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	192	1.4 s
2	—	MiniMax-M3OpenMiniMax	44.4	$0.52	96	1.6 s
3	—	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	44.3	$0.54	64	1.6 s
4	—	Kimi K2.6OpenKimi · 1 more variant	44.2	$1.7	59	2.8 s
5	—	MiMo-V2.5-ProOpenXiaomi · 1 more variant	42.2	$0.54	61	3.2 s
6	—	Kimi K2.7 CodeOpenKimi	41.9	$1.7	48	2.9 s
7	New	Hy3OpenTencent	41.2	$0.000	59	2.5 s
8	▼ 1	Nex-N2-ProOpenNex AGI	41.0	$1.0	139	1.7 s
9	New	Inkling (xhigh)OpenThinking Machines	40.7	$2.6	—	—
10	▼ 2	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	40.3	$0.18	120	1.2 s
11	▼ 2	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	40.2	$2.2	81	1.5 s
12	▼ 2	GLM-5 (Reasoning)OpenZ AI · 1 more variant	39.5	$1.6	54	1.7 s
13	▼ 2	MiniMax-M2.7OpenMiniMax	38.1	$0.52	69	1.7 s
14	▼ 1	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	37.8	$1.2	218	1.2 s
15	▼ 1	MiMo-V2.5OpenXiaomi	37.2	$0.18	63	4.3 s
16	▼ 1	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	37.1	$1.4	56	3.7 s
17	▼ 5	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	35.4	$1.2	56	2.9 s
18	▼ 2	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	33.8	$0.83	77	5.6 s
19	▼ 2	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	33.7	$1.0	121	0.8 s
20	▼ 2	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	33.7	$1.4	62	2.6 s
21	▼ 2	MiniMax-M2.5OpenMiniMax	33.7	$0.52	88	1.7 s
22	▼ 2	Hy3-preview (Reasoning)OpenTencent · 1 more variant	33.6	$0.20	158	3.1 s
23	New	LongCat 2.0OpenLongCat	33.5	—	—	—
24	▼ 3	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	33.2	—	—	—
25	▼ 3	Kimi K2 ThinkingOpenKimi	32.7	$1.1	124	1.4 s
26	▼ 3	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	32.3	$1.1	135	2.3 s
27	▼ 3	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	32.0	$0.32	—	—
28	▼ 3	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	31.6	$0.56	152	2.3 s
29	▼ 3	MiniMax-M2.1OpenMiniMax	31.4	$0.52	86	1.7 s
30	▼ 3	Ring-2.6-1TOpenInclusionAI	30.6	$0.85	135	3.2 s
31	▼ 3	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	30.4	$1.9	—	—
32	▼ 3	Step 3.7 FlashOpenStepFun	30.3	$0.44	396	0.8 s
33	▼ 3	Mistral Medium 3.5OpenMistral	29.9	$3.0	56	2.3 s
34	▼ 3	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	29.4	$0.000	35	1.2 s
35	▼ 3	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	29.3	$0.69	142	2.2 s
36	▼ 3	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	28.7	$0.96	48	2.4 s
37	▼ 3	MiniMax-M2OpenMiniMax	28.3	$0.52	86	1.6 s
38	▼ 3	Ling-2.6-1TOpenInclusionAI	26.1	$0.85	—	—
39	▼ 3	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	25.7	$0.20	—	—
40	▼ 3	Step 3.5 FlashOpenStepFun	25.5	$0.15	295	1.0 s
