Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)ClosedAnthropic	59.9	$20	60	103 s
2	—	GPT-5.6 Sol (max)ClosedOpenAI · 5 more variants	58.9	$11	72	170 s
3	—	Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic	55.7	$10	56	46 s
4	—	GPT-5.6 Terra (max)ClosedOpenAI · 5 more variants	55.0	$5.6	141	155 s
5	—	GPT-5.5 (xhigh)ClosedOpenAI · 4 more variants	54.8	$11	69	98 s
6	—	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	53.5	$10	47	23 s
7	—	Claude Sonnet 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	53.4	$4.0	77	221 s
8	—	GPT-5.4 (xhigh)ClosedOpenAI · 2 more variants	51.4	$5.6	156	113 s
9	—	GPT-5.6 Luna (max)ClosedOpenAI · 5 more variants	51.2	$2.3	217	99 s
10	—	Muse Spark 1.1 (xhigh)ClosedMeta	50.6	$2.0	119	1.1 s
11	—	Gemini 3.5 Flash (high)ClosedGoogle · 2 more variants	50.2	$3.4	152	24 s
12	—	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants	47.2	$6.0	66	164 s
13	—	Gemini 3.1 Pro PreviewClosedGoogle	46.5	$4.5	128	25 s
14	—	GPT-5.3 Codex (xhigh)ClosedOpenAI	44.3	$4.8	91	75 s
15	—	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	43.7	$10	43	26 s
16	—	Muse SparkClosedMeta	43.1	—	—	—
17	—	GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants	42.2	$4.8	74	150 s
18	—	Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant	40.8	$10	48	17 s
19	—	GPT-5.2 Codex (xhigh)ClosedOpenAI	40.1	$4.8	160	74 s
20	—	GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants	40.0	$1.7	164	9.2 s
21	—	Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant	39.6	$4.5	—	—
22	—	GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants	38.2	$0.46	171	7.4 s
23	—	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	37.8	$1.2	194	1.1 s
24	—	Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant	37.8	$1.1	172	6.9 s
25	—	GPT-5.1 (high)ClosedOpenAI · 1 more variant	36.9	$3.4	101	40 s
26	—	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	36.4	$6.0	41	14 s
27	—	GPT-5 Codex (high)ClosedOpenAI	36.1	$3.4	172	8.5 s
28	—	GPT-5.1 Codex (high)ClosedOpenAI	34.7	$3.4	167	7.7 s
29	—	GPT-5 (high)ClosedOpenAI · 4 more variants	34.7	$3.4	87	81 s
30	—	Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant	33.7	$30	29	15 s
31	—	GPT-5.5 Instant (May 2026)ClosedOpenAI · 1 more variant	33.5	$11	—	—
32	—	o3-proClosedOpenAI	32.5	$35	36	68 s
33	—	Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant	31.0	$30	—	—
34	—	GPT-5 mini (medium)ClosedOpenAI · 2 more variants	30.9	$0.69	105	17 s
35	—	GPT-5.1 Codex mini (high)ClosedOpenAI	30.6	$0.69	207	14 s
36	—	o3ClosedOpenAI	30.4	$3.5	123	6.0 s
37	—	Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant	29.6	$2.0	102	19 s
38	—	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	29.4	$0.000	35	1.1 s
39	—	Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	28.9	$6.0	—	—
40	—	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	27.1	—	—	—
41	—	Gemini 2.5 ProClosedGoogle	25.8	$3.4	139	19 s
42	—	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	25.7	$0.20	—	—
43	—	o4-mini (high)ClosedOpenAI	25.6	$1.9	165	23 s
44	—	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	25.4	$0.38	146	1.1 s
45	—	Mercury 2ClosedInception	25.3	$0.38	783	3.0 s
46	—	Gemini 3.1 Flash-LiteClosedGoogle	25.0	$0.56	272	5.8 s
47	—	gpt-oss-120b (high)OpenOpenAI · 1 more variant	23.8	$0.26	319	0.8 s
