Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	gpt-oss-120B (high)OpenOpenAI	58.0	$0.26	—	—
2	—	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	57.7	$1.9	—	—
3	—	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	57.5	$2.6	—	—
4	—	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	56.9	$0.32	—	—
5	—	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	56.0	$0.98	—	—
6	—	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	54.3	$1.9	—	—
7	—	DeepSeek V3.1 (Reasoning)OpenDeepSeek · 1 more variant	54.0	$0.65	—	—
8	—	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	52.0	$1.7	—	—
9	—	Seed-OSS-36B-InstructOpenByteDance Seed	51.6	$0.30	—	—
10	—	Apriel-v1.5-15B-ThinkerOpenServiceNow	51.6	$0.000	—	—
11	—	GLM-4.5 (Reasoning)OpenZ AI	51.3	$0.98	—	—
12	—	Kimi K2 0905OpenMoonshot AI · 1 more variant	50.4	$1.4	—	—
13	—	GLM-4.5-AirOpenZ AI	48.8	$0.43	—	—
14	—	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	46.4	$0.75	—	—
15	—	MiniMax M1 80kOpenMiniMax	46.2	$0.83	—	—
16	—	Qwen3 235B A22B 2507 InstructOpenAlibaba	45.3	$1.2	—	—
17	—	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	45.2	$0.18	—	—
18	—	Qwen3 Next 80B A3B InstructOpenAlibaba	44.8	$0.88	—	—
19	—	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	43.4	$0.000	—	—
20	—	gpt-oss-20B (high)OpenOpenAI	43.3	$0.095	—	—
21	—	Magistral Small 1.2OpenMistral	43.0	$0.75	—	—
22	—	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	42.6	$0.70	—	—
23	—	Qwen3 Coder 480B A35B InstructOpenAlibaba	42.3	$3.0	—	—
24	—	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research · 1 more variant	41.6	$1.5	—	—
25	—	DeepSeek V3 0324OpenDeepSeek · 1 more variant	41.3	$0.99	—	—
26	—	MiniMax M1 40kOpenMiniMax	40.0	$0.83	—	—
27	—	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	40.0	$0.43	—	—
28	—	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research · 1 more variant	39.2	$0.20	—	—
29	—	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	38.7	$2.6	—	—
30	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	38.5	$0.90	—	—
31	—	QwQ 32BOpenAlibaba	37.9	$0.44	—	—
32	—	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	37.0	$0.90	—	—
33	—	Qwen3 30B A3B 2507 InstructOpenAlibaba	37.0	$0.35	—	—
34	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	36.9	$0.070	—	—
35	—	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	36.0	$1.3	—	—
36	—	Llama 4 MaverickOpenMeta	35.8	$0.40	—	—
37	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	35.5	$0.000	—	—
38	—	Qwen3 Coder 30B A3B InstructOpenAlibaba	33.4	$0.90	—	—
39	—	ERNIE 4.5 300B A47BOpenBaidu	32.9	$0.49	—	—
40	—	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	32.7	$0.29	—	—
41	—	Magistral Small 1OpenMistral	31.9	$0.75	—	—
42	—	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	31.0	$0.065	—	—