41	▼ 3	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	25.4	$0.32	—	—
42	▼ 3	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	25.4	$0.38	161	1.5 s
43	▼ 3	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	24.7	—	—	—
44	▼ 3	Trinity Large ThinkingOpenArcee AI	24.5	$0.40	208	1.0 s
45	▼ 3	gpt-oss-120b (high)OpenOpenAI · 1 more variant	23.8	$0.26	307	0.8 s
46	▼ 3	Kimi K2 0905OpenKimi · 1 more variant	23.5	$1.1	38	2.0 s
47	▼ 3	EXAONE 4.5 33BOpenLG AI Research	23.0	—	—	—
48	▼ 3	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	22.9	$0.15	98	1.3 s
49	▼ 3	Command A+OpenCohere · 1 more variant	22.5	$0.000	185	0.4 s
50	▼ 3	DeepSeek V3.2 SpecialeOpenDeepSeek	22.2	—	—	—
51	▼ 3	Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant	22.0	$0.15	112	2.5 s
52	▼ 3	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	21.4	$0.11	55	1.7 s
53	▼ 3	Nemotron Cascade 2 30B A3BOpenNVIDIA	21.3	—	—	—
54	▼ 3	Apriel-v1.5-15B-ThinkerOpenServiceNow	21.2	$0.000	—	—
55	▼ 3	Qwen3 Coder NextOpenAlibaba	21.1	$0.56	106	1.5 s
56	▼ 3	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	21.0	$0.84	—	—
57	▼ 3	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	20.6	$2.6	56	2.9 s
58	▼ 2	Apriel-v1.6-15B-ThinkerOpenServiceNow	20.5	$0.000	—	—
59	▼ 2	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	20.1	$0.060	24	0.8 s
60	▼ 2	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	20.1	$2.1	—	—
61	▼ 6	North Mini CodeOpenCohere	19.8	$0.000	118	0.3 s
62	▼ 3	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	19.6	$2.6	59	2.8 s
63	▼ 3	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	19.6	$0.26	167	0.8 s
64	▼ 3	GLM-4.5 (Reasoning)OpenZ AI	19.5	—	—	—
65	▼ 3	Devstral 2OpenMistral	19.2	$0.000	76	1.5 s
66	▼ 3	Seed-OSS-36B-InstructOpenByteDance Seed	18.3	$0.30	34	3.0 s
67	▼ 3	Qwen3 235B A22B 2507 InstructOpenAlibaba	18.2	$1.2	60	2.3 s
68	▼ 3	Qwen3 Coder 480B A35B InstructOpenAlibaba	18.0	$3.0	62	2.9 s
69	▼ 3	Qwen3 VL 32B (Reasoning)OpenAlibaba	17.9	$2.6	90	2.6 s
70	▼ 3	HyperNova 60B 2605OpenMultiverse Computing	17.8	$0.065	362	0.9 s
71	▼ 3	MiniMax M1 80kOpenMiniMax	17.7	$0.96	—	—
72	▼ 3	Devstral Small 2OpenMistral	17.4	$0.000	77	1.3 s
73	▼ 3	K2 Think V2OpenMBZUAI Institute of Foundation Models	17.3	—	—	—
74	▼ 3	LongCat Flash LiteOpenLongCat	17.2	—	—	—
75	▼ 3	HyperCLOVA X SEED Think (32B)OpenNaver	17.0	—	—	—
76	▼ 3	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	16.8	$0.45	50	4.3 s
77	▼ 3	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	16.7	$1.9	182	2.1 s
78	▼ 3	GLM-4.5-AirOpenZ AI	16.5	$0.37	71	2.7 s
79	▼ 3	Ring-1TOpenInclusionAI	16.2	—	—	—
80	▼ 3	Mistral Large 3OpenMistral	15.9	$0.75	51	1.1 s
81	▼ 3	INTELLECT-3OpenPrime Intellect	15.6	—	—	—
