Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	GLM-5.2 (max)OpenZ AI	51.1	$2.2	168	1.4 s
2	—	MiniMax-M3OpenMiniMax	44.4	$0.52	92	2.0 s
3	—	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	44.3	$0.54	68	1.8 s
4	—	Kimi K2.6OpenKimi · 1 more variant	42.8	$1.7	42	2.3 s
5	—	MiMo-V2.5-ProOpenXiaomi · 1 more variant	42.2	$0.54	44	2.7 s
6	—	Kimi K2.7 CodeOpenKimi	41.9	$1.7	50	3.0 s
7	—	Nex-N2-ProOpenNex AGI	41.0	$1.0	110	1.6 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	65	1.5 s
10	—	MiMo-V2.5OpenXiaomi	40.1	$0.18	83	2.6 s
11	—	GLM-5 (Reasoning)OpenZ AI · 1 more variant	39.5	$1.6	65	1.6 s
12	—	MiniMax-M2.7OpenMiniMax	38.1	$0.52	53	2.0 s
13	—	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	38.1	$1.2	45	3.0 s
14	—	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	37.8	$1.2	132	1.2 s
15	—	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	37.1	$1.4	56	3.7 s
16	▲ 1	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	33.8	$0.83	81	5.7 s
17	▼ 1	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	33.7	$1.0	112	0.9 s
18	—	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	33.7	$1.4	49	2.7 s
19	—	MiniMax-M2.5OpenMiniMax	33.7	$0.52	85	1.8 s
20	—	Hy3-preview (Reasoning)OpenTencent · 1 more variant	33.6	$0.20	151	3.2 s
21	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	33.4	$0.32	—	—
22	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	33.2	$0.15	—	—
23	—	Kimi K2 ThinkingOpenKimi	32.7	$1.1	155	1.4 s
24	—	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	32.3	$1.1	142	2.4 s
25	—	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	31.6	$0.56	156	2.3 s
26	—	MiniMax-M2.1OpenMiniMax	31.4	$0.52	81	2.2 s
27	—	Ring-2.6-1TOpenInclusionAI	30.6	$0.85	119	3.4 s
28	—	Mistral Medium 3.5OpenMistral	29.9	$3.0	123	1.9 s
29	—	Step 3.7 FlashOpenStepFun	29.7	$0.44	397	0.9 s
30	—	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	29.4	$0.000	35	1.1 s
31	▲ 1	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	29.3	$0.69	157	2.1 s
32	▲ 1	MiniMax-M2OpenMiniMax	28.3	$0.52	82	1.8 s
33	▲ 1	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	26.3	$1.9	—	—
34	▲ 1	Ling-2.6-1TOpenInclusionAI	26.1	$0.85	—	—
35	▲ 1	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	25.7	$0.20	—	—
36	▲ 1	Step 3.5 FlashOpenStepFun	25.5	$0.15	178	1.1 s
37	▲ 1	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	25.4	$0.32	—	—
38	▲ 1	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	25.4	$0.41	223	1.4 s
39	▲ 1	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	25.1	$0.96	41	1.3 s
40	▲ 2	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	24.7	—	—	—
