Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	o1-2024-12-17ClosedOpenAI	1,323	±7	5,223	—
2	—	o1-previewClosedOpenAI	1,303	±3	33,195	—
3	—	claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant	1,285	±3	44,399	—
4	—	gemini-1.5-pro-002ClosedGoogle	1,269	±3	42,041	—
5	—	gpt-4o-2024-05-13ClosedOpenAI	1,263	±2	117,780	—
6	—	o1-miniClosedOpenAI	1,258	±3	45,635	—
7	—	gemini-advanced-0514ClosedGoogle	1,254	±3	52,142	—
8	—	llama-3.1-405b-instruct-fp8OpenMeta	1,253	±3	63,222	—
9	—	llama-3.1-405b-instruct-bf16OpenMeta	1,253	±4	18,184	—
10	—	gpt-4o-2024-08-06ClosedOpenAI	1,250	±3	47,980	—
11	—	grok-2-2024-08-13ClosedxAI	1,249	±3	63,635	—
12	—	gpt-4-turbo-2024-04-09ClosedOpenAI	1,242	±2	102,135	—
13	—	gemini-1.5-pro-001ClosedGoogle	1,241	±3	82,451	—
14	—	claude-3-opus-20240229ClosedAnthropic	1,239	±2	201,772	—
15	—	gpt-4o-mini-2024-07-18ClosedOpenAI	1,235	±3	58,963	—
16	—	llama-3.3-70b-instructOpenMeta	1,235	±5	12,451	—
17	—	gpt-4-1106-previewClosedOpenAI	1,235	±2	103,742	—
18	—	claude-3-5-haiku-20241022ClosedAnthropic	1,234	±6	7,681	—
19	—	gpt-4-0125-previewClosedOpenAI	1,231	±2	97,078	—
20	—	gemini-1.5-flash-002ClosedGoogle	1,230	±3	32,994	—
21	—	grok-2-mini-2024-08-13ClosedxAI	1,224	±3	53,444	—
22	—	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,217	±6	7,603	—
23	—	llama-3.1-70b-instructOpenMeta	1,214	±3	58,806	—
24	—	llama-3.1-tulu-3-70bOpenAi2	1,211	±11	2,054	—
25	—	amazon-nova-pro-v1.0ClosedAmazon	1,208	±6	10,935	—
26	—	gemma-2-27b-itOpenGoogle	1,207	±3	70,811	—
27	—	gemini-1.5-flash-001ClosedGoogle	1,204	±3	65,650	—
28	—	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,204	±9	3,897	—
29	—	gpt-4-0314ClosedOpenAI	1,200	±3	55,981	—
30	—	claude-3-sonnet-20240229ClosedAnthropic	1,197	±2	113,029	—
31	—	nemotron-4-340b-instructOpenNVIDIA	1,196	±4	20,615	—
32	—	llama-3-70b-instructOpenMeta	1,195	±2	163,781	—
33	—	gpt-4-0613ClosedOpenAI	1,185	±2	91,645	—
34	—	amazon-nova-lite-v1.0ClosedAmazon	1,184	±5	9,319	—
35	—	gemma-2-9b-itOpenGoogle	1,179	±3	48,642	—
36	—	gemini-1.5-flash-8b-001ClosedGoogle	1,179	±4	34,691	—
37	—	claude-3-haiku-20240307ClosedAnthropic	1,178	±2	122,318	—
38	—	amazon-nova-micro-v1.0ClosedAmazon	1,162	±5	9,363	—
39	—	llama-3.1-tulu-3-8bOpenAi2	1,150	±12	2,040	—
40	—	gemini-pro-dev-apiClosedGoogle	1,147	±4	18,796	—
41	—	llama-3-8b-instructOpenMeta	1,143	±3	109,217	—
42	—	gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant	1,137	±2	68,864	—
43	—	llama-3.1-8b-instructOpenMeta	1,133	±3	52,649	—
44	—	gemini-proClosedGoogle	1,131	±7	6,559	—
45	—	phi-3-medium-4k-instructOpenMicrosoft	1,118	±4	26,106	—
46	—	gemma-2-2b-itOpenGoogle	1,116	±3	40,232	—
47	—	dbrx-instruct-previewOpenDatabricks	1,113	±3	33,731	—
48	—	granite-3.0-8b-instructOpenIBM	1,110	±7	7,003	—
49	—	wizardlm-70bOpenMicrosoft	1,105	±6	8,382	—
50	—	snowflake-arctic-instructOpenSnowflake	1,103	±4	34,181	—
51	—	gemma-1.1-7b-itOpenGoogle	1,099	±4	25,062	—
52	—	phi-3-small-8k-instructOpenMicrosoft	1,098	±4	18,479	—
53	—	llama-3.2-3b-instructOpenMeta	1,094	±6	8,413	—
54	—	granite-3.0-2b-instructOpenIBM	1,082	±7	7,195	—
55	—	llama-2-70b-chatOpenMeta	1,082	±3	39,640	—
56	—	llama2-70b-steerlm-chatOpenNVIDIA	1,074	±8	3,637	—
57	—	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,068	±5	12,820	—
58	—	wizardlm-13bOpenMicrosoft	1,063	±7	7,180	—
59	—	phi-3-mini-4k-instructOpenMicrosoft	1,056	±4	21,090	—
60	—	llama-2-13b-chatOpenMeta	1,054	±4	19,741	—
61	—	phi-3-mini-128k-instructOpenMicrosoft	1,049	±4	21,620	—
62	—	gemma-7b-itOpenGoogle	1,048	±6	9,177	—
63	—	codellama-34b-instructOpenMeta	1,047	±7	7,511	—
64	—	llama-3.2-1b-instructOpenMeta	1,045	±6	8,533	—
65	—	palm-2ClosedGoogle	1,042	±7	8,741	—
66	—	gemma-1.1-2b-itOpenGoogle	1,040	±5	11,352	—
67	—	codellama-70b-instructOpenMeta	1,038	±14	1,194	—
68	—	llama-2-7b-chatOpenMeta	1,025	±5	14,548	—
69	—	gemma-2b-itOpenGoogle	1,008	±10	4,919	—
70	—	olmo-7b-instructOpenAi2	994	±7	6,507	—
71	—	dolly-v2-12bOpenDatabricks	881	±9	3,485	—
72	—	llama-13bOpenMeta	867	±12	2,445	—

22 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