82	▼ 3	DeepSeek V3 0324OpenDeepSeek · 1 more variant	15.4	$1.2	—	—
83	▼ 3	Solar Open 100B (Reasoning)OpenUpstage	15.1	—	—	—
84	▼ 3	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	14.9	$0.13	323	1.0 s
85	▼ 3	gpt-oss-20b (high)OpenOpenAI · 1 more variant	14.9	$0.088	225	0.8 s
86	▼ 3	Mistral Small 3.1OpenMistral	14.7	$0.15	149	0.7 s
87	▼ 3	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	14.4	$0.75	144	2.3 s
88	▼ 3	MiniMax M1 40kOpenMiniMax	14.4	—	—	—
89	▼ 3	Qwen3 VL 235B A22B InstructOpenAlibaba	14.3	$1.2	51	2.7 s
90	▼ 3	Llama 4 MaverickOpenMeta	14.3	$0.48	114	1.0 s
91	▼ 3	K2-V2 (high)OpenMBZUAI Institute of Foundation Models · 2 more variants	14.2	—	—	—
92	▼ 3	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	14.2	$0.088	167	1.2 s
93	▼ 3	Ling 2.6 FlashOpenInclusionAI	14.1	$0.15	181	1.1 s
94	▼ 3	Qwen3 Next 80B A3B InstructOpenAlibaba	13.7	$0.88	186	2.2 s
95	▼ 3	Tri-21B-think PreviewOpenTrillion Labs	13.6	—	—	—
96	▼ 3	Qwen3 Coder 30B A3B InstructOpenAlibaba	13.6	$0.90	100	2.6 s
97	▼ 3	DiffusionGemma 26B A4BOpenGoogle	13.5	—	—	—
98	▼ 3	QwQ 32BOpenAlibaba	13.4	$0.75	31	2.1 s
99	▼ 3	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	13.3	$0.75	111	2.2 s
100	▼ 3	Ling-1TOpenInclusionAI	12.8	—	—	—
101	▼ 3	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	12.5	—	—	—
102	▼ 3	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	12.4	$0.40	58	2.4 s
103	▼ 3	Tri-21B-ThinkOpenTrillion Labs	12.4	—	—	—
104	▼ 3	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	12.2	—	—	—
105	▼ 3	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	12.0	—	—	—
106	▼ 3	MiniCPM5-1B (Reasoning)OpenOpenBMB · 1 more variant	12.0	—	—	—
107	▼ 3	Sarvam 105B (high)OpenSarvam	11.9	$0.074	96	2.2 s
108	▼ 3	Devstral Small (May '25)OpenMistral · 1 more variant	11.8	—	—	—
109	▼ 3	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	11.5	$2.6	96	2.4 s
110	▼ 3	Magistral Small 1.2OpenMistral	11.3	$0.75	82	0.9 s
111	▼ 3	Nanbeige4.1-3BOpenNanbeige	11.1	—	—	—
112	▼ 3	Qwen3 VL 32B InstructOpenAlibaba	11.1	$1.2	76	2.9 s
113	▼ 3	Ministral 3 14BOpenMistral	11.1	$0.20	58	0.9 s
114	▼ 3	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	11.0	—	—	—
115	▼ 3	Magistral Small 1OpenMistral	10.7	—	—	—
116	▼ 3	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	10.6	—	—	—
117	▼ 3	Qwen3 VL 8B (Reasoning)OpenAlibaba	10.6	$0.66	113	2.3 s
118	▼ 3	Mistral Small 3.2OpenMistral	10.6	$0.15	146	0.7 s
119	▼ 3	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	10.4	$1.3	63	2.7 s
120	▼ 3	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	10.4	—	—	—
121	▼ 3	Llama 4 ScoutOpenMeta	10.0	$0.29	89	0.8 s