41	▲ 2	Trinity Large ThinkingOpenArcee AI	24.5	$0.40	213	1.1 s
42	▲ 2	gpt-oss-120b (high)OpenOpenAI · 1 more variant	23.8	$0.26	261	1.0 s
43	▲ 2	Kimi K2 0905OpenKimi · 1 more variant	23.5	$1.1	37	2.2 s
44	▲ 2	EXAONE 4.5 33BOpenLG AI Research	23.0	—	—	—
45	▲ 2	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	22.9	$0.15	77	1.3 s
46	▼ 15	Command A+OpenCohere · 1 more variant	22.5	$0.000	159	0.4 s
47	▲ 2	DeepSeek V3.2 SpecialeOpenDeepSeek	22.2	—	—	—
48	▲ 2	HyperNova 60B 2605OpenMultiverse Computing	22.1	$0.065	376	0.7 s
49	▲ 2	Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant	22.0	$0.15	120	2.4 s
50	▼ 9	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	21.4	$0.11	53	2.1 s
51	▲ 1	Nemotron Cascade 2 30B A3BOpenNVIDIA	21.3	—	—	—
52	New	Apriel-v1.5-15B-ThinkerOpenServiceNow	21.2	$0.000	—	—
53	—	Qwen3 Coder NextOpenAlibaba	21.2	$0.56	102	1.6 s
54	—	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	21.0	$0.83	—	—
55	▲ 1	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	20.6	$2.6	57	3.1 s
56	▲ 1	North Mini CodeOpenCohere	20.6	$0.000	39	0.4 s
57	New	Apriel-v1.6-15B-ThinkerOpenServiceNow	20.5	$0.000	—	—
58	—	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	20.1	$0.060	27	0.8 s
59	—	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	20.1	$2.1	—	—
60	▼ 12	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	19.6	$2.6	57	2.8 s
61	▼ 6	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	19.6	$0.26	166	0.8 s
62	▼ 1	GLM-4.5 (Reasoning)OpenZ AI	19.5	$1.0	—	—
63	▼ 1	Ling 2.6 FlashOpenInclusionAI	19.3	$0.15	156	1.5 s
64	▼ 1	Devstral 2OpenMistral	19.2	$0.000	53	1.4 s
65	▼ 1	Seed-OSS-36B-InstructOpenByteDance Seed	18.3	$0.30	32	3.1 s
66	▼ 1	Qwen3 235B A22B 2507 InstructOpenAlibaba	18.2	$1.2	59	2.3 s
67	▼ 1	Qwen3 Coder 480B A35B InstructOpenAlibaba	18.0	$3.0	64	3.1 s
68	▼ 1	Qwen3 VL 32B (Reasoning)OpenAlibaba	17.9	$2.6	90	2.7 s
69	▼ 1	MiniMax M1 80kOpenMiniMax	17.7	$0.96	—	—
70	▲ 18	Devstral Small 2OpenMistral	17.4	$0.000	43	1.2 s
71	New	K2 Think V2OpenMBZUAI Institute of Foundation Models	17.3	—	—	—
72	▼ 3	LongCat Flash LiteOpenLongCat	17.2	$0.000	—	—
73	New	HyperCLOVA X SEED Think (32B)OpenNaver	17.0	—	—	—
74	▼ 4	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	16.8	$0.45	63	4.9 s
75	▼ 15	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	16.7	$1.9	162	2.2 s
76	▼ 5	GLM-4.5-AirOpenZ AI	16.5	$0.37	67	2.8 s
77	▼ 5	Ring-1TOpenInclusionAI	16.2	—	—	—
78	▼ 5	Mistral Large 3OpenMistral	15.9	$0.75	49	1.3 s
79	▼ 3	INTELLECT-3OpenPrime Intellect	15.6	—	—	—
80	▼ 5	DeepSeek V3 0324OpenDeepSeek · 1 more variant	15.4	$1.2	—	—
81	▼ 4	Solar Open 100B (Reasoning)OpenUpstage	15.1	—	—	—