48	—	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants	23.8	—	—	—
49	—	o1ClosedOpenAI · 1 more variant	23.4	$26	101	30 s
50	—	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant	23.0	—	—	—
51	—	Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant	22.0	$0.15	71	2.5 s
52	—	Nova 2.0 Pro Preview (medium)ClosedAmazon · 2 more variants	21.8	$3.4	126	15 s
53	—	Nemotron Cascade 2 30B A3BOpenNVIDIA	21.3	—	—	—
54	—	Apriel-v1.5-15B-ThinkerOpenServiceNow	21.2	$0.000	—	—
55	—	Nova 2.0 Omni (medium)ClosedAmazon · 2 more variants	20.9	$0.85	—	—
56	—	Apriel-v1.6-15B-ThinkerOpenServiceNow	20.5	$0.000	—	—
57	—	Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant	20.1	$0.85	211	15 s
58	—	GPT-5 nano (high)ClosedOpenAI · 2 more variants	19.9	$0.14	152	101 s
59	—	GPT-4.1ClosedOpenAI	19.4	$3.5	109	0.9 s
60	—	Nova 2.0 Lite (medium)ClosedAmazon · 3 more variants	19.0	$0.85	149	17 s
61	—	o3-miniClosedOpenAI · 1 more variant	19.0	$1.9	226	6.2 s
62	—	o1-proClosedOpenAI	18.9	$263	—	—
63	—	Sonar Reasoning ProClosedPerplexity	17.8	—	—	—
64	—	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle · 1 more variant	15.1	$0.18	—	—
65	—	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	14.9	$0.13	313	1.0 s
66	—	gpt-oss-20b (high)OpenOpenAI · 1 more variant	14.9	$0.088	218	0.8 s
67	—	GPT-4.1 miniClosedOpenAI	14.8	$0.70	78	0.9 s
68	—	Llama 4 MaverickOpenMeta	14.3	$0.48	118	1.0 s
69	—	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	14.2	$0.088	107	1.4 s
70	—	o1-miniClosedOpenAI	14.0	—	—	—
71	—	GPT-4.5 (Preview)ClosedOpenAI	13.6	—	—	—
72	—	DiffusionGemma 26B A4BOpenGoogle	13.5	—	—	—
73	—	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant	13.3	—	—	—
74	—	Nova PremierClosedAmazon	12.7	$5.0	35	2.9 s
75	—	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	12.5	—	—	—
76	—	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	12.4	$0.40	50	1.2 s
77	—	GPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI · 4 more variants	12.3	—	—	—
78	—	Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant	12.3	$0.26	—	—
79	—	Claude 3.5 HaikuClosedAnthropic	12.3	$1.6	—	—
80	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	12.2	—	—	—
81	—	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	11.8	—	—	—
82	—	Claude 3 OpusClosedAnthropic	11.8	$30	—	—
83	—	Sonar ReasoningClosedPerplexity	11.7	—	—	—
84	—	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant	11.4	$0.18	223	26 s
85	—	Llama 4 ScoutOpenMeta	10.0	$0.29	115	0.9 s
86	—	Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant	10.0	—	—	—
87	—	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant	9.9	$6.0	—	—
88	—	GPT-4.1 nanoClosedOpenAI	9.6	$0.18	154	0.7 s
89	—	SonarClosedPerplexity	9.5	—	—	—
90	—	Llama 3.3 Instruct 70BOpenMeta	9.4	$0.61	90	1.6 s
91	—	Sonar ProClosedPerplexity	9.3	—	—	—
92	—	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	9.3	—	—	—
93	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	9.1	$0.90	51	2.4 s
94	—	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	9.0	$0.30	285	0.4 s
95	—	Granite 4.1 30BOpenIBM	8.9	—	—	—
96	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	8.8	$0.070	86	6.4 s
97	—	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant	8.8	—	—	—
98	—	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	8.7	—	—	—