122	▼ 3	Qwen3 VL 30B A3B InstructOpenAlibaba	10.0	$0.35	112	2.1 s
123	▼ 3	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research · 1 more variant	10.0	$0.20	89	1.4 s
124	▼ 3	DeepSeek R1 Distill Llama 70BOpenDeepSeek	9.9	$0.79	31	0.7 s
125	▼ 3	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	9.8	—	—	—
126	▼ 3	Falcon-H1R-7BOpenTII UAE	9.8	—	—	—
127	▼ 3	Ling-flash-2.0OpenInclusionAI	9.7	$0.25	66	1.6 s
128	▼ 3	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	9.6	$0.43	100	1.9 s
129	▼ 3	Qwen2.5 Instruct 72BOpenAlibaba	9.6	$0.48	—	—
130	▼ 3	Step3 VL 10BOpenStepFun	9.5	—	—	—
131	▼ 3	Llama 3.3 Instruct 70BOpenMeta	9.4	$0.61	86	1.6 s
132	▼ 3	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	9.3	—	—	—
133	▼ 3	QwQ 32B-PreviewOpenAlibaba	9.2	—	—	—
134	▼ 3	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	9.1	$0.90	74	4.8 s
135	▼ 3	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	9.1	—	—	—
136	▼ 3	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	9.1	$0.90	53	2.3 s
137	▼ 3	Qwen3 30B A3B 2507 InstructOpenAlibaba	9.1	$0.35	156	1.9 s
138	▼ 3	ERNIE 4.5 300B A47BOpenBaidu	9.0	$0.49	—	—
139	▼ 3	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research · 1 more variant	9.0	$1.5	39	2.4 s
140	▼ 3	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	9.0	$0.30	90	8.6 s
141	▼ 3	Ministral 3 8BOpenMistral	9.0	$0.15	114	0.8 s
142	▼ 3	Granite 4.1 30BOpenIBM	8.9	—	—	—
143	▼ 3	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	8.8	$0.070	74	6.6 s
144	▼ 3	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	8.7	—	—	—
145	▼ 3	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	8.5	—	—	—
146	▼ 3	Kimi Linear 48B A3B InstructOpenKimi	8.5	—	—	—
147	▼ 3	Llama 3.1 Instruct 405BOpenMeta	8.5	$6.2	—	—
148	▼ 3	Qwen3 VL 8B InstructOpenAlibaba	8.4	$0.31	122	2.2 s
149	▼ 3	LFM2.5-8B-A1BOpenLiquid AI	8.3	$0.000	338	2.9 s
150	▼ 3	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	8.3	$0.66	39	3.8 s
151	▼ 3	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	8.3	—	—	—
152	▼ 3	Ring-flash-2.0OpenInclusionAI	8.2	$0.25	—	—
153	▼ 3	Pixtral LargeOpenMistral	8.1	—	—	—
154	▼ 3	Olmo 3.1 32B ThinkOpenAllen Institute for AI	8.1	$0.000	—	—
155	▼ 3	Grok 2 (Dec '24)OpenSpaceXAI	8.0	—	—	—
156	▼ 3	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.9	—	—	—
157	▼ 3	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	7.6	—	—	—
158	▼ 3	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	7.6	$1.2	106	4.7 s
159	▼ 3	Llama 3.1 Instruct 8BOpenMeta	7.6	$0.10	149	0.9 s
160	▼ 3	Qwen2.5 Instruct 32BOpenAlibaba	7.5	—	—	—
161	▼ 3	Gemma 3 27B InstructOpenGoogle	7.4	$0.000	—	—
162	▼ 3	Qwen3 4B 2507 InstructOpenAlibaba	7.1	—	—	—