82	▼ 4	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	14.9	$0.13	292	1.0 s
83	▼ 4	gpt-oss-20b (high)OpenOpenAI · 1 more variant	14.9	$0.088	234	0.8 s
84	▲ 48	Mistral Small 3.1OpenMistral	14.7	$0.15	162	0.8 s
85	▼ 11	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	14.4	$0.75	110	2.5 s
86	▼ 6	MiniMax M1 40kOpenMiniMax	14.4	—	—	—
87	▼ 6	Qwen3 VL 235B A22B InstructOpenAlibaba	14.3	$1.2	50	2.8 s
88	▼ 6	Llama 4 MaverickOpenMeta	14.3	$0.48	107	1.0 s
89	New	K2-V2 (high)OpenMBZUAI Institute of Foundation Models · 2 more variants	14.2	—	—	—
90	▼ 7	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	14.2	$0.096	96	2.6 s
91	▼ 7	Qwen3 Next 80B A3B InstructOpenAlibaba	13.7	$0.88	183	2.3 s
92	New	Tri-21B-think PreviewOpenTrillion Labs	13.6	—	—	—
93	▼ 8	Qwen3 Coder 30B A3B InstructOpenAlibaba	13.6	$0.90	102	2.6 s
94	New	DiffusionGemma 26B A4BOpenGoogle	13.5	—	—	—
95	▼ 9	QwQ 32BOpenAlibaba	13.4	$0.75	29	2.1 s
96	▼ 9	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	13.3	$0.75	109	2.3 s
97	▼ 8	Ling-1TOpenInclusionAI	12.8	—	—	—
98	▼ 8	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	12.5	—	—	—
99	▼ 8	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	12.4	$0.18	50	1.3 s
100	New	Tri-21B-ThinkOpenTrillion Labs	12.4	—	—	—
101	▼ 9	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	12.2	—	—	—
102	▼ 9	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	12.0	—	—	—
103	▼ 9	MiniCPM5-1B (Reasoning)OpenOpenBMB · 1 more variant	12.0	—	—	—
104	▼ 8	Sarvam 105B (high)OpenSarvam	11.9	$0.074	95	2.1 s
105	▼ 8	Devstral Small (May '25)OpenMistral · 1 more variant	11.8	—	—	—
106	▼ 2	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	11.5	$2.6	97	2.4 s
107	▼ 12	Magistral Small 1.2OpenMistral	11.3	$0.75	81	1.0 s
108	▼ 10	Qwen3 VL 32B InstructOpenAlibaba	11.1	$1.2	66	2.7 s
109	▼ 10	Ministral 3 14BOpenMistral	11.1	$0.20	58	1.2 s
110	▼ 10	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	11.0	—	—	—
111	▼ 10	Magistral Small 1OpenMistral	10.7	—	—	—
112	▼ 10	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	10.6	—	—	—
113	▼ 10	Qwen3 VL 8B (Reasoning)OpenAlibaba	10.6	$0.66	110	2.4 s
114	▲ 8	Mistral Small 3.2OpenMistral	10.6	$0.15	140	0.7 s
115	▼ 8	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	10.4	$1.3	60	3.0 s
116	▼ 11	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	10.4	—	—	—
117	▼ 11	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	10.2	—	—	—
118	▼ 10	Nanbeige4.1-3BOpenNanbeige	10.1	—	—	—
119	▼ 10	Llama 4 ScoutOpenMeta	10.0	$0.29	105	0.9 s
120	▼ 10	Qwen3 VL 30B A3B InstructOpenAlibaba	10.0	$0.35	101	2.3 s
121	New	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research · 1 more variant	10.0	$0.20	85	1.4 s
