.063	121	0.8 s
166	—	Sarvam 30B (high)OpenSarvam	6.6	$0.047	164	1.9 s
167	—	Olmo 3.1 32B InstructOpenAllen Institute for AI	6.5	—	—	—
168	—	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.4	—	—	—
169	—	Olmo 3 32B ThinkOpenAllen Institute for AI	6.4	—	—	—
170	—	R1 1776OpenPerplexity	6.3	—	—	—
171	—	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.2	$1.4	60	1.2 s
171	—	Solar MiniOpenUpstage	6.2	$0.15	—	—
173	—	Grok-1OpenSpaceXAI	6.0	—	—	—
174	—	Qwen2 Instruct 72BOpenAlibaba	6.0	—	—	—
175	—	Phi-4 Mini InstructOpenMicrosoft	6.0	$0.000	45	0.8 s
176	—	Gemma 3 12B InstructOpenGoogle	5.5	$0.000	—	—
177	—	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	5.5	—	—	—
178	—	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	5.3	—	—	—
179	—	Jamba 1.7 LargeOpenAI21 Labs	5.3	$3.5	57	1.4 s
180	—	Granite 4.0 H SmallOpenIBM	5.2	$0.11	386	11 s
181	—	Jamba 1.5 LargeOpenAI21 Labs	5.1	$3.5	—	—
182	—	Qwen3 Omni 30B A3B InstructOpenAlibaba	5.1	$0.43	94	2.0 s
183	—	Hermes 3 - Llama-3.1 70BOpenNous Research	5.1	$0.70	34	1.9 s
184	—	DeepSeek-Coder-V2OpenDeepSeek	5.1	—	—	—
185	—	OLMo 2 32BOpenAllen Institute for AI	5.0	—	—	—
186	—	Jamba 1.6 LargeOpenAI21 Labs	5.0	$3.5	58	1.4 s
187	—	LFM2 24B A2BOpenLiquid AI	4.9	$0.053	—	—
188	—	Phi-4OpenMicrosoft	4.9	$0.22	25	2.2 s
189	—	Granite 4.1 3BOpenIBM	4.7	—	—	—
190	—	Mistral Small (Sep '24)OpenMistral	4.7	$0.30	159	0.8 s
191	—	Phi-3 Mini Instruct 3.8BOpenMicrosoft	4.6	—	—	—
192	—	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	4.6	—	—	—
193	—	Phi-4 Multimodal InstructOpenMicrosoft	4.5	$0.000	18	0.8 s
194	—	Qwen2.5 Coder Instruct 7BOpenAlibaba	4.5	—	—	—
195	—	Mixtral 8x22B InstructOpenMistral	4.4	—	—	—
196	—	Llama 2 Chat 7BOpenMeta	4.3	$0.10	—	—
197	—	Llama 3.2 Instruct 3BOpenMeta	4.2	$0.15	52	1.1 s
198	—	MiniCPM-V 4.6 1.3BOpenOpenBMB	4.2	—	—	—
199	—	Jamba Reasoning 3BOpenAI21 Labs	4.1	—	—	—
200	—	Qwen3 VL 4B InstructOpenAlibaba	4.1	—	—	—
201	—	Qwen1.5 Chat 110BOpenAlibaba	4.1	—	—	—
202	—	Reka Flash 3OpenReka AI	4.1	$0.35	—	—
203	—	Olmo 3 7B ThinkOpenAllen Institute for AI	4.0	—	—	—
204	—	OLMo 2 7BOpenAllen Institute for AI	3.9	—	—	—
205	—	Molmo 7B-DOpenAllen Institute for AI	3.8	—	—	—
206	—	Ling-mini-2.0OpenInclusionAI	3.8	—	—	—
207	—	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	3.7	—	—	—
208	—	DeepSeek-V2-ChatOpenDeepSeek	3.6	—	—	—
209	—	Llama 3 Instruct 70BOpenMeta	3.5	$1.2	—	—
210	—	Arctic InstructOpenSnowflake	3.4	—	—	—