163	▼ 3	Qwen2.5 Coder Instruct 32BOpenAlibaba	7.1	—	—	—
164	▼ 3	Mistral Small 3OpenMistral	6.9	$0.15	151	0.8 s
165	▼ 3	Ministral 3 3BOpenMistral	6.8	$0.10	167	0.6 s
166	▼ 3	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	6.8	—	—	—
167	▼ 3	Llama 3.1 Instruct 70BOpenMeta	6.8	$0.56	62	1.4 s
168	▼ 3	Granite 4.1 8BOpenIBM	6.7	$0.063	121	0.8 s
169	▼ 3	Sarvam 30B (high)OpenSarvam	6.6	$0.047	166	1.9 s
170	▼ 3	Olmo 3.1 32B InstructOpenAllen Institute for AI	6.5	—	—	—
171	▼ 3	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.4	—	—	—
172	▼ 3	Olmo 3 32B ThinkOpenAllen Institute for AI	6.4	—	—	—
173	▼ 3	R1 1776OpenPerplexity	6.3	—	—	—
174	▼ 3	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.2	$2.0	—	—
174	▼ 3	Solar MiniOpenUpstage	6.2	$0.15	—	—
176	▼ 3	Grok-1OpenSpaceXAI	6.0	—	—	—
177	▼ 3	Qwen2 Instruct 72BOpenAlibaba	6.0	—	—	—
178	▼ 3	Phi-4 Mini InstructOpenMicrosoft	6.0	$0.000	44	0.8 s
179	▼ 3	Gemma 3 12B InstructOpenGoogle	5.5	$0.000	—	—
180	▼ 3	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	5.5	—	—	—
181	▼ 3	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	5.3	—	—	—
182	▼ 3	Jamba 1.7 LargeOpenAI21 Labs	5.3	$3.5	57	1.4 s
183	▼ 3	Granite 4.0 H SmallOpenIBM	5.2	$0.11	407	10 s
184	▼ 3	Jamba 1.5 LargeOpenAI21 Labs	5.1	$3.5	—	—
185	▼ 3	Qwen3 Omni 30B A3B InstructOpenAlibaba	5.1	$0.43	97	1.9 s
186	▼ 3	Hermes 3 - Llama-3.1 70BOpenNous Research	5.1	$0.70	35	1.9 s
187	▼ 3	DeepSeek-Coder-V2OpenDeepSeek	5.1	—	—	—
188	▼ 3	OLMo 2 32BOpenAllen Institute for AI	5.0	—	—	—
189	▼ 3	Jamba 1.6 LargeOpenAI21 Labs	5.0	$3.5	55	1.4 s
190	▼ 3	LFM2 24B A2BOpenLiquid AI	4.9	—	—	—
191	▼ 3	Phi-4OpenMicrosoft	4.9	$0.22	42	3.8 s
192	▼ 3	Granite 4.1 3BOpenIBM	4.7	—	—	—
193	▼ 3	Mistral Small (Sep '24)OpenMistral	4.7	$0.30	156	0.9 s
194	▼ 3	Phi-3 Mini Instruct 3.8BOpenMicrosoft	4.6	—	—	—
195	▼ 3	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	4.6	—	—	—
196	▼ 3	Phi-4 Multimodal InstructOpenMicrosoft	4.5	$0.000	18	0.7 s
197	▼ 3	Qwen2.5 Coder Instruct 7BOpenAlibaba	4.5	—	—	—
198	▼ 3	Mixtral 8x22B InstructOpenMistral	4.4	—	—	—
199	▼ 3	Llama 2 Chat 7BOpenMeta	4.3	$0.10	—	—
200	▼ 3	Llama 3.2 Instruct 3BOpenMeta	4.2	—	—	—
201	▼ 3	MiniCPM-V 4.6 1.3BOpenOpenBMB	4.2	—	—	—
202	▼ 3	Jamba Reasoning 3BOpenAI21 Labs	4.1	—	—	—
203	▼ 3	Qwen3 VL 4B InstructOpenAlibaba	4.1	—	—	—
204	▼ 3	Qwen1.5 Chat 110BOpenAlibaba	4.1	—	—	—
205	▼ 3	Reka Flash 3OpenReka AI	4.1	$0.35	—	—
206	▼ 3	Olmo 3 7B ThinkOpenAllen Institute for AI	4.0	—	—	—
207	▼ 3	OLMo 2 7BOpenAllen Institute for AI	3.9	—	—	—
208	▼ 3	Molmo 7B-DOpenAllen Institute for AI	3.8	—	—	—
209	▼ 3	Ling-mini-2.0OpenInclusionAI	3.8	—	—	—
210	▼ 3	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	3.7	—	—	—
