Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant	72.9	$4.5	—	—
2	—	GPT-5.2 (xhigh)ClosedOpenAI · 1 more variant	72.6	$4.8	—	—
3	—	Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant	71.3	$1.1	—	—
4	—	Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant	69.8	$10	—	—
5	—	GPT-5.1 (high)ClosedOpenAI · 1 more variant	69.7	$3.4	—	—
6	—	GPT-5 Codex (high)ClosedOpenAI	68.5	$3.4	—	—
7	—	GPT-5 (high)ClosedOpenAI · 4 more variants	68.5	$3.4	—	—
8	—	GPT-5.1 Codex (high)ClosedOpenAI	66.9	$3.4	—	—
9	—	o3ClosedOpenAI	65.5	$3.5	—	—
10	—	Grok 4ClosedxAI	65.3	$6.0	—	—
11	—	o3-proClosedOpenAI	65.3	$35	—	—
12	—	GPT-5 mini (high)ClosedOpenAI · 2 more variants	64.3	$0.69	—	—
13	—	Grok 4.1 Fast (Reasoning)ClosedxAI · 1 more variant	64.1	$0.28	—	—
14	—	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	62.7	$6.0	—	—
15	—	Nova 2.0 Pro Preview (medium)ClosedAmazon · 2 more variants	62.4	$3.4	—	—
16	—	GPT-5.1 Codex mini (high)ClosedOpenAI	62.3	$0.69	—	—
17	—	gpt-oss-120B (high)OpenOpenAI · 1 more variant	60.5	$0.26	—	—
18	—	Grok 4 Fast (Reasoning)ClosedxAI · 1 more variant	60.3	$0.28	—	—
19	—	Gemini 2.5 ProClosedGoogle	59.6	$3.4	—	—
20	—	o4-mini (high)ClosedOpenAI	59.6	$1.9	—	—
21	—	Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant	59.3	$30	—	—
22	—	Nova 2.0 Lite (medium)ClosedAmazon · 2 more variants	57.7	$0.85	—	—
23	—	Grok 3 mini Reasoning (high)ClosedxAI	57.1	$0.35	—	—
24	—	Apriel-v1.6-15B-ThinkerOpenServiceNow	57.0	$0.000	—	—
25	—	Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	56.5	$6.0	—	—
26	—	Nova 2.0 Omni (medium)ClosedAmazon · 2 more variants	56.0	$0.85	—	—
27	—	Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant	54.6	$2.0	—	—
28	—	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants	54.4	$0.85	—	—
29	—	Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant	54.2	$30	—	—
30	—	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant	54.1	$3.4	—	—
31	—	gpt-oss-20B (high)OpenOpenAI · 1 more variant	52.1	$0.10	—	—
32	—	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	51.8	$0.11	—	—
33	—	Apriel-v1.5-15B-ThinkerOpenServiceNow	51.6	$0.000	—	—
34	—	Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant	51.2	$0.85	—	—
35	—	GPT-5 nano (high)ClosedOpenAI · 2 more variants	51.0	$0.14	—	—
36	—	o3-mini (high)ClosedOpenAI · 1 more variant	50.8	$1.9	—	—
37	—	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	49.9	$6.0	—	—
38	—	Grok Code Fast 1ClosedxAI	48.7	$0.53	—	—
39	—	o1-proClosedOpenAI	48.0	$263	—	—
40	—	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle · 1 more variant	47.9	$0.18	—	—
41	—	o1ClosedOpenAI · 1 more variant	47.2	$26	—	—
42	—	Sonar Reasoning ProClosedPerplexity	46.3	$0.000	—	—
43	—	Grok 3ClosedxAI	45.3	$6.0	—	—
44	—	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	45.2	$0.18	—	—
45	—	GPT-4.1ClosedOpenAI	43.4	$3.5	—	—
46	—	GPT-4.1 miniClosedOpenAI	42.5	$0.70	—	—
47	—	Grok 3 Reasoning BetaClosedxAI	41.4	$0.000	—	—
48	—	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	40.7	$0.30	—	—
49	—	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant	40.1	$0.18	—	—
50	—	o1-miniClosedOpenAI	39.2	$0.000	—	—
51	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	38.5	$0.90	—	—
52	—	GPT-4.5 (Preview)ClosedOpenAI	38.4	$0.000	—	—
53	—	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant	37.7	$0.000	—	—
54	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	37.2	$0.070	—	—
55	—	Llama 4 MaverickOpenMeta	35.8	$0.42	—	—
56	—	GPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI · 4 more variants	35.6	$7.5	—	—
57	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	35.5	$0.000	—	—
58	—	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	34.6	$0.000	—	—
59	—	Sonar ReasoningClosedPerplexity	34.2	$2.0	—	—