210	—	Qwen Chat 72BOpenAlibaba	3.4	—	—	—
212	—	Llama 3.2 Instruct 11B (Vision)OpenMeta	3.3	$0.35	52	0.7 s
213	—	DeepSeek Coder V2 Lite InstructOpenDeepSeek	3.1	—	—	—
214	—	Sarvam M (Reasoning)OpenSarvam	3.0	$0.000	—	—
215	—	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	3.0	—	—	—
215	—	Llama 2 Chat 70BOpenMeta	3.0	—	—	—
217	—	Llama 2 Chat 13BOpenMeta	3.0	—	—	—
218	—	Command-R+ (Apr '24)OpenCohere · 1 more variant	3.0	$6.0	—	—
219	—	OpenChat 3.5 (1210)OpenOpenChat	3.0	—	—	—
220	—	DBRX InstructOpenDatabricks	3.0	—	—	—
221	—	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	2.9	—	—	—
222	—	Olmo 3 7B InstructOpenAllen Institute for AI	2.8	$0.13	—	—
223	—	LFM2.5-1.2B-ThinkingOpenLiquid AI	2.7	—	—	—
224	—	Jamba 1.7 MiniOpenAI21 Labs	2.7	—	—	—
225	—	LFM2 2.6BOpenLiquid AI	2.7	—	—	—
226	—	LFM2.5-1.2B-InstructOpenLiquid AI	2.7	—	—	—
227	—	Jamba 1.5 MiniOpenAI21 Labs	2.7	$0.25	—	—
228	—	Granite 4.0 H 1BOpenIBM	2.7	—	—	—
229	—	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	2.6	—	—	—
230	—	Jamba 1.6 MiniOpenAI21 Labs	2.6	$0.25	182	0.9 s
231	—	Mixtral 8x7B InstructOpenMistral	2.4	$0.51	—	—
232	—	Gemma 3 270MOpenGoogle	2.4	—	—	—
233	—	Apertus 70B InstructOpenSwiss AI Initiative	2.4	$1.3	—	—
234	—	Granite 4.0 MicroOpenIBM	2.4	—	—	—
235	—	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	2.3	—	—	—
236	—	Llama 65BOpenMeta	2.1	—	—	—
236	—	Mistral 7B InstructOpenMistral	2.1	$0.25	81	0.8 s
236	—	Qwen Chat 14BOpenAlibaba	2.1	—	—	—
239	—	Granite 4.0 1BOpenIBM	2.1	—	—	—
240	—	Molmo2-8BOpenAllen Institute for AI	2.0	—	—	—
241	—	LFM2 8B A1BOpenLiquid AI	1.8	—	—	—
242	—	Granite 3.3 8B (Non-reasoning)OpenIBM	1.8	$0.085	326	26 s
243	—	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	1.3	—	—	—
244	—	Llama 3 Instruct 8BOpenMeta	1.2	$0.070	—	—
245	—	Gemma 3n E4B InstructOpenGoogle	1.2	$0.025	57	1.2 s
246	—	LFM2 1.2BOpenLiquid AI	1.1	—	—	—
247	—	Gemma 3 4B InstructOpenGoogle	1.1	$0.000	—	—
248	—	Llama 3.2 Instruct 1BOpenMeta	1.1	$0.050	85	0.9 s
249	—	LFM2.5-VL-1.6BOpenLiquid AI	1.0	$0.000	438	11 s
250	—	Apertus 8B InstructOpenSwiss AI Initiative	1.0	$0.13	—	—
250	—	Gemma 3 1B InstructOpenGoogle	1.0	$0.000	—	—
250	—	Gemma 3n E2B InstructOpenGoogle	1.0	$0.000	—	—
250	—	Granite 4.0 350MOpenIBM	1.0	—	—	—
250	—	Granite 4.0 H 350MOpenIBM	1.0	—	—	—
250	—	Tiny Aya GlobalOpenCohere	1.0	$0.000	—	—

205 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