122	▼ 11	DeepSeek R1 Distill Llama 70BOpenDeepSeek	9.9	$0.79	30	0.7 s
123	▼ 11	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	9.8	—	—	—
124	▼ 11	Falcon-H1R-7BOpenTII UAE	9.8	—	—	—
125	▼ 11	Ling-flash-2.0OpenInclusionAI	9.7	$0.25	67	2.2 s
126	▼ 11	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	9.6	$0.43	90	2.1 s
127	▼ 11	Qwen2.5 Instruct 72BOpenAlibaba	9.6	$0.000	—	—
128	▼ 11	Step3 VL 10BOpenStepFun	9.5	—	—	—
129	▼ 11	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	9.3	—	—	—
130	▼ 11	QwQ 32B-PreviewOpenAlibaba	9.2	—	—	—
131	▼ 11	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	9.1	$0.90	88	5.0 s
132	▼ 11	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	9.1	$3.0	47	1.3 s
133	▼ 10	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	9.1	$0.90	52	2.4 s
134	▼ 10	Qwen3 30B A3B 2507 InstructOpenAlibaba	9.1	$0.35	150	1.9 s
135	▼ 10	ERNIE 4.5 300B A47BOpenBaidu	9.0	$0.49	—	—
136	New	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research · 1 more variant	9.0	$1.5	40	2.4 s
137	▼ 11	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	9.0	$0.30	290	0.4 s
138	▼ 11	Ministral 3 8BOpenMistral	9.0	$0.15	88	0.8 s
139	▼ 11	Granite 4.1 30BOpenIBM	8.9	—	—	—
140	▼ 11	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	8.8	$0.070	84	8.6 s
141	▼ 11	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	8.8	—	—	—
142	▼ 11	Llama 3.3 Instruct 70BOpenMeta	8.6	$0.61	91	1.6 s
143	▼ 10	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	8.5	—	—	—
144	▼ 10	Kimi Linear 48B A3B InstructOpenKimi	8.5	—	—	—
145	▼ 10	Llama 3.1 Instruct 405BOpenMeta	8.5	$3.7	75	2.4 s
146	▼ 10	Qwen3 VL 8B InstructOpenAlibaba	8.4	$0.31	111	2.4 s
147	▼ 10	LFM2.5-8B-A1BOpenLiquid AI	8.3	$0.000	340	2.6 s
148	▼ 4	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	8.3	$0.66	39	3.9 s
149	New	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	8.3	—	—	—
150	▼ 12	Ring-flash-2.0OpenInclusionAI	8.2	$0.25	—	—
151	▼ 12	Pixtral LargeOpenMistral	8.1	$3.0	48	1.3 s
152	New	Olmo 3.1 32B ThinkOpenAllen Institute for AI	8.1	$0.000	—	—
153	▼ 13	Grok 2 (Dec '24)OpenxAI	8.0	—	—	—
154	▼ 13	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.9	—	—	—
155	▼ 13	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	7.6	$1.2	301	4.9 s
156	▲ 1	Llama 3.1 Instruct 8BOpenMeta	7.6	$0.080	141	0.9 s
157	▼ 14	Qwen2.5 Instruct 32BOpenAlibaba	7.5	—	—	—
158	▲ 11	Gemma 3 27B InstructOpenGoogle	7.4	$0.000	—	—
159	▼ 14	Qwen3 4B 2507 InstructOpenAlibaba	7.1	—	—	—
160	▼ 14	Qwen2.5 Coder Instruct 32BOpenAlibaba	7.1	—	—	—
161	▼ 14	Mistral Small 3OpenMistral	6.9	$0.15	161	0.8 s