60	—	Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant	33.6	$0.18	—	—
61	—	Nova PremierClosedAmazon	32.3	$5.0	—	—
62	—	Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant	30.0	$0.000	—	—
63	—	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant	29.9	$6.0	—	—
64	—	SonarClosedPerplexity	28.8	$1.0	—	—
65	—	Sonar ProClosedPerplexity	28.2	$6.0	—	—
66	—	Llama 4 ScoutOpenMeta	28.1	$0.24	—	—
67	—	Llama 3.1 Instruct 405BOpenMeta	28.1	$4.5	—	—
68	—	Llama 3.3 Instruct 70BOpenMeta	27.9	$0.61	—	—
69	—	GPT-4.1 nanoClosedOpenAI	27.3	$0.18	—	—
70	—	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant	26.8	$0.13	—	—
71	—	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	26.1	$0.000	—	—
72	—	Nova ProClosedAmazon	25.0	$1.4	—	—
73	—	Grok 2 (Dec '24)OpenxAI	24.7	$4.0	—	—
74	—	Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant	24.4	$0.000	—	—
75	—	GPT-4 TurboClosedOpenAI	24.2	$15	—	—
76	—	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	23.6	$1.2	—	—
77	—	Grok BetaClosedxAI	23.0	$0.000	—	—
78	—	Granite 4.0 H SmallOpenIBM	22.7	$0.11	—	—
79	—	Phi-4OpenMicrosoft Azure	22.7	$0.22	—	—
80	—	Llama 3.1 Instruct 70BOpenMeta	22.6	$0.56	—	—
81	—	Gemma 3 27B InstructOpenGoogle	22.2	$0.000	—	—
82	—	GPT-4ClosedOpenAI	21.5	$38	—	—
83	—	Nova LiteClosedAmazon	21.5	$0.11	—	—
84	—	GPT-4o miniClosedOpenAI	21.2	$0.26	—	—
85	—	Claude 3 OpusClosedAnthropic	20.6	$30	—	—
86	—	Gemma 3 12B InstructOpenGoogle	20.4	$0.000	—	—
87	—	Claude 3.5 HaikuClosedAnthropic	20.2	$1.6	—	—
88	—	R1 1776OpenPerplexity	19.1	$0.000	—	—
89	—	Llama 3.2 Instruct 90B (Vision)OpenMeta	18.9	$0.72	—	—
90	—	Grok-1OpenxAI	18.2	$0.000	—	—
91	—	Nova MicroClosedAmazon	17.7	$0.061	—	—
92	—	LFM2 8B A1BOpenLiquid AI	17.4	$0.000	—	—
93	—	Llama 3.1 Instruct 8BOpenMeta	16.9	$0.10	—	—
94	—	Gemini 1.5 Flash-8BClosedGoogle	16.3	$0.000	—	—
95	—	Granite 4.0 MicroOpenIBM	16.2	$0.000	—	—
96	—	Phi-4 Mini InstructOpenMicrosoft Azure	15.7	$0.000	—	—
97	—	Llama 3.2 Instruct 11B (Vision)OpenMeta	15.5	$0.16	—	—
98	—	Gemma 3n E4B InstructOpenGoogle	15.5	$0.025	—	—
99	—	Granite 3.3 8B (Non-reasoning)OpenIBM	15.2	$0.085	—	—
100	—	Gemma 3 4B InstructOpenGoogle	14.7	$0.000	—	—
101	—	Granite 4.0 H 1BOpenIBM	13.7	$0.000	—	—
102	—	Claude 3 SonnetClosedAnthropic	13.3	$6.0	—	—
103	—	Granite 4.0 1BOpenIBM	13.3	$0.000	—	—
104	—	Llama 3 Instruct 70BOpenMeta	13.0	$0.71	—	—
105	—	Gemini 1.0 UltraClosedGoogle	12.8	$0.000	—	—
106	—	Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure	12.7	$0.23	—	—
107	—	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	12.5	$0.000	—	—
108	—	Phi-4 Multimodal InstructOpenMicrosoft Azure	12.4	$0.000	—	—
109	—	LFM2 2.6BOpenLiquid AI	11.8	$0.000	—	—
110	—	Llama 2 Chat 7BOpenMeta	11.3	$0.10	—	—
111	—	Gemma 3n E2B InstructOpenGoogle	11.3	$0.000	—	—
112	—	Llama 3.2 Instruct 3BOpenMeta	11.2	$0.060	—	—
113	—	LFM2 1.2BOpenLiquid AI	9.7	$0.000	—	—
114	—	Claude 2.1ClosedAnthropic	9.7	$0.000	—	—
115	—	Claude 3 HaikuClosedAnthropic	9.6	$0.50	—	—
116	—	Llama 3.2 Instruct 1BOpenMeta	8.9	$0.053	—	—
117	—	Claude 2.0ClosedAnthropic	8.6	$0.000	—	—
118	—	GPT-3.5 TurboClosedOpenAI	8.3	$0.75	—	—
119	—	Granite 4.0 H 350MOpenIBM	8.2	$0.000	—	—
120	—	Granite 4.0 350MOpenIBM	7.7	$0.000	—	—
121	—	Arctic InstructOpenSnowflake	7.6	$0.000	—	—
122	—	LFM 40BClosedLiquid AI	7.3	$0.000	—	—
123	—	Llama 3 Instruct 8BOpenMeta	7.0	$0.073	—	—
124	—	Gemma 3 1B InstructOpenGoogle	6.8	$0.000	—	—
125	—	PALM-2ClosedGoogle	6.6	$0.000	—	—
126	—	Gemini 1.0 ProClosedGoogle	6.2	$0.000	—	—
127	—	Gemma 3 270MOpenGoogle	5.6	$0.000	—	—
128	—	Llama 2 Chat 70BOpenMeta	5.6	$0.000	—	—
129	—	Llama 2 Chat 13BOpenMeta	5.5	$0.000	—	—
130	—	DBRX InstructOpenDatabricks	5.3	$0.000	—	—
131	—	Claude InstantClosedAnthropic	1.0	$0.000	—	—
131	—	Llama 65BOpenMeta	1.0	$0.000	—	—

82 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