99	—	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	8.5	—	—	—
100	—	Llama 3.1 Instruct 405BOpenMeta	8.5	$3.7	75	2.4 s
101	—	LFM2.5-8B-A1BOpenLiquid AI	8.3	$0.000	338	5.2 s
102	—	Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant	8.0	—	—	—
103	—	GPT-4 TurboClosedOpenAI	7.9	$15	32	2.8 s
104	—	Nova ProClosedAmazon	7.7	$1.4	—	—
105	—	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	7.6	$1.2	300	5.5 s
106	—	Llama 3.1 Instruct 8BOpenMeta	7.6	$0.080	155	0.9 s
107	—	Gemma 3 27B InstructOpenGoogle	7.4	$0.000	—	—
108	—	GPT-4ClosedOpenAI	7.0	$38	—	—
109	—	Nova LiteClosedAmazon	6.9	$0.11	181	1.0 s
110	—	GPT-4o miniClosedOpenAI	6.9	$0.26	67	0.9 s
111	—	Llama 3.1 Instruct 70BOpenMeta	6.8	$0.56	33	1.8 s
112	—	Granite 4.1 8BOpenIBM	6.7	$0.063	121	0.8 s
113	—	R1 1776OpenPerplexity	6.3	—	—	—
114	—	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.2	$1.4	60	1.2 s
115	—	Phi-4 Mini InstructOpenMicrosoft	6.0	$0.000	45	0.8 s
116	—	Gemini 1.5 Flash-8BClosedGoogle	5.5	—	—	—
117	—	Gemma 3 12B InstructOpenGoogle	5.5	$0.000	—	—
118	—	Granite 4.0 H SmallOpenIBM	5.2	$0.11	386	11 s
119	—	LFM2 24B A2BOpenLiquid AI	4.9	$0.053	—	—
120	—	Phi-4OpenMicrosoft	4.9	$0.22	25	2.2 s
121	—	Claude 3 SonnetClosedAnthropic	4.7	$6.0	—	—
122	—	Nova MicroClosedAmazon	4.7	$0.061	290	1.1 s
123	—	Granite 4.1 3BOpenIBM	4.7	—	—	—
124	—	Gemini 1.0 UltraClosedGoogle	4.6	—	—	—
125	—	Phi-3 Mini Instruct 3.8BOpenMicrosoft	4.6	—	—	—
126	—	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	4.6	—	—	—
127	—	Phi-4 Multimodal InstructOpenMicrosoft	4.5	$0.000	18	0.8 s
128	—	Llama 2 Chat 7BOpenMeta	4.3	$0.10	—	—
129	—	Llama 3.2 Instruct 3BOpenMeta	4.2	$0.15	52	1.1 s
130	—	Claude 2.1ClosedAnthropic	3.9	—	—	—
131	—	Claude 3 HaikuClosedAnthropic	3.9	$0.50	—	—
132	—	Claude 2.0ClosedAnthropic	3.6	—	—	—
133	—	GPT-3.5 TurboClosedOpenAI	3.6	$0.75	—	—
134	—	Llama 3 Instruct 70BOpenMeta	3.5	$1.2	—	—
135	—	Arctic InstructOpenSnowflake	3.4	—	—	—
136	—	LFM 40BClosedLiquid AI	3.4	—	—	—
137	—	Llama 3.2 Instruct 11B (Vision)OpenMeta	3.3	$0.35	52	0.7 s
138	—	PALM-2ClosedGoogle	3.2	—	—	—
139	—	Gemini 1.0 ProClosedGoogle	3.1	—	—	—
140	—	Llama 2 Chat 70BOpenMeta	3.0	—	—	—
141	—	Llama 2 Chat 13BOpenMeta	3.0	—	—	—
142	—	DBRX InstructOpenDatabricks	3.0	—	—	—
143	—	LFM2.5-1.2B-ThinkingOpenLiquid AI	2.7	—	—	—
144	—	LFM2 2.6BOpenLiquid AI	2.7	—	—	—
145	—	LFM2.5-1.2B-InstructOpenLiquid AI	2.7	—	—	—
146	—	Granite 4.0 H 1BOpenIBM	2.7	—	—	—
147	—	Gemma 3 270MOpenGoogle	2.4	—	—	—
148	—	Granite 4.0 MicroOpenIBM	2.4	—	—	—
149	—	Claude InstantClosedAnthropic	2.1	—	—	—
149	—	Llama 65BOpenMeta	2.1	—	—	—
151	—	Granite 4.0 1BOpenIBM	2.1	—	—	—
152	—	LFM2 8B A1BOpenLiquid AI	1.8	—	—	—
153	—	Granite 3.3 8B (Non-reasoning)OpenIBM	1.8	$0.085	326	26 s
154	—	Llama 3 Instruct 8BOpenMeta	1.2	$0.070	—	—
155	—	Gemma 3n E4B InstructOpenGoogle	1.2	$0.025	57	1.2 s
156	—	LFM2 1.2BOpenLiquid AI	1.1	—	—	—
157	—	Gemma 3 4B InstructOpenGoogle	1.1	$0.000	—	—
158	—	Llama 3.2 Instruct 1BOpenMeta	1.1	$0.050	85	0.9 s
159	—	LFM2.5-VL-1.6BOpenLiquid AI	1.0	$0.000	438	11 s
160	—	Gemma 3 1B InstructOpenGoogle	1.0	$0.000	—	—
160	—	Gemma 3n E2B InstructOpenGoogle	1.0	$0.000	—	—
160	—	Granite 4.0 350MOpenIBM	1.0	—	—	—
160	—	Granite 4.0 H 350MOpenIBM	1.0	—	—	—

113 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