Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	o1-2024-12-17ClosedOpenAI	1,323	±6	9,230	—
2	—	o1-previewClosedOpenAI	1,303	±4	33,186	—
3	—	claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant	1,286	±4	48,847	—
4	—	gemini-1.5-pro-002ClosedGoogle	1,269	±4	46,621	—
5	—	gpt-4o-2024-05-13ClosedOpenAI	1,263	±3	117,745	—
6	—	o1-miniClosedOpenAI	1,257	±3	49,952	—
7	▲ 1	llama-3.1-405b-instruct-bf16OpenMeta	1,254	±4	22,703	—
8	▼ 1	gemini-advanced-0514ClosedGoogle	1,254	±3	52,145	—
9	—	llama-3.1-405b-instruct-fp8OpenMeta	1,253	±3	63,187	—
10	—	gpt-4o-2024-08-06ClosedOpenAI	1,250	±3	47,975	—
11	—	grok-2-2024-08-13ClosedxAI	1,249	±3	67,150	—
12	—	gpt-4-turbo-2024-04-09ClosedOpenAI	1,242	±3	102,125	—
13	—	gemini-1.5-pro-001ClosedGoogle	1,241	±3	82,433	—
14	—	claude-3-opus-20240229ClosedAnthropic	1,239	±2	202,713	—
15	▲ 3	claude-3-5-haiku-20241022ClosedAnthropic	1,235	±6	12,181	—
16	—	gpt-4o-mini-2024-07-18ClosedOpenAI	1,235	±3	61,233	—
17	▼ 2	llama-3.3-70b-instructOpenMeta	1,235	±5	16,905	—
18	▼ 1	gpt-4-1106-previewClosedOpenAI	1,235	±3	103,732	—
19	—	gpt-4-0125-previewClosedOpenAI	1,231	±3	97,064	—
20	—	gemini-1.5-flash-002ClosedGoogle	1,230	±4	35,199	—
21	—	grok-2-mini-2024-08-13ClosedxAI	1,225	±3	55,507	—
22	—	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,217	±6	7,598	—
23	—	llama-3.1-70b-instructOpenMeta	1,214	±3	58,785	—
24	—	llama-3.1-tulu-3-70bOpenAi2	1,209	±10	3,031	—
25	▲ 1	gemma-2-27b-itOpenGoogle	1,208	±3	73,168	—
26	▼ 1	amazon-nova-pro-v1.0ClosedAmazon	1,207	±5	13,738	—
27	—	gemini-1.5-flash-001ClosedGoogle	1,205	±3	65,656	—
28	—	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,204	±8	3,898	—
29	—	gpt-4-0314ClosedOpenAI	1,200	±3	55,956	—
30	—	claude-3-sonnet-20240229ClosedAnthropic	1,197	±3	113,011	—
31	—	nemotron-4-340b-instructOpenNVIDIA	1,196	±4	20,604	—
32	—	llama-3-70b-instructOpenMeta	1,195	±2	163,809	—
33	—	gpt-4-0613ClosedOpenAI	1,185	±3	91,646	—
34	—	amazon-nova-lite-v1.0ClosedAmazon	1,184	±5	11,563	—
35	—	phi-4OpenMicrosoft	1,184	±8	4,039	—
36	▲ 1	gemma-2-9b-itOpenGoogle	1,180	±3	50,951	—
37	▼ 1	gemini-1.5-flash-8b-001ClosedGoogle	1,180	±4	36,856	—
38	—	claude-3-haiku-20240307ClosedAnthropic	1,178	±3	122,299	—
39	—	amazon-nova-micro-v1.0ClosedAmazon	1,163	±5	11,643	—
40	—	gemini-pro-dev-apiClosedGoogle	1,147	±5	18,792	—
41	—	llama-3.1-tulu-3-8bOpenAi2	1,147	±10	3,079	—
42	—	llama-3-8b-instructOpenMeta	1,143	±2	109,237	—
43	—	gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant	1,137	±3	68,861	—
44	▲ 2	granite-3.1-8b-instructOpenIBM	1,135	±9	3,064	—
45	▼ 1	llama-3.1-8b-instructOpenMeta	1,133	±3	52,651	—
46	▼ 1	gemini-proClosedGoogle	1,131	±7	6,559	—
47	—	phi-3-medium-4k-instructOpenMicrosoft	1,118	±4	26,110	—
48	—	gemma-2-2b-itOpenGoogle	1,117	±3	42,631	—
49	—	dbrx-instruct-previewOpenDatabricks	1,113	±4	33,730	—
50	—	granite-3.0-8b-instructOpenIBM	1,110	±8	7,002	—
51	—	wizardlm-70bOpenMicrosoft	1,105	±6	8,379	—
52	▲ 1	granite-3.1-2b-instructOpenIBM	1,103	±9	3,127	—
53	▼ 1	snowflake-arctic-instructOpenSnowflake	1,102	±3	34,173	—
54	—	gemma-1.1-7b-itOpenGoogle	1,099	±4	25,059	—
55	—	phi-3-small-8k-instructOpenMicrosoft	1,098	±4	18,478	—
56	—	llama-3.2-3b-instructOpenMeta	1,093	±6	8,403	—
57	—	granite-3.0-2b-instructOpenIBM	1,082	±8	7,195	—
58	—	llama-2-70b-chatOpenMeta	1,082	±4	39,634	—
59	—	llama2-70b-steerlm-chatOpenNVIDIA	1,074	±10	3,637	—
60	—	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,068	±5	12,818	—
61	—	wizardlm-13bOpenMicrosoft	1,063	±7	7,177	—
62	—	phi-3-mini-4k-instructOpenMicrosoft	1,056	±5	21,095	—
63	—	llama-2-13b-chatOpenMeta	1,054	±5	19,736	—
64	—	phi-3-mini-128k-instructOpenMicrosoft	1,049	±4	21,627	—
65	—	gemma-7b-itOpenGoogle	1,048	±7	9,174	—
66	—	codellama-34b-instructOpenMeta	1,047	±7	7,512	—
67	—	llama-3.2-1b-instructOpenMeta	1,045	±7	8,531	—
68	—	palm-2ClosedGoogle	1,042	±7	8,743	—
69	—	gemma-1.1-2b-itOpenGoogle	1,040	±6	11,346	—
70	—	codellama-70b-instructOpenMeta	1,040	±16	1,193	—
71	—	llama-2-7b-chatOpenMeta	1,025	±5	14,553	—
72	—	gemma-2b-itOpenGoogle	1,007	±7	4,921	—
73	—	olmo-7b-instructOpenAi2	994	±6	6,508	—
74	—	dolly-v2-12bOpenDatabricks	881	±11	3,485	—
75	—	llama-13bOpenMeta	867	±13	2,444	—

25 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