Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Gemini 3.1 Pro PreviewClosedGoogle	57.2	$4.5	129	29 s
2	—	GPT-5.4 (xhigh)ClosedOpenAI · 1 more variant	56.8	$5.6	72	206 s
3	—	GPT-5.3 Codex (xhigh)ClosedOpenAI	53.6	$4.8	81	116 s
4	—	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	53.0	$10	40	17 s
5	—	Muse SparkClosedMeta	52.2	—	—	—
6	—	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants	51.7	$6.0	48	94 s
7	—	GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants	51.3	$4.8	69	173 s
8	—	Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant	49.7	$10	45	14 s
9	—	Grok 4.20 0309 v2 (Reasoning)ClosedxAI · 1 more variant	49.3	$3.0	162	13 s
10	—	GPT-5.2 Codex (xhigh)ClosedOpenAI	49.0	$4.8	121	125 s
11	—	GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants	48.9	$1.7	149	9.8 s
12	—	Grok 4.20 0309 (Reasoning)ClosedxAI · 1 more variant	48.5	$3.0	155	17 s
13	—	Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant	48.4	$4.5	130	33 s
14	—	GPT-5.1 (high)ClosedOpenAI · 1 more variant	47.7	$3.4	91	30 s
15	—	Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant	46.4	$1.1	149	7.3 s
16	—	GPT-5 (high)ClosedOpenAI · 4 more variants	44.6	$3.4	85	84 s
16	—	GPT-5 Codex (high)ClosedOpenAI	44.6	$3.4	168	10 s
18	—	GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants	44.0	$0.46	156	4.4 s
19	—	GPT-5.1 Codex (high)ClosedOpenAI	43.1	$3.4	163	8.2 s
20	—	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	43.0	$6.0	40	9.9 s
21	—	Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant	42.0	$30	30	9.9 s
22	—	Grok 4ClosedxAI	41.5	$6.0	55	11 s
23	—	GPT-5 mini (high)ClosedOpenAI · 2 more variants	41.2	$0.69	77	95 s
24	—	o3-proClosedOpenAI	40.7	$35	27	128 s
25	—	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	39.2	$0.000	36	1.7 s
26	—	Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant	39.0	$30	30	7.9 s
27	—	Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	38.7	$6.0	43	11 s
28	—	GPT-5.1 Codex mini (high)ClosedOpenAI	38.6	$0.69	200	7.0 s
29	—	Grok 4.1 Fast (Reasoning)ClosedxAI · 1 more variant	38.6	$0.28	150	7.6 s
30	—	o3ClosedOpenAI	38.4	$3.5	89	8.4 s
31	—	Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant	37.1	$2.0	88	10 s
32	—	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	193	1.1 s
33	—	Nova 2.0 Pro Preview (medium)ClosedAmazon · 2 more variants	35.7	$3.4	128	12 s
34	—	Grok 4 Fast (Reasoning)ClosedxAI · 1 more variant	35.1	$0.28	201	3.0 s
35	—	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	34.7	$6.0	—	—
36	—	Gemini 2.5 ProClosedGoogle	34.6	$3.4	118	25 s
37	—	Nova 2.0 Lite (high)ClosedAmazon · 3 more variants	34.5	$0.85	145	19 s
38	—	Gemini 3.1 Flash-Lite PreviewClosedGoogle	33.5	$0.56	236	7.1 s
39	—	gpt-oss-120B (high)OpenOpenAI · 1 more variant	33.3	$0.26	206	0.9 s
40	—	o4-mini (high)ClosedOpenAI	33.1	$1.9	128	27 s
41	—	Mercury 2ClosedInception	32.8	$0.38	625	4.4 s
42	—	Grok 3 mini Reasoning (high)ClosedxAI	32.1	$0.35	190	0.6 s
43	—	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	31.2	$0.20	—	—
44	—	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants	31.1	—	—	—
45	—	o1ClosedOpenAI · 1 more variant	30.8	$26	87	40 s
46	—	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant	30.3	—	—	—
47	—	Grok Code Fast 1ClosedxAI	28.7	$0.53	140	4.5 s
48	▲ 1	Nemotron Cascade 2 30B A3BOpenNVIDIA	28.4	—	—	—
49	▼ 1	Nova 2.0 Omni (medium)ClosedAmazon · 2 more variants	28.0	$0.85	—	—
50	—	Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant	27.0	$0.85	200	23 s
51	—	GPT-5 nano (high)ClosedOpenAI · 2 more variants	26.8	$0.14	135	64 s
52	—	GPT-4.1ClosedOpenAI	26.3	$3.5	84	1.1 s
53	—	o3-miniClosedOpenAI · 1 more variant	25.9	$1.9	142	8.4 s
54	—	o1-proClosedOpenAI	25.8	$263	—	—
55	—	Grok 3ClosedxAI	25.2	$6.0	67	1.4 s
56	—	Sonar Reasoning ProClosedPerplexity	24.6	—	—	—
57	—	gpt-oss-20B (high)OpenOpenAI · 1 more variant	24.5	$0.10	265	0.7 s
58	—	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	24.3	$0.11	171	2.5 s
59	—	GPT-4.1 miniClosedOpenAI	22.9	$0.70	73	0.9 s
60	—	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle · 1 more variant	21.7	$0.18	—	—
61	—	Grok 3 Reasoning BetaClosedxAI	21.6	—	—	—
62	—	o1-miniClosedOpenAI	20.4	—	—	—
63	—	GPT-4.5 (Preview)ClosedOpenAI	20.0	—	—	—
64	—	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant	19.6	—	—	—
65	—	Nova PremierClosedAmazon	19.0	$5.0	31	3.1 s
66	—	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	18.8	—	—	—
67	—	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	18.7	$0.18	59	1.5 s
68	—	Claude 3.5 HaikuClosedAnthropic	18.7	$1.6	—	—
69	—	GPT-4o (Aug '24)ClosedOpenAI · 4 more variants	18.6	$4.4	86	1.1 s
70	—	Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant	18.5	$0.26	—	—
71	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	18.5	—	—	—