43	—	Qwen3 4B 2507 InstructOpenAlibaba	30.4	$0.000	—	—
44	—	Qwen3 Omni 30B A3B InstructOpenAlibaba	30.2	$0.43	—	—
45	—	DeepSeek R1 Distill Llama 70BOpenDeepSeek	29.9	$0.77	—	—
46	—	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	29.7	$0.88	—	—
47	—	Mistral Small 3.2OpenMistral	29.1	$0.15	—	—
48	—	Qwen2.5 Instruct 72BOpenAlibaba	29.0	$0.000	—	—
49	—	MiniMax-Text-01OpenMiniMax	28.3	$0.43	—	—
50	—	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	28.3	$0.66	—	—
51	—	Llama 4 ScoutOpenMeta	28.1	$0.24	—	—
52	—	Llama 3.1 Instruct 405BOpenMeta	28.1	$3.4	—	—
53	—	QwQ 32B-PreviewOpenAlibaba	28.0	$0.67	—	—
54	—	Llama 3.3 Instruct 70BOpenMeta	27.9	$0.54	—	—
55	—	Devstral Small (Jul '25)OpenMistral · 1 more variant	27.2	$0.15	—	—
56	—	Qwen3 VL 8B InstructOpenAlibaba	27.1	$0.31	—	—
57	—	Command AOpenCohere	26.9	$4.4	—	—
58	—	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	26.8	$3.0	—	—
59	—	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	26.7	$0.000	—	—
60	—	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	26.1	$0.000	—	—
61	—	Reka Flash 3OpenReka AI	25.9	$0.35	—	—
62	—	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	25.4	$0.000	—	—
63	—	Pixtral LargeOpenMistral	25.0	$3.0	—	—
64	—	Grok 2 (Dec '24)OpenxAI	24.7	$0.000	—	—
65	—	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	23.6	$0.60	—	—
66	—	Mistral Small 3.1OpenMistral	23.1	$0.15	—	—
67	—	Qwen2.5 Instruct 32BOpenAlibaba	22.9	$0.000	—	—
68	—	Granite 4.0 H SmallOpenIBM	22.7	$0.11	—	—
69	—	Phi-4OpenMicrosoft Azure	22.7	$0.22	—	—
70	—	Llama 3.1 Instruct 70BOpenMeta	22.6	$0.72	—	—
71	—	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	22.4	$0.40	—	—
72	—	Gemma 3 27B InstructOpenGoogle	22.2	$0.000	—	—
73	—	Qwen2.5 Coder Instruct 32BOpenAlibaba	21.8	$0.20	—	—
74	—	Mistral Small 3OpenMistral	21.2	$0.15	—	—
75	—	Jamba Reasoning 3BOpenAI21 Labs	20.9	$0.000	—	—
76	—	Jamba 1.7 LargeOpenAI21 Labs	20.8	$3.5	—	—
77	—	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	20.7	$0.000	—	—
78	—	Gemma 3 12B InstructOpenGoogle	20.4	$0.000	—	—
79	—	DeepSeek R1 Distill Llama 8BOpenDeepSeek	19.5	$0.000	—	—
80	—	R1 1776OpenPerplexity	19.1	$3.5	—	—
81	—	Llama 3.2 Instruct 90B (Vision)OpenMeta	18.9	$0.72	—	—
81	—	Solar MiniOpenUpstage	18.9	$0.15	—	—
83	—	Grok-1OpenxAI	18.2	$0.000	—	—
84	—	Qwen2 Instruct 72BOpenAlibaba	18.1	$0.000	—	—
85	—	LFM2 8B A1BOpenLiquid AI	17.4	$0.000	—	—
86	—	Gemma 2 27BOpenGoogle	17.2	$0.000	—	—
87	—	Llama 3.1 Instruct 8BOpenMeta	16.9	$0.089	—	—
88	—	Granite 4.0 MicroOpenIBM	16.2	$0.000	—	—
89	—	Phi-4 Mini InstructOpenMicrosoft Azure	15.7	$0.000	—	—
90	—	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	15.5	$0.000	—	—
91	—	Llama 3.2 Instruct 11B (Vision)OpenMeta	15.5	$0.16	—	—
92	—	Gemma 3n E4B InstructOpenGoogle	15.5	$0.025	—	—
93	—	Granite 3.3 8B (Non-reasoning)OpenIBM	15.2	$0.085	—	—