162	▼ 13	Ministral 3 3BOpenMistral	6.8	$0.10	151	0.7 s
163	▼ 15	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	6.8	—	—	—
164	▼ 14	Llama 3.1 Instruct 70BOpenMeta	6.8	$0.56	32	2.0 s
165	▼ 14	Granite 4.1 8BOpenIBM	6.7	$0.063	114	0.8 s
166	▼ 14	Sarvam 30B (high)OpenSarvam	6.6	$0.047	165	1.9 s
167	New	Olmo 3.1 32B InstructOpenAllen Institute for AI	6.5	—	—	—
168	▼ 15	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.4	—	—	—
169	New	Olmo 3 32B ThinkOpenAllen Institute for AI	6.4	—	—	—
170	▼ 16	R1 1776OpenPerplexity	6.3	—	—	—
171	▼ 16	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.2	$1.4	58	1.2 s
171	▼ 16	Solar MiniOpenUpstage	6.2	$0.15	—	—
173	▼ 15	Grok-1OpenxAI	6.0	—	—	—
174	▼ 15	Qwen2 Instruct 72BOpenAlibaba	6.0	—	—	—
175	New	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	5.3	—	—	—
176	▼ 16	Jamba 1.7 LargeOpenAI21 Labs	5.3	$3.5	60	1.7 s
177	▼ 16	Granite 4.0 H SmallOpenIBM	5.2	$0.11	413	10 s
178	▼ 16	Jamba 1.5 LargeOpenAI21 Labs	5.1	$3.5	—	—
179	▼ 16	Qwen3 Omni 30B A3B InstructOpenAlibaba	5.1	$0.43	94	2.0 s
180	New	Hermes 3 - Llama-3.1 70BOpenNous Research	5.1	$0.30	31	2.0 s
181	▼ 17	DeepSeek-Coder-V2OpenDeepSeek	5.1	—	—	—
182	New	OLMo 2 32BOpenAllen Institute for AI	5.0	—	—	—
183	▼ 18	Jamba 1.6 LargeOpenAI21 Labs	5.0	$3.5	61	1.7 s
184	▼ 18	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	5.0	—	—	—
185	▼ 18	LFM2 24B A2BOpenLiquid AI	4.9	$0.053	120	0.6 s
186	▼ 18	Phi-4OpenMicrosoft	4.9	$0.22	36	2.2 s
187	▼ 17	Mistral Small (Sep '24)OpenMistral	4.7	$0.30	156	0.8 s
188	▼ 17	Phi-3 Mini Instruct 3.8BOpenMicrosoft	4.6	—	—	—
189	▼ 17	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	4.6	—	—	—
190	▼ 17	Phi-4 Multimodal InstructOpenMicrosoft	4.5	$0.000	17	1.3 s
191	▼ 17	Qwen2.5 Coder Instruct 7BOpenAlibaba	4.5	—	—	—
192	▼ 17	Mixtral 8x22B InstructOpenMistral	4.4	—	—	—
193	▼ 17	Llama 2 Chat 7BOpenMeta	4.3	$0.10	—	—
194	▼ 17	Llama 3.2 Instruct 3BOpenMeta	4.2	$0.15	52	1.1 s
195	▼ 17	MiniCPM-V 4.6 1.3BOpenOpenBMB	4.2	—	—	—
196	▼ 17	Jamba Reasoning 3BOpenAI21 Labs	4.1	—	—	—
197	▼ 17	Qwen3 VL 4B InstructOpenAlibaba	4.1	—	—	—
198	▼ 17	Qwen1.5 Chat 110BOpenAlibaba	4.1	—	—	—
199	▼ 17	Reka Flash 3OpenReka AI	4.1	$0.35	—	—
200	New	Olmo 3 7B ThinkOpenAllen Institute for AI	4.0	—	—	—
201	New	OLMo 2 7BOpenAllen Institute for AI	3.9	—	—	—
202	New	Molmo 7B-DOpenAllen Institute for AI	3.8	—	—	—
203	▼ 20	Ling-mini-2.0OpenInclusionAI	3.8	—	—	—
204	▼ 20	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	3.7	—	—	—
205	▼ 20	DeepSeek-V2-ChatOpenDeepSeek	3.6	—	—	—
206	▼ 20	Llama 3 Instruct 70BOpenMeta	3.5	$1.2	—	—
207	▼ 20	Arctic InstructOpenSnowflake	3.4	—	—	—
207	▼ 20	Qwen Chat 72BOpenAlibaba	3.4	—	—	—