72	—	Llama 4 MaverickOpenMeta	18.4	$0.48	106	1.1 s
73	—	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	18.1	—	—	—
74	—	Claude 3 OpusClosedAnthropic	18.0	$30	—	—
75	—	Sonar ReasoningClosedPerplexity	17.9	—	—	—
76	—	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant	17.6	$0.18	276	26 s
77	—	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	29	2.6 s
78	—	Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant	16.0	—	—	—
79	—	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant	15.9	$6.0	—	—
80	—	SonarClosedPerplexity	15.5	—	—	—
81	—	Sonar ProClosedPerplexity	15.2	—	—	—
82	—	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	15.2	—	—	—
83	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	42	2.5 s
84	—	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	14.9	$0.30	133	0.9 s
85	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	14.8	$0.070	132	0.7 s
86	—	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant	14.7	—	—	—
87	—	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
88	—	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.62	87	1.4 s
89	—	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
90	—	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
91	—	Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant	13.8	—	—	—
92	—	GPT-4 TurboClosedOpenAI	13.7	$15	26	2.8 s
93	—	Llama 4 ScoutOpenMeta	13.5	$0.29	127	0.8 s
94	—	Nova ProClosedAmazon	13.5	$1.4	—	—
95	—	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	37	1.9 s
96	—	Grok BetaClosedxAI	13.3	—	—	—
97	—	GPT-4.1 nanoClosedOpenAI	13.0	$0.18	172	0.7 s
98	—	GPT-4ClosedOpenAI	12.8	$38	—	—
99	—	Nova LiteClosedAmazon	12.7	$0.11	151	1.1 s
100	—	GPT-4o miniClosedOpenAI	12.6	$0.26	33	3.6 s
101	—	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	20	2.1 s
102	—	Claude 3 HaikuClosedAnthropic	12.3	$0.50	134	1.2 s
103	—	R1 1776OpenPerplexity	12.0	—	—	—
104	—	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$0.72	50	1.0 s
105	—	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	143	0.9 s
106	—	Grok-1OpenxAI	11.7	—	—	—
107	—	Gemini 1.5 Flash-8BClosedGoogle	11.1	—	—	—
108	—	Granite 4.0 H SmallOpenIBM	10.8	$0.11	358	10 s
109	—	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	93	0.5 s
110	—	Phi-4OpenMicrosoft Azure	10.4	$0.22	25	2.3 s
111	—	Gemma 3 27B InstructOpenGoogle	10.3	$0.000	26	2.1 s
112	—	Claude 3 SonnetClosedAnthropic	10.3	$6.0	—	—
113	—	Nova MicroClosedAmazon	10.3	$0.061	275	0.9 s
114	—	Gemini 1.0 UltraClosedGoogle	10.1	—	—	—
115	—	Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure	10.1	—	—	—
116	—	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
117	—	Phi-4 Multimodal InstructOpenMicrosoft Azure	10.0	$0.000	16	0.8 s
118	—	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
119	—	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.085	53	1.0 s
120	—	Claude 2.1ClosedAnthropic	9.3	—	—	—
121	—	Claude 2.0ClosedAnthropic	9.1	—	—	—
122	—	GPT-3.5 TurboClosedOpenAI	9.0	$0.75	—	—
123	—	Llama 3 Instruct 70BOpenMeta	8.9	$0.87	—	—
124	—	Arctic InstructOpenSnowflake	8.8	—	—	—
125	—	Gemma 3 12B InstructOpenGoogle	8.8	$0.000	27	30 s
126	—	LFM 40BClosedLiquid AI	8.8	—	—	—
127	—	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.25	50	0.7 s
128	—	PALM-2ClosedGoogle	8.6	—	—	—
129	—	Gemini 1.0 ProClosedGoogle	8.5	—	—	—
130	—	Phi-4 Mini InstructOpenMicrosoft Azure	8.4	$0.000	42	0.9 s
131	—	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
132	—	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
133	—	DBRX InstructOpenDatabricks	8.3	—	—	—
134	—	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
135	—	LFM2 2.6BOpenLiquid AI	8.0	$0.000	—	—
135	—	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
137	—	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
138	—	Gemma 3 270MOpenGoogle	7.7	—	—	—
139	—	Granite 4.0 MicroOpenIBM	7.7	—	—	—
140	—	Claude InstantClosedAnthropic	7.4	—	—	—
140	—	Llama 65BOpenMeta	7.4	—	—	—
142	—	Granite 4.0 1BOpenIBM	7.3	—	—	—
143	—	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
144	—	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	348	23 s
145	—	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	15	1.2 s
145	—	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
147	—	LFM2 1.2BOpenLiquid AI	6.3	$0.000	—	—
148	—	Gemma 3 4B InstructOpenGoogle	6.3	$0.000	27	1.5 s
149	—	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	94	1.1 s
150	—	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	—	—
151	—	Granite 4.0 350MOpenIBM	6.1	—	—	—
152	—	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	38	0.9 s
153	—	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
154	—	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—

104 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