94	—	Jamba 1.5 LargeOpenAI21 Labs	14.8	$3.5	—	—
95	—	Jamba 1.7 MiniOpenAI21 Labs	14.8	$0.25	—	—
96	—	Gemma 3 4B InstructOpenGoogle	14.7	$0.000	—	—
97	—	Hermes 3 - Llama-3.1 70BOpenNous Research	14.7	$0.30	—	—
98	—	DeepSeek-Coder-V2OpenDeepSeek	14.5	$0.000	—	—
99	—	Phi-3 Medium Instruct 14BOpenMicrosoft Azure	14.4	$0.30	—	—
100	—	Jamba 1.6 LargeOpenAI21 Labs	14.3	$3.5	—	—
101	—	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	14.2	$0.40	—	—
102	—	Aya Expanse 32BOpenCohere	13.6	$0.75	—	—
103	—	Llama 3 Instruct 70BOpenMeta	13.0	$0.75	—	—
104	—	Mistral Small (Sep '24)OpenMistral	13.0	$0.30	—	—
105	—	Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure	12.7	$0.23	—	—
106	—	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	12.5	$0.000	—	—
107	—	Phi-4 Multimodal InstructOpenMicrosoft Azure	12.4	$0.000	—	—
108	—	Ministral 8BOpenMistral	12.4	$0.10	—	—
109	—	Qwen2.5 Coder Instruct 7BOpenAlibaba	12.2	$0.000	—	—
110	—	LFM2 2.6BOpenLiquid AI	11.8	$0.000	—	—
111	—	Mixtral 8x22B InstructOpenMistral	11.7	$3.0	—	—
112	—	Llama 2 Chat 7BOpenMeta	11.3	$0.10	—	—
113	—	Gemma 3n E2B InstructOpenGoogle	11.3	$0.000	—	—
114	—	Llama 3.2 Instruct 3BOpenMeta	11.2	$0.048	—	—
115	—	Qwen1.5 Chat 110BOpenAlibaba	10.5	$0.000	—	—
116	—	Aya Expanse 8BOpenCohere	10.0	$0.75	—	—
117	—	Pixtral 12B (2409)OpenMistral	8.9	$0.15	—	—
118	—	Llama 3.2 Instruct 1BOpenMeta	8.9	$0.053	—	—
119	—	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	8.6	$0.000	—	—
120	—	DeepSeek-V2-ChatOpenDeepSeek	8.6	$0.000	—	—
121	—	LFM2 1.2BOpenLiquid AI	8.0	$0.000	—	—
122	—	Gemma 2 9BOpenGoogle	7.8	$0.045	—	—
123	—	Arctic InstructOpenSnowflake	7.6	$0.000	—	—
123	—	Qwen Chat 72BOpenAlibaba	7.6	$1.0	—	—
125	—	Command-R+ (Aug '24)OpenCohere · 3 more variants	7.1	$4.4	—	—
126	—	Llama 3 Instruct 8BOpenMeta	7.0	$0.055	—	—
127	—	Gemma 3 1B InstructOpenGoogle	6.8	$0.000	—	—
128	—	DeepSeek Coder V2 Lite InstructOpenDeepSeek	6.1	$0.000	—	—
129	—	Codestral (May '24)OpenMistral	6.0	$0.000	—	—
130	—	Gemma 3 270MOpenGoogle	5.6	$0.000	—	—
131	—	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	5.6	$0.000	—	—
131	—	Llama 2 Chat 70BOpenMeta	5.6	$0.000	—	—
133	—	Llama 2 Chat 13BOpenMeta	5.5	$0.000	—	—
134	—	OpenChat 3.5 (1210)OpenOpenChat	5.4	$0.000	—	—
135	—	DBRX InstructOpenDatabricks	5.3	$0.000	—	—
136	—	Mistral NeMoOpenMistral	5.2	$0.15	—	—
137	—	Jamba 1.5 MiniOpenAI21 Labs	4.0	$0.25	—	—
138	—	Jamba 1.6 MiniOpenAI21 Labs	3.3	$0.25	—	—
139	—	Mixtral 8x7B InstructOpenMistral	2.6	$0.70	—	—
140	—	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	1.8	$0.000	—	—
141	—	Codestral-MambaOpenMistral	1.0	$0.000	—	—
141	—	Llama 65BOpenMeta	1.0	$0.000	—	—
141	—	Mistral 7B InstructOpenMistral	1.0	$0.25	—	—
141	—	Qwen Chat 14BOpenAlibaba	1.0	$0.000	—	—

94 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