209	▼ 20	Gemma 3 12B InstructOpenGoogle	3.4	$0.000	—	—
210	▼ 20	Llama 3.2 Instruct 11B (Vision)OpenMeta	3.3	$0.25	49	0.8 s
211	▼ 20	Granite 4.1 3BOpenIBM	3.2	—	—	—
212	▼ 20	DeepSeek Coder V2 Lite InstructOpenDeepSeek	3.1	—	—	—
213	▼ 20	Sarvam M (Reasoning)OpenSarvam	3.0	$0.000	—	—
214	▼ 20	Phi-4 Mini InstructOpenMicrosoft	3.0	$0.000	44	1.7 s
215	▼ 20	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	3.0	—	—	—
215	▼ 20	Llama 2 Chat 70BOpenMeta	3.0	—	—	—
217	▼ 20	Llama 2 Chat 13BOpenMeta	3.0	—	—	—
218	▼ 20	Command-R+ (Apr '24)OpenCohere · 1 more variant	3.0	$6.0	—	—
219	▼ 20	OpenChat 3.5 (1210)OpenOpenChat	3.0	—	—	—
220	▼ 20	DBRX InstructOpenDatabricks	3.0	—	—	—
221	▼ 20	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	2.9	—	—	—
222	New	Olmo 3 7B InstructOpenAllen Institute for AI	2.8	$0.13	—	—
223	▼ 21	LFM2.5-1.2B-ThinkingOpenLiquid AI	2.7	—	—	—
224	▼ 21	Jamba 1.7 MiniOpenAI21 Labs	2.7	—	—	—
225	▼ 21	LFM2 2.6BOpenLiquid AI	2.7	$0.000	—	—
226	▼ 21	LFM2.5-1.2B-InstructOpenLiquid AI	2.7	$0.000	—	—
227	▼ 21	Jamba 1.5 MiniOpenAI21 Labs	2.7	$0.25	—	—
228	▼ 21	Granite 4.0 H 1BOpenIBM	2.7	—	—	—
229	▼ 21	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	2.6	$0.40	—	—
230	▼ 21	Jamba 1.6 MiniOpenAI21 Labs	2.6	$0.25	181	1.0 s
231	▼ 21	Mixtral 8x7B InstructOpenMistral	2.4	$0.51	—	—
232	▼ 21	Gemma 3 270MOpenGoogle	2.4	—	—	—
233	▼ 21	Apertus 70B InstructOpenSwiss AI Initiative	2.4	$1.3	—	—
234	▼ 21	Granite 4.0 MicroOpenIBM	2.4	—	—	—
235	New	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	2.3	—	—	—
236	▼ 22	Llama 65BOpenMeta	2.1	—	—	—
236	▼ 22	Mistral 7B InstructOpenMistral	2.1	$0.25	88	0.8 s
236	▼ 22	Qwen Chat 14BOpenAlibaba	2.1	—	—	—
239	▼ 22	Granite 4.0 1BOpenIBM	2.1	—	—	—
240	New	Molmo2-8BOpenAllen Institute for AI	2.0	—	—	—
241	▼ 23	LFM2 8B A1BOpenLiquid AI	1.8	$0.000	—	—
242	▼ 23	Granite 3.3 8B (Non-reasoning)OpenIBM	1.8	$0.085	401	26 s
243	▼ 23	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	1.3	$0.40	—	—
244	▼ 23	Llama 3 Instruct 8BOpenMeta	1.2	$0.070	—	—
245	▼ 23	Gemma 3n E4B InstructOpenGoogle	1.2	$0.025	50	1.3 s
246	▼ 23	LFM2 1.2BOpenLiquid AI	1.1	$0.000	—	—
247	▼ 23	Gemma 3 4B InstructOpenGoogle	1.1	$0.000	—	—
248	▼ 23	Llama 3.2 Instruct 1BOpenMeta	1.1	$0.050	85	0.9 s
249	▼ 23	LFM2.5-VL-1.6BOpenLiquid AI	1.0	$0.000	455	1.3 s
250	▼ 23	Apertus 8B InstructOpenSwiss AI Initiative	1.0	$0.13	—	—
250	▼ 23	Gemma 3 1B InstructOpenGoogle	1.0	$0.000	—	—
250	▼ 23	Gemma 3n E2B InstructOpenGoogle	1.0	$0.000	—	—
250	▼ 23	Granite 4.0 350MOpenIBM	1.0	—	—	—
250	▼ 23	Granite 4.0 H 350MOpenIBM	1.0	—	—	—
250	▼ 23	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