211	▼ 3	DeepSeek-V2-ChatOpenDeepSeek	3.6	—	—	—
212	▼ 3	Llama 3 Instruct 70BOpenMeta	3.5	$1.2	—	—
213	▼ 3	Arctic InstructOpenSnowflake	3.4	—	—	—
213	▼ 3	Qwen Chat 72BOpenAlibaba	3.4	—	—	—
215	▼ 3	Llama 3.2 Instruct 11B (Vision)OpenMeta	3.3	$0.36	27	0.8 s
216	▼ 3	DeepSeek Coder V2 Lite InstructOpenDeepSeek	3.1	—	—	—
217	▼ 3	Sarvam M (Reasoning)OpenSarvam	3.0	$0.000	—	—
218	▼ 3	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	3.0	—	—	—
218	▼ 3	Llama 2 Chat 70BOpenMeta	3.0	—	—	—
220	▼ 3	Llama 2 Chat 13BOpenMeta	3.0	—	—	—
221	▼ 3	Command-R+ (Apr '24)OpenCohere · 1 more variant	3.0	$6.0	—	—
222	▼ 3	OpenChat 3.5 (1210)OpenOpenChat	3.0	—	—	—
223	▼ 3	DBRX InstructOpenDatabricks	3.0	—	—	—
224	▼ 3	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	2.9	—	—	—
225	▼ 3	Olmo 3 7B InstructOpenAllen Institute for AI	2.8	$0.13	—	—
226	▼ 3	LFM2.5-1.2B-ThinkingOpenLiquid AI	2.7	—	—	—
227	▼ 3	Jamba 1.7 MiniOpenAI21 Labs	2.7	—	—	—
228	▼ 3	LFM2 2.6BOpenLiquid AI	2.7	—	—	—
229	▼ 3	LFM2.5-1.2B-InstructOpenLiquid AI	2.7	—	—	—
230	▼ 3	Jamba 1.5 MiniOpenAI21 Labs	2.7	$0.25	—	—
231	▼ 3	Granite 4.0 H 1BOpenIBM	2.7	—	—	—
232	▼ 3	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	2.6	—	—	—
233	▼ 3	Jamba 1.6 MiniOpenAI21 Labs	2.6	$0.25	181	0.8 s
234	▼ 3	Mixtral 8x7B InstructOpenMistral	2.4	$0.51	—	—
235	▼ 3	Gemma 3 270MOpenGoogle	2.4	—	—	—
236	▼ 3	Apertus 70B InstructOpenSwiss AI Initiative	2.4	$1.3	—	—
237	▼ 3	Granite 4.0 MicroOpenIBM	2.4	—	—	—
238	▼ 3	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	2.3	—	—	—
239	▼ 3	Llama 65BOpenMeta	2.1	—	—	—
239	▼ 3	Mistral 7B InstructOpenMistral	2.1	$0.25	110	0.9 s
239	▼ 3	Qwen Chat 14BOpenAlibaba	2.1	—	—	—
242	▼ 3	Granite 4.0 1BOpenIBM	2.1	—	—	—
243	▼ 3	Molmo2-8BOpenAllen Institute for AI	2.0	—	—	—
244	▼ 3	LFM2 8B A1BOpenLiquid AI	1.8	—	—	—
245	▼ 3	Granite 3.3 8B (Non-reasoning)OpenIBM	1.8	$0.085	366	27 s
246	▼ 3	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	1.3	—	—	—
247	▼ 3	Llama 3 Instruct 8BOpenMeta	1.2	$0.070	—	—
248	▼ 3	Gemma 3n E4B InstructOpenGoogle	1.2	$0.025	57	1.3 s
249	▼ 3	LFM2 1.2BOpenLiquid AI	1.1	—	—	—
250	▼ 3	Gemma 3 4B InstructOpenGoogle	1.1	$0.000	—	—
251	▼ 3	Llama 3.2 Instruct 1BOpenMeta	1.1	—	—	—
252	▼ 3	LFM2.5-VL-1.6BOpenLiquid AI	1.0	$0.000	430	2.0 s
253	▼ 3	Apertus 8B InstructOpenSwiss AI Initiative	1.0	$0.13	—	—
253	▼ 3	Gemma 3 1B InstructOpenGoogle	1.0	$0.000	—	—
253	▼ 3	Gemma 3n E2B InstructOpenGoogle	1.0	$0.000	—	—
253	▼ 3	Granite 4.0 350MOpenIBM	1.0	—	—	—
253	▼ 3	Granite 4.0 H 350MOpenIBM	1.0	—	—	—
253	▼ 3	Tiny Aya GlobalOpenCohere	1.0	$0.000	—